@misc{aessi-an-around-ear-silent-speech-interface-for-cross-day-online-reuse-without-test-day-calibrat,
  title = {AESSI: An Around-Ear Silent Speech Interface for Cross-Day Online Reuse without Test-Day Calibration},
  author = {Xiran Xu and Mochu Dong and Yujie Yan and Chenxi Wang and Yu Jiao and Jing Chen},
  year = {2026},
  note = {arXiv},
  eprint = {2609.21436},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.21436v1},
}

@misc{multi-subject-pretraining-enables-short-calibration-personalization-for-closed-corpus-surface-emg-speech-decoding,
  title = {Multi-Subject Pretraining Enables Short-Calibration Personalization for Closed-Corpus Surface EMG Speech Decoding},
  author = {Chenqian Le and Beatrice Fumagalli and Yasamin Esmaeili and Xupeng Chen and Tianyu He and Nikasadat Emami and Adeen Flinker and Yao Wang},
  year = {2026},
  note = {arXiv},
  eprint = {2609.21288},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2609.21288v1},
}

@misc{avsrbench-a-multi-condition-avsr-benchmark,
  title = {AVSRBench: A Multi-Condition AVSR Benchmark},
  author = {Rishabh Jain and Naomi Harte},
  year = {2026},
  note = {arXiv},
  eprint = {2609.10366},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2609.10366v1},
}

@misc{brain2speech-net-intelligible-real-time-brain-to-speech-synthesis-without-text-decoding,
  title = {Brain2Speech-Net: Intelligible, Real-Time Brain-to-Speech Synthesis Without Text Decoding},
  author = {Shreeram Suresh Chandra and Zexin Cai and Yu Tsao and Simon King and Berrak Sisman},
  year = {2026},
  note = {arXiv},
  eprint = {2609.04455},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2609.04455v1},
}

@misc{soft-active-electromyography-interface-for-machine-learning-enabled-silent-speech-recognition,
  title = {Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognition},
  author = {Yuta Kurotaki and Shusuke Yamakoshi and Reitaro Yoshida and Yutaka Isoda and Tamami Takano and Yuji Isano and Yusuke Miyake and Kentaro Kuribayashi and Hiroki Ota},
  year = {2026},
  note = {arXiv},
  eprint = {2608.27048},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2608.27048v1},
}

@misc{sonispeech-a-large-scale-open-vocabulary-tri-modal-dataset-for-wearable-silent-speech-interfaces,
  title = {SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces},
  author = {Ruidong Zhang and Jiacheng Liu and François Guimbretière and Cheng Zhang},
  year = {2026},
  note = {arXiv},
  eprint = {2608.00803},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2608.00803v1},
}

@misc{do-eeg-foundation-models-transfer-to-speech-a-benchmark-on-overt-and-imagined-speech-decoding,
  title = {Do EEG Foundation Models Transfer to Speech? A Benchmark on Overt and Imagined Speech Decoding},
  author = {Owais Mujtaba Khanday and Mohamed Baha Ben Ticha and Sanae Belfrouh and Marc Ouellet and Jose A. Gonzalez-Lopez},
  year = {2026},
  note = {arXiv},
  eprint = {2607.27268},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2607.27268v2},
}

@misc{cs-ets-chaos-inspired-samba-based-emg-to-speech-synthesis-with-nonlinear-chaotic-losses,
  title = {CS-ETS: Chaos-Inspired Samba-Based EMG-To-Speech Synthesis with Nonlinear Chaotic Losses},
  author = {Sajid Fardin Dipto and Tarikul Islam Tamiti and David Vergano and Luke Baja-Ricketts and Anomadarshi Barua},
  year = {2026},
  note = {arXiv},
  eprint = {2607.18629},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2607.18629v1},
}

@misc{physiological-noise-augmentation-improves-non-invasive-brain-to-speech,
  title = {Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech},
  author = {Benjamin Ballyk and Teyun Kwon and Miran Özdogan and Oiwi Parker Jones},
  year = {2026},
  note = {arXiv},
  eprint = {2607.05165},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2607.05165v1},
}

@misc{eeg-based-imagined-speech-decoding-using-a-hybrid-cnn-snn-architecture,
  title = {EEG-Based Imagined Speech Decoding Using a Hybrid CNN-SNN Architecture},
  author = {Fatima Shalhoub and Mariam Al Mawla and Kabalan Chaccour and Iván López-Espejo and Hoda Fares},
  year = {2026},
  note = {arXiv},
  eprint = {2607.03844},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2607.03844v1},
}

@misc{lipsflow-a-first-exploration-of-neuromorphic-ot-cfm-for-multi-speaker-vsr,
  title = {A First Exploration of Neuromorphic OT-CFM for Multi-Speaker VSR},
  author = {Lin Chen and Jingping Fang and Hairui Liu and Chenyang Xu and Junhao Chen and Xiaorui Li and Weidong Cai and Xiaoming Chen},
  year = {2026},
  note = {ECCV 2026},
  doi = {10.1007/978-3-032-37281-9_8},
  eprint = {2606.31225},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1007/978-3-032-37281-9_8},
}

@misc{cross-modal-masking-for-robust-silent-speech-synthesis-using-semg-and-lipreading,
  title = {Cross-Modal Masking for Robust Silent Speech Synthesis Using sEMG and Lipreading},
  author = {Eder del Blanco and David Gimeno-Gómez and Eva Navas and Carlos-D Martínez-Hinarejos and Inma Hernáez},
  year = {2026},
  note = {arXiv},
  eprint = {2606.09667},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2606.09667v1},
}

@misc{a-1000-hour-eeg-emg-audio-dataset-of-japanese-speech-production,
  title = {A 1000-hour EEG-EMG-audio dataset of Japanese speech production},
  author = {Motoshige Sato and Ilya Horiguchi and Masakazu Inoue and Kenichi Tomeoka and Eri Hatakeyama and Yuya Kita and Atsushi Yamamoto and Ippei Fujisawa and Shuntaro Sasai},
  year = {2026},
  note = {arXiv},
  eprint = {2606.01264},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2606.01264v1},
}

@misc{zero-shot-imagined-speech-decoding-via-imagined-to-listened-meg-mapping,
  title = {Zero-Shot Imagined Speech Decoding via Imagined-to-Listened MEG Mapping},
  author = {Maryam Maghsoudi and Shihab Shamma},
  year = {2026},
  note = {arXiv},
  eprint = {2605.08075},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2605.08075v1},
}

@misc{articulatory-movements-influence-electromagnetic-wave-transmission-through-the-vocal-tract,
  title = {Articulatory movements influence electromagnetic wave transmission through the vocal tract},
  author = {Rémi Blandin and Martin Laabs and Rudolf von Bünau and Bryn Lloyd and Silvia Farcito and Denys Nikolayev and Gabriela Hossu and Peter Birkholz and Dirk Plettemeier},
  year = {2026},
  note = {arXiv},
  eprint = {2604.19362},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2604.19362v3},
}

@misc{comparison-of-semg-encoding-accuracy-across-speech-modes-using-articulatory-and-phoneme-features,
  title = {Comparison of sEMG Encoding Accuracy Across Speech Modes Using Articulatory and Phoneme Features},
  author = {Chenqian Le and Ruisi Li and Beatrice Fumagalli and Yasamin Esmaeili and Xupeng Chen and Amirhossein Khalilian-Gourtani and Tianyu He and Adeen Flinker and Yao Wang},
  year = {2026},
  note = {arXiv},
  eprint = {2604.18920},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2604.18920v2},
}

@misc{iphoneme-brain-to-text-communication-for-als-using-conformerxl-decoding,
  title = {iPhoneme: Brain-to-Text Communication for ALS Using ConformerXL Decoding},
  author = {Yoonmin Cha and Dawit Chun and Sung Goon Park},
  year = {2026},
  note = {arXiv},
  eprint = {2604.16441},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2604.16441v1},
}

@misc{brain-to-speech-prosody-feature-engineering-and-transformer-based-reconstruction,
  title = {Brain-to-Speech: Prosody Feature Engineering and Transformer-Based Reconstruction},
  author = {Mohammed Salah Al-Radhi and Géza Németh and Andon Tchechmedjiev and Binbin Xu},
  year = {2026},
  note = {arXiv},
  eprint = {2604.05751},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2604.05751v1},
}

@misc{toward-robust-reproducible-and-widely-accessible-intracranial-language-brain-computer-interfaces,
  title = {Toward Robust, Reproducible, and Widely Accessible Intracranial Language Brain-Computer Interfaces: A Comprehensive Review of Neural Mechanisms, Hardware, Algorithms, Evaluation, Clinical Pathways and Future Directions},
  author = {Dongyi He and Wai Ting Siok and Nizhuan Wang},
  year = {2026},
  note = {arXiv},
  eprint = {2603.12279},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2603.12279v2},
}

@misc{silent-speech-interfaces-in-the-era-of-large-language-models-a-comprehensive-taxonomy-and-system,
  title = {Silent Speech Interfaces in the Era of Large Language Models: A Comprehensive Taxonomy and Systematic Review},
  author = {Kele Xu and Yifan Wang and Ming Feng and Qisheng Xu and Wuyang Chen and Yutao Dou and Cheng Yang and Huaimin Wang},
  year = {2026},
  note = {arXiv},
  eprint = {2603.11877},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2603.11877v1},
}

@misc{affect-decoding-in-phonated-and-silent-speech-production-from-surface-emg,
  title = {Affect Decoding in Phonated and Silent Speech Production from Surface EMG},
  author = {Simon Pistrosch and Kleanthis Avramidis and Zhao Ren and Tiantian Feng and Jihwan Lee and Monica Gonzalez-Machorro and A. Batliner and Tanja Schultz and Shrikanth Narayanan and Björn W. Schuller},
  year = {2026},
  note = {arXiv},
  eprint = {2603.11715},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2603.11715v2},
}

@misc{nasovoce,
  title = {NasoVoce: A Nose-Mounted Low-Audibility Speech Interface for Always-Available Speech Interaction},
  author = {Jun Rekimoto and Yu Nishimura and Bojian Yang},
  year = {2026},
  note = {CHI '26 / arXiv},
  doi = {10.1145/3772318.3791397},
  eprint = {2603.10324},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1145/3772318.3791397},
}

@misc{silentwear-an-ultra-low-power-wearable-system-for-emg-based-silent-speech-recognition,
  title = {SilentWear: an Ultra-Low Power Wearable System for EMG-based Silent Speech Recognition},
  author = {Giusy Spacone and Sebastian Frey and Giovanni Pollo and Alessio Burrello and Daniele Jahier Pagliari and Victor Kartsch and Andrea Cossettini and Luca Benini},
  year = {2026},
  note = {arXiv},
  eprint = {2603.02847},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2603.02847v2},
}

@misc{relating-the-neural-representations-of-vocalized-mimed-and-imagined-speech,
  title = {Relating the Neural Representations of Vocalized, Mimed, and Imagined Speech},
  author = {Maryam Maghsoudi and Rupesh Chillale and Shihab A. Shamma},
  year = {2026},
  note = {arXiv},
  eprint = {2602.22597},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2602.22597v1},
}

@misc{sld-l2s-hierarchical-subspace-latent-diffusion-for-high-fidelity-lip-to-speech-synthesis,
  title = {SLD-L2S: Hierarchical Subspace Latent Diffusion for High-Fidelity Lip to Speech Synthesis},
  author = {Yifan Liang and Andong Li and Kang Yang and Guochen Yu and Fangkun Liu and Lingling Dai and Xiaodong Li and Chengshi Zheng},
  year = {2026},
  note = {arXiv},
  eprint = {2602.11477},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2602.11477v1},
}

@misc{emg-to-speech-with-fewer-channels,
  title = {EMG-to-Speech with Fewer Channels},
  author = {Injune Hwang and Jaejun Lee and Kyogu Lee},
  year = {2026},
  note = {arXiv},
  eprint = {2602.06460},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2602.06460v1},
}

@misc{lipsody-lip-to-speech-synthesis-with-enhanced-prosody-consistency,
  title = {LipSody: Lip-to-Speech Synthesis with Enhanced Prosody Consistency},
  author = {Jaejun Lee and Yoori Oh and Kyogu Lee},
  year = {2026},
  note = {arXiv},
  eprint = {2602.01908},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2602.01908v1},
}

@misc{speaking-without-sound-multi-speaker-silent-speech-voicing-with-facial-inputs-only,
  title = {Speaking Without Sound: Multi-speaker Silent Speech Voicing with Facial Inputs Only},
  author = {Jaejun Lee and Yoori Oh and Kyogu Lee},
  year = {2026},
  note = {arXiv},
  eprint = {2602.01879},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2602.01879v1},
}

@misc{mechanistic-interpretability-of-brain-to-speech-models-across-speech-modes,
  title = {Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes},
  author = {Maryam Maghsoudi and Ayushi Mishra},
  year = {2026},
  note = {arXiv},
  eprint = {2602.01247},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2602.01247v1},
}

@misc{lip-siri-contactless-open-sentence-silent-speech-with-wi-fi-backscatter,
  title = {Lip-Siri: Contactless Open-Sentence Silent Speech with Wi-Fi Backscatter},
  author = {Ye Tian and Haohua Du and Chao Gu and Junyang Zhang and Shanyue Wang and Hao Zhou and Jiahui Hou and Xiang-Yang Li},
  year = {2026},
  note = {arXiv},
  eprint = {2601.18177},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2601.18177v1},
}

@misc{transfer-learning-from-imagenet-for-meg-based-decoding-of-imagined-speech,
  title = {Transfer Learning from ImageNet for MEG-Based Decoding of Imagined Speech},
  author = {Soufiane Jhilal and Stéphanie Martin and Anne-Lise Giraud},
  year = {2026},
  note = {arXiv},
  eprint = {2601.15909},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2601.15909v1},
}

@misc{eeg-to-voice-decoding-of-spoken-and-imagined-speech-using-non-invasive-eeg,
  title = {EEG-to-Voice Decoding of Spoken and Imagined speech Using Non-Invasive EEG},
  author = {Hanbeot Park and Yunjeong Cho and Hunhee Kim},
  year = {2025},
  note = {arXiv},
  eprint = {2512.22146},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2512.22146v1},
}

@misc{poster-recognizing-hidden-in-the-ear-private-key-for-reliable-silent-speech-interface-using-mult,
  title = {Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning},
  author = {Xuefu Dong and Liqiang Xu and Lixing He and Zengyi Han and Ken Christofferson and Yifei Chen and Akihito Taya and Yuuki Nishiyama and Kaoru Sezaki},
  year = {2025},
  note = {arXiv},
  eprint = {2512.16518},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2512.16518v1},
}

@misc{a-convolutional-framework-for-mapping-imagined-auditory-meg-into-listened-brain-responses,
  title = {A Convolutional Framework for Mapping Imagined Auditory MEG into Listened Brain Responses},
  author = {Maryam Maghsoudi and Mohsen Rezaeizadeh and Shihab Shamma},
  year = {2025},
  note = {arXiv},
  eprint = {2512.03458},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2512.03458v1},
}

@misc{vspeechlm-a-visual-speech-language-model-for-visual-text-to-speech-task,
  title = {VSpeechLM: A Visual Speech Language Model for Visual Text-to-Speech Task},
  author = {Yuyue Wang and Xin Cheng and Yihan Wu and Xihua Wang and Jinchuan Tian and Ruihua Song},
  year = {2025},
  note = {arXiv},
  eprint = {2511.22229},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2511.22229v1},
}

@misc{a-cross-species-neural-foundation-model-for-end-to-end-speech-decoding,
  title = {A cross-species neural foundation model for end-to-end speech decoding},
  author = {Zhang, Yizi and He, Linyang and Fan, Chaofei and Liu, Tingkai and Yu, Han and Le, Trung and Li, Jingyuan and Linderman, Scott and Duncker, Lea and Willett, Francis R and Mesgarani, Nima and Paninski, Liam},
  year = {2025},
  note = {arXiv},
  eprint = {2511.21740},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2511.21740v5},
}

@misc{multidiffnet-a-multi-objective-diffusion-framework-for-generalizable-brain-decoding,
  title = {MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding},
  author = {Mengchun Zhang and Kateryna Shapovalenko and Yucheng Shao and Eddie Guo and Parusha Pradhan},
  year = {2025},
  note = {arXiv},
  eprint = {2511.18294},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2511.18294v1},
}

@misc{subject-independent-imagined-speech-detection-via-cross-subject-generalization-and-calibration,
  title = {Subject-Independent Imagined Speech Detection via Cross-Subject Generalization and Calibration},
  author = {Byung-Kwan Ko and Soowon Kim and Seo-Hyun Lee},
  year = {2025},
  note = {arXiv},
  eprint = {2511.13739},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2511.13739v1},
}

@misc{cat-net-a-cross-attention-tone-network-for-cross-subject-eeg-emg-fusion-tone-decoding,
  title = {CAT-Net: A Cross-Attention Tone Network for Cross-Subject EEG-EMG Fusion Tone Decoding},
  author = {Yifan Zhuang and Calvin Huang and Zepeng Yu and Yongjie Zou and Jiawei Ju},
  year = {2025},
  note = {arXiv},
  eprint = {2511.10935},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2511.10935v1},
}

@misc{toward-practical-bci-a-real-time-wireless-imagined-speech-eeg-decoding-system,
  title = {Toward Practical BCI: A Real-time Wireless Imagined Speech EEG Decoding System},
  author = {Ji-Ha Park and Heon-Gyu Kwak and Gi-Hwan Shin and Yoo-In Jeon and Sun-Min Park and Ji-Yeon Hwang and Seong-Whan Lee},
  year = {2025},
  note = {arXiv},
  eprint = {2511.07936},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2511.07936v1},
}

@misc{lightweight-diffusion-based-framework-for-online-imagined-speech-decoding-in-aphasia,
  title = {Lightweight Diffusion-based Framework for Online Imagined Speech Decoding in Aphasia},
  author = {Eunyeong Ko and Soowon Kim and Ha-Na Jo},
  year = {2025},
  note = {arXiv},
  eprint = {2511.07920},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2511.07920v3},
}

@misc{distinct-theta-synchrony-across-speech-modes-perceived-spoken-whispered-and-imagined,
  title = {Distinct Theta Synchrony across Speech Modes: Perceived, Spoken, Whispered, and Imagined},
  author = {Jung-Sun Lee and Ha-Na Jo and Eunyeong Ko},
  year = {2025},
  note = {arXiv},
  eprint = {2511.07918},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2511.07918v1},
}

@misc{reconstructing-unseen-sentences-from-speech-related-biosignals-for-open-vocabulary-neural-commun,
  title = {Reconstructing Unseen Sentences from Speech-related Biosignals for Open-vocabulary Neural Communication},
  author = {Deok-Seon Kim and Seo-Hyun Lee and Kang Yin and Seong-Whan Lee},
  year = {2025},
  note = {arXiv},
  eprint = {2510.27247},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2510.27247v1},
}

@misc{emg2speech-synthesizing-speech-from-electromyography-using-self-supervised-speech-models,
  title = {emg2speech: Synthesizing speech from electromyography using self-supervised speech models},
  author = {Harshavardhana T. Gowda and Daniel C. Comstock and Lee M. Miller},
  year = {2025},
  note = {arXiv},
  eprint = {2510.23969},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2510.23969v2},
}

@misc{ir-uwb-radar-based-contactless-silent-speech-recognition-with-attention-enhanced-temporal-convol,
  title = {IR-UWB Radar-Based Contactless Silent Speech Recognition with Attention-Enhanced Temporal Convolutional Networks},
  author = {Sunghwa Lee and Jaewon Yu},
  year = {2025},
  note = {arXiv},
  eprint = {2509.26409},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2509.26409v1},
}

@misc{neurottt-bridging-pretraining-downstream-task-misalignment-in-eeg-foundation-models-via-test-tim,
  title = {NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training},
  author = {Suli Wang and Yangshen Deng and Zhenghua Bao and Xinyu Zhan and Yiqun Duan},
  year = {2025},
  note = {arXiv},
  eprint = {2509.26301},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2509.26301v2},
}

@misc{lta-l2s-lexical-tone-aware-lip-to-speech-synthesis-for-mandarin-with-cross-lingual-transfer-lear,
  title = {LTA-L2S: Lexical Tone-Aware Lip-to-Speech Synthesis for Mandarin with Cross-Lingual Transfer Learning},
  author = {Kang Yang and Yifan Liang and Fangkun Liu and Zhenping Xie and Chengshi Zheng},
  year = {2025},
  note = {arXiv},
  eprint = {2509.25670},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2509.25670v1},
}

@misc{a-parallel-ultra-low-power-silent-speech-interface-based-on-a-wearable-fully-dry-emg-neckband,
  title = {A Parallel Ultra-Low Power Silent Speech Interface based on a Wearable, Fully-dry EMG Neckband},
  author = {Fiona Meier and Giusy Spacone and Sebastian Frey and Luca Benini and Andrea Cossettini},
  year = {2025},
  note = {arXiv},
  eprint = {2509.21964},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2509.21964v1},
}

@misc{from-silent-signals-to-natural-language-a-dual-stage-transformer-llm-approach,
  title = {From Silent Signals to Natural Language: A Dual-Stage Transformer-LLM Approach},
  author = {Nithyashree Sivasubramaniam},
  year = {2025},
  note = {arXiv},
  eprint = {2509.04507},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2509.04507v1},
}

@misc{an-introduction-to-silent-paralinguistics,
  title = {An Introduction to Silent Paralinguistics},
  author = {Zhao Ren and Simon Pistrosch and Buket Coşkun and Kevin Scheck and Anton Batliner and Björn W. Schuller and Tanja Schultz},
  year = {2025},
  note = {arXiv},
  eprint = {2508.18127},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2508.18127v1},
}

@misc{landmark-guided-visual-feature-extractor-for-visual-speech-recognition-with-limited-resource,
  title = {Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource},
  author = {Lei Yang and Junshan Jin and Mingyuan Zhang and Yi He and Bofan Chen and Shilin Wang},
  year = {2025},
  note = {arXiv},
  eprint = {2508.07233},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2508.07233v1},
}

@misc{a-silent-speech-decoding-system-from-eeg-and-emg-with-heterogenous-electrode-configurations,
  title = {A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations},
  author = {Masakazu Inoue and Motoshige Sato and Kenichi Tomeoka and Nathania Nah and Eri Hatakeyama and Kai Arulkumaran and Ilya Horiguchi and Shuntaro Sasai},
  year = {2025},
  note = {arXiv},
  eprint = {2506.13835},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2506.13835v1},
}

@misc{confidence-based-self-training-for-emg-to-speech-leveraging-synthetic-emg-for-robust-modeling,
  title = {Confidence-Based Self-Training for EMG-to-Speech: Leveraging Synthetic EMG for Robust Modeling},
  author = {Xiaodan Chen and Xiaoxue Gao and Mathias Quoy and Alexandre Pitti and Nancy F. Chen},
  year = {2025},
  note = {arXiv},
  eprint = {2506.11862},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2506.11862v2},
}

@misc{sonicvisionlm-playing-sound-with-vision-language-models,
  title = {SonicVisionLM: Playing Sound with Vision Language Models},
  author = {Zhifeng Xie and Shengye Yu and Qile He and Mengtian Li},
  year = {2024},
  note = {arXiv / imported corpus page},
  eprint = {2401.04394},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2401.04394v1},
}

@misc{ir-uwb-radar-based-contactless-silent-speech-recognition-of-vowels-consonants-words-and-phrases,
  title = {IR-UWB Radar-Based Contactless Silent Speech Recognition of Vowels, Consonants, Words, and Phrases},
  author = {Sunghwa Lee and Younghoon Shin and Myungjong Kim and Jiwon Seo},
  year = {2023},
  note = {arXiv / imported corpus page},
  doi = {10.1109/ACCESS.2023.3344177},
  eprint = {2312.09572},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1109/ACCESS.2023.3344177},
}

@misc{ultrasensitive-textile-strain-sensors-redefine-wearable-silent-speech-interfaces-with-high-machine-learning-efficiency,
  title = {Ultrasensitive Textile Strain Sensors Redefine Wearable Silent Speech Interfaces with High Machine Learning Efficiency},
  author = {Chenyu Tang and Muzi Xu and Wentian Yi and Zibo Zhang and Edoardo Occhipinti and Chaoqun Dong and Dafydd Ravenscroft and Sung‐Min Jung and Sanghyo Lee and Shuo Gao and Jong Min Kim and Luigi G. Occhipinti},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2311.15683},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2311.15683v1},
}

@misc{distributed-pressure-matching-strategy-using-diffusion-adaptation,
  title = {Distributed pressure matching strategy using diffusion adaptation},
  author = {Mengfei Zhang and Junqing Zhang and Jie Chen and Cédric Richard},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2311.07729},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2311.07729v1},
}

@misc{advancing-test-time-adaptation-for-acoustic-foundation-models-in-open-world-shifts,
  title = {Advancing Test-Time Adaptation for Acoustic Foundation Models in Open-World Shifts},
  author = {Andy Clark},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2310.09505},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2310.09505v1},
}

@misc{sound-source-localization-is-all-about-cross-modal-alignment,
  title = {Sound Source Localization is All about Cross-Modal Alignment},
  author = {Arda Senocak and Hyeonggon Ryu and Junsik Kim and Tae-Hyun Oh and Hanspeter Pfister and Joon Son Chung},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2309.10724},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2309.10724v1},
}

@misc{let-there-be-sound-reconstructing-high-quality-speech-from-silent-videos,
  title = {Let There Be Sound: Reconstructing High Quality Speech from Silent Videos},
  author = {Ji-Hoon Kim and Jaehun Kim and Joon Son Chung},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2308.15256},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2308.15256v2},
}

@misc{an-initial-exploration-learning-to-generate-realistic-audio-for-silent-video,
  title = {An Initial Exploration: Learning to Generate Realistic Audio for Silent Video},
  author = {Matthew Martel and Jackson Wagner},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2308.12408},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2308.12408v1},
}

@misc{akvsr-audio-knowledge-empowered-visual-speech-recognition-by-compressing-audio-knowledge-of-a-pretrained-model,
  title = {Audio Knowledge Empowered Visual Speech Recognition},
  author = {Jeong Hun Yeo and Minsu Kim and Jeongsoo Choi and Dae Hoe Kim and Yong Man Ro},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2308.07593},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2308.07593v2},
}

@misc{knowledge-distilled-ensemble-model-for-semg-based-silent-speech-interface,
  title = {Knowledge Distilled Ensemble Model for sEMG-based Silent Speech Interface},
  author = {Wenqiang Lai and Qihan Yang and Mao Ye and Endong Sun and Jiangnan Ye},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2308.06533},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2308.06533v1},
}

@misc{automatically-measuring-speech-fluency-in-people-with-aphasia-first-achievements-using-read-speech-data,
  title = {Automatically measuring speech fluency in people with aphasia: first achievements using read-speech data},
  author = {Lionel Fontan and Typhanie Prince and Aleksandra Nowakowska and Halima Sahraoui and Silvia Martínez‐Ferreiro},
  year = {2023},
  note = {arXiv / imported corpus page},
  doi = {10.1080/02687038.2023.2244728},
  eprint = {2308.04763},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1080/02687038.2023.2244728},
}

@misc{exploring-how-a-generative-ai-interprets-music,
  title = {Exploring how a Generative AI interprets music},
  author = {Gabriela Barenboim and Luigi Del Debbio and Johannes Hirn and Verónica Sanz},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2308.00015},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2308.00015v1},
}

@misc{audio-visual-video-to-speech-synthesis-with-synthesized-input-audio,
  title = {Audio-visual video-to-speech synthesis with synthesized input audio},
  author = {Triantafyllos Kefalas and Yannis Panagakis and Maja Pantić},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2307.16584},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2307.16584v1},
}

@misc{audio-aware-query-enhanced-transformer-for-audio-visual-segmentation,
  title = {Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation},
  author = {Jinxiang Liu and Chen Ju and Chaofan Ma and Yanfeng Wang and Yu Wang and Ya Zhang},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2307.13236},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2307.13236v1},
}

@misc{robustl2s-speaker-specific-lip-to-speech-synthesis-exploiting-self-supervised-representations,
  title = {RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations},
  author = {Neha Sahipjohn and Neil Shah and Vishal Tambrahalli and Vineet Gandhi},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2307.01233},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2307.01233v1},
}

@misc{diff-foley-synchronized-video-to-audio-synthesis-with-latent-diffusion-models,
  title = {Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models},
  author = {Simian Luo and Chuanhao Yan and Chenxu Hu and Hang Zhao},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2306.17203},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2306.17203v1},
}

@misc{high-quality-automatic-voice-over-with-accurate-alignment-supervision-through-self-supervised-discrete-speech-units,
  title = {High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units},
  author = {Junchen Lu and Berrak Şişman and Mingyang Zhang and Haizhou Li},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2306.17005},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2306.17005v1},
}

@misc{large-scale-unsupervised-audio-pre-training-for-video-to-speech-synthesis,
  title = {Large-scale unsupervised audio pre-training for video-to-speech synthesis},
  author = {Triantafyllos Kefalas and Yannis Panagakis and Maja Pantić},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2306.15464},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2306.15464v2},
}

@misc{lipvoicer-generating-speech-from-silent-videos-guided-by-lip-reading,
  title = {LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading},
  author = {Yochai Yemini and Aviv Shamsian and Lior Bracha and Sharon Gannot and Ethan Fetaya},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2306.03258},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2306.03258v1},
}

@misc{intelligible-lip-to-speech-synthesis-with-speech-units,
  title = {Intelligible Lip-to-Speech Synthesis with Speech Units},
  author = {Jeongsoo Choi and Minsu Kim and Yong Man Ro},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2305.19603},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2305.19603v1},
}

@misc{adaptation-of-tongue-ultrasound-based-silent-speech-interfaces-using-spatial-transformer-networks,
  title = {Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks},
  author = {László Tóth and Amin Honarmandi Shandiz and Gábor Gosztolya and Tamás Gábor Csapó},
  year = {2023},
  note = {the Proceedings of Interspeech 2023},
  doi = {10.21437/Interspeech.2023-1607},
  eprint = {2305.19130},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.21437/Interspeech.2023-1607},
}

@misc{zero-shot-personalized-lip-to-speech-synthesis-with-face-image-based-voice-control,
  title = {Zero-shot personalized lip-to-speech synthesis with face image based voice control},
  author = {Zheng-Yan Sheng and Yang Ai and Zhen-Hua Ling},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2305.14359},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2305.14359v1},
}

@misc{improving-the-gap-in-visual-speech-recognition-between-normal-and-silent-speech-based-on-metric-learning,
  title = {Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning},
  author = {Sara Kashiwagi and Keitaro Tanaka and Feng Qi and Shigeo Morishima},
  year = {2023},
  note = {arXiv / imported corpus page},
  doi = {10.21437/Interspeech.2023-370},
  eprint = {2305.14203},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.21437/Interspeech.2023-370},
}

@misc{conditional-generation-of-audio-from-video-via-foley-analogies,
  title = {Conditional Generation of Audio from Video via Foley Analogies},
  author = {Yuexi Du and Ziyang Chen and Justin Salamon and Bryan Russell and Andrew Owens},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2304.08490},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2304.08490v1},
}

@misc{speech-reconstruction-from-silent-tongue-and-lip-articulation-by-pseudo-target-generation-and-domain-adversarial-training,
  title = {Speech Reconstruction from Silent Tongue and Lip Articulation By Pseudo Target Generation and Domain Adversarial Training},
  author = {Rui-Chen Zheng and Yang Ai and Zhen-Hua Ling},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2304.05574},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2304.05574v1},
}

@misc{wesper-zero-shot-and-realtime-whisper-to-normal-voice-conversion-for-whisper-based-speech-interactions,
  title = {WESPER: Zero-shot and Realtime Whisper to Normal Voice Conversion for Whisper-based Speech Interactions},
  author = {Jun Rekimoto},
  year = {2023},
  note = {Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23), April 23--28, 2023},
  doi = {10.1145/3544548.3580706},
  eprint = {2303.01639},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1145/3544548.3580706},
}

@misc{duration-aware-pause-insertion-using-pre-trained-language-model-for-multi-speaker-text-to-speech,
  title = {Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech},
  author = {Dong Yang and Tomoki Koriyama and Yuki Saito and Takaaki Saeki and Detai Xin and Hiroshi Saruwatari},
  year = {2023},
  note = {arXiv / imported corpus page},
  eprint = {2302.13652},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2302.13652v1},
}

@misc{liplearner-customizable-silent-speech-interactions-on-mobile-devices,
  title = {LipLearner: Customizable Silent Speech Interactions on Mobile Devices},
  author = {Zixiong Su and Shitao Fang and Jun Rekimoto},
  year = {2023},
  note = {arXiv / imported corpus page},
  doi = {10.1145/3544548.3581465},
  eprint = {2302.05907},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1145/3544548.3581465},
}

@misc{towards-neural-decoding-of-imagined-speech-based-on-spoken-speech,
  title = {Towards Neural Decoding of Imagined Speech based on Spoken Speech},
  author = {Seo‐Hyun Lee and Young-Eun Lee and Soo-Won Kim and Byung-Kwan Ko and Seong‐Whan Lee},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2212.02047},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2212.02047v2},
}

@misc{breaking-the-trade-off-in-personalized-speech-enhancement-with-cross-task-knowledge-distillation,
  title = {Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation},
  author = {Hassan Taherian and Şefik Emre Eskimez and Takuya Yoshioka},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2211.02944},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2211.02944v1},
}

@misc{movement-detection-of-tongue-and-related-body-parts-using-ir-uwb-radar,
  title = {Movement Detection of Tongue and Related Body Parts Using IR-UWB Radar},
  author = {Sunghwa Lee and Younghoon Shin},
  year = {2022},
  note = {arXiv / imported corpus page},
  doi = {10.1109/ICTC55196.2022.9952644},
  eprint = {2209.01762},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1109/ICTC55196.2022.9952644},
}

@misc{lip-to-speech-synthesis-for-arbitrary-speakers-in-the-wild,
  title = {Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild},
  author = {Sindhu B Hegde and K R Prajwal and Rudrabha Mukhopadhyay and Vinay P. Namboodiri and C. V. Jawahar},
  year = {2022},
  note = {arXiv / imported corpus page},
  doi = {10.1145/3503161.3548081},
  eprint = {2209.00642},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1145/3503161.3548081},
}

@misc{an-anchor-free-detector-for-continuous-speech-keyword-spotting,
  title = {An Anchor-Free Detector for Continuous Speech Keyword Spotting},
  author = {Zhiyuan Zhao and Chuanxin Tang and Chengdong Yao and Chong Luo},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2208.04622},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2208.04622v1},
}

@misc{fastlts-non-autoregressive-end-to-end-unconstrained-lip-to-speech-synthesis,
  title = {FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis},
  author = {Yongqi Wang and Zhou Zhao},
  year = {2022},
  note = {arXiv / imported corpus page},
  doi = {10.1145/3503161.3548194},
  eprint = {2207.03800},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1145/3503161.3548194},
}

@misc{improved-processing-of-ultrasound-tongue-videos-by-combining-convlstm-and-3d-convolutional-networks,
  title = {Improved Processing of Ultrasound Tongue Videos by Combining ConvLSTM and 3D Convolutional Networks},
  author = {Amin Honarmandi Shandiz and László Tóth},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2206.12947},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2206.12947v1},
}

@misc{visagesyntalk-unseen-speaker-video-to-speech-synthesis-via-speech-visage-feature-selection,
  title = {VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection},
  author = {Joanna Hong and Minsu Kim and Yong Man Ro},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2206.07458},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2206.07458v2},
}

@misc{silence-is-sweeter-than-speech-self-supervised-model-using-silence-to-store-speaker-information,
  title = {Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information},
  author = {Chi-Luen Feng and Po‐Chun Hsu and Hung-yi Lee},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2205.03759},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2205.03759v1},
}

@misc{svts-scalable-video-to-speech-synthesis,
  title = {SVTS: Scalable Video-to-Speech Synthesis},
  author = {Rodrigo Mira and Alexandros Haliassos and Stavros Petridis and Björn W. Schuller and Maja Pantić},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2205.02058},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2205.02058v2},
}

@misc{listen-only-to-me-how-well-can-target-speech-extraction-handle-false-alarms,
  title = {Listen only to me! How well can target speech extraction handle false alarms?},
  author = {Marc Delcroix and Keisuke Kinoshita and Tsubasa Ochiai and Kateřina Žmolíková and Hiroshi Satō and Tomohiro Nakatani},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2204.04811},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2204.04811v2},
}

@misc{multi-modality-associative-bridging-through-memory-speech-sound-recollected-from-face-video,
  title = {Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video},
  author = {Minsu Kim and Joanna Hong and Se Jin Park and Yong Man Ro},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2204.01265},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2204.01265v1},
}

@misc{vcvts-multi-speaker-video-to-speech-synthesis-via-cross-modal-knowledge-transfer-from-voice-conversion,
  title = {VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion},
  author = {Disong Wang and Shan Yang and Dan Su and Xunying Liu and Dong Yu and Helen Meng},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2202.09081},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2202.09081v1},
}

@misc{supervised-and-self-supervised-pretraining-based-covid-19-detection-using-acoustic-breathing-cough-speech-signals,
  title = {Supervised and Self-supervised Pretraining Based COVID-19 Detection Using Acoustic Breathing/Cough/Speech Signals},
  author = {Xingyu Chen and Qiushi Zhu and Jie Zhang and Li-Rong Dai},
  year = {2022},
  note = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp. 561-565},
  doi = {10.1109/ICASSP43922.2022.9746205},
  eprint = {2201.08934},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746205},
}

@misc{visualtts-tts-with-accurate-lip-speech-synchronization-for-automatic-voice-over,
  title = {VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over},
  author = {Junchen Lu and Berrak Şişman and Rui Liu and Mingyang Zhang and Haizhou Li},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2110.03342},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2110.03342v3},
}

@misc{sequence-to-sequence-voice-reconstruction-for-silent-speech-in-a-tonal-language,
  title = {Sequence-to-Sequence Voice Reconstruction for Silent Speech in a Tonal Language},
  author = {Huiyan Li and Haohong Lin and You Wang and Hengyang Wang and Ming Zhang and Han Gao and Qing Ai and Zhiyuan Luo and Guang Li},
  year = {2022},
  note = {arXiv / imported corpus page},
  eprint = {2108.00190},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2108.00190v3},
}

@misc{silentspeller,
  title = {SilentSpeller: Towards mobile, hands-free, silent speech text entry using electropalatography},
  author = {Naoki Kimura and Tan Gemicioglu and Jonathan Womack and Richard Li and Yuhui Zhao and Abdelkareem Bedri and Zixiong Su and Alex Olwal and Jun Rekimoto and Thad Starner},
  year = {2022},
  note = {CHI '22},
  doi = {10.1145/3491102.3502015},
  url = {https://doi.org/10.1145/3491102.3502015},
}

@misc{sa-sdr-a-novel-loss-function-for-separation-of-meeting-style-data,
  title = {SA-SDR: A novel loss function for separation of meeting style data},
  author = {Thilo von Neumann and Keisuke Kinoshita and Christoph Boeddeker and Marc Delcroix and Reinhold Haeb‐Umbach},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2110.15581},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2110.15581v2},
}

@misc{advances-and-challenges-in-deep-lip-reading,
  title = {Advances and Challenges in Deep Lip Reading},
  author = {Marzieh Oghbaie and Arian Sabaghi and Kooshan Hashemifard and Mohammad Kazem Akbari},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2110.07879},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2110.07879v1},
}

@misc{sub-word-level-lip-reading-with-visual-attention,
  title = {Sub-word Level Lip Reading With Visual Attention},
  author = {K R Prajwal and Triantafyllos Afouras and Andrew Zisserman},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2110.07603},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2110.07603v2},
}

@misc{speech-synthesis-from-text-and-ultrasound-tongue-image-based-articulatory-input,
  title = {Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input},
  author = {Csapó Tamás Gábor and László Tóth and Gosztolya Gábor and Alexandra Markó},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2107.02003},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2107.02003v1},
}

@misc{sparsely-overlapped-speech-training-in-the-time-domain-joint-learning-of-target-speech-separation-and-personal-vad-benefits,
  title = {Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits},
  author = {Qingjian Lin and Lin Yang and Xuyang Wang and Luyuan Xie and Jia Chen and Junjie Wang},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2106.14371},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2106.14371v2},
}

@misc{silent-speech-and-emotion-recognition-from-vocal-tract-shape-dynamics-in-real-time-mri,
  title = {Silent Speech and Emotion Recognition from Vocal Tract Shape Dynamics in Real-Time MRI},
  author = {Laxmi Pandey and Ahmed Sabbir Arif},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2106.08706},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2106.08706v1},
}

@misc{neural-speaker-embeddings-for-ultrasound-based-silent-speech-interfaces,
  title = {Neural Speaker Embeddings for Ultrasound-based Silent Speech Interfaces},
  author = {Honarmandi Shandiz Amin and László Tóth and Gosztolya Gábor and Alexandra Markó and Csapó Tamás Gábor},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2106.04552},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2106.04552v2},
}

@misc{an-improved-model-for-voicing-silent-speech,
  title = {An Improved Model for Voicing Silent Speech},
  author = {David Gaddy and Dan Klein},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2106.01933},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2106.01933v2},
}

@misc{voice-activity-detection-for-ultrasound-based-silent-speech-interfaces-using-convolutional-neural-networks,
  title = {Voice Activity Detection for Ultrasound-based Silent Speech Interfaces using Convolutional Neural Networks},
  author = {Amin Honarmandi Shandiz and László Tóth},
  year = {2021},
  note = {arXiv / imported corpus page},
  doi = {10.1007/978-3-030-83527-9_43},
  eprint = {2105.13718},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1007/978-3-030-83527-9_43},
}

@misc{speaker-disentanglement-in-video-to-speech-conversion,
  title = {Speaker disentanglement in video-to-speech conversion},
  author = {Dan Oneaţă and Adriana Stan and Horia Cucu},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2105.09652},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2105.09652v1},
}

@misc{improving-neural-silent-speech-interface-models-by-adversarial-training,
  title = {Improving Neural Silent Speech Interface Models by Adversarial Training},
  author = {Amin Honarmandi Shandiz and László Tóth and Gábor Gosztolya and Alexandra Markó and Tamás Gábor Csapó},
  year = {2021},
  note = {arXiv / imported corpus page},
  doi = {10.1007/978-3-030-76346-6_39},
  eprint = {2104.11601},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1007/978-3-030-76346-6_39},
}

@misc{3d-convolutional-neural-networks-for-ultrasound-based-silent-speech-interfaces,
  title = {3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces},
  author = {László Tóth and Amin Honarmandi Shandiz},
  year = {2021},
  note = {arXiv / imported corpus page},
  doi = {10.1007/978-3-030-61401-0_16},
  eprint = {2104.11532},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1007/978-3-030-61401-0_16},
}

@misc{htmd-net-a-hybrid-masking-denoising-approach-to-time-domain-monaural-singing-voice-separation,
  title = {HTMD-Net: A Hybrid Masking-Denoising Approach to Time-Domain Monaural Singing Voice Separation},
  author = {Christos Garoufis and Athanasia Zlatintsi and Petros Maragos},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2103.04336},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2103.04336v1},
}

@misc{silent-versus-modal-multi-speaker-speech-recognition-from-ultrasound-and-video,
  title = {Silent versus modal multi-speaker speech recognition from ultrasound and video},
  author = {Manuel Sam Ribeiro and Aciel Eshky and Korin Richmond and Steve Renals},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2103.00333},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2103.00333v1},
}

@misc{ema2s-an-end-to-end-multimodal-articulatory-to-speech-system,
  title = {EMA2S: An End-to-End Multimodal Articulatory-to-Speech System},
  author = {Yu‐Wen Chen and Kuo-Hsuan Hung and Shang-Yi Chuang and Jonathan H. Sherman and Wen-Chin Huang and Xugang Lu and Yu Tsao},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2102.03786},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2102.03786v2},
}

@misc{convolutional-neural-network-based-age-estimation-using-b-mode-ultrasound-tongue-image,
  title = {Convolutional Neural Network-Based Age Estimation Using B-Mode Ultrasound Tongue Image},
  author = {Kele Xu and Tamás Gábor Csapó and Ming Feng},
  year = {2021},
  note = {arXiv / imported corpus page},
  eprint = {2101.11245},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2101.11245v1},
}

@misc{end-to-end-silent-speech-recognition-with-acoustic-sensing,
  title = {End-to-end Silent Speech Recognition with Acoustic Sensing},
  author = {Jian Luo and Jianzong Wang and Ning Cheng and Guilin Jiang and Jing Xiao},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2011.11315},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2011.11315v1},
}

@misc{speech-prediction-in-silent-videos-using-variational-autoencoders,
  title = {Speech Prediction in Silent Videos using Variational Autoencoders},
  author = {Ravindra Yadav and Ashish Sardana and Vinay P. Namboodiri and Rajesh M. Hegde},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2011.07340},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2011.07340v1},
}

@misc{x-tasnet-robust-and-accurate-time-domain-speaker-extraction-network,
  title = {X-TaSNet: Robust and Accurate Time-Domain Speaker Extraction Network},
  author = {Zining Zhang and Bingsheng He and Zhenjie Zhang},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2010.12766},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2010.12766v1},
}

@misc{listening-to-sounds-of-silence-for-speech-denoising,
  title = {Listening to Sounds of Silence for Speech Denoising},
  author = {Ruilin Xu and Rundi Wu and Yuko Ishiwaka and Carl Vondrick and Changxi Zheng},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2010.12013},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2010.12013v1},
}

@misc{discriminative-sounding-objects-localization-via-self-supervised-audiovisual-matching,
  title = {Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching},
  author = {Di Hu and Rui Qian and Minyue Jiang and Xiao Tan and Shilei Wen and Errui Ding and Weiyao Lin and Dejing Dou},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2010.05466},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2010.05466v1},
}

@misc{digital-voicing-of-silent-speech,
  title = {Digital Voicing of Silent Speech},
  author = {David Gaddy and Dan Klein},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2010.02960},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2010.02960v1},
}

@misc{end-to-end-speaker-dependent-voice-activity-detection,
  title = {End-to-End Speaker-Dependent Voice Activity Detection},
  author = {Yefei Chen and Shuai Wang and Yanmin Qian and Kai Yu},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2009.09906},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2009.09906v1},
}

@misc{a-comparison-of-oscillatory-characteristics-in-covert-speech-and-speech-perception,
  title = {A comparison of oscillatory characteristics in covert speech and speech perception},
  author = {Jae Moon and Silvia Orlandi and Tom Chau},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2009.02816},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2009.02816v1},
}

@misc{silent-speech-interfaces-for-speech-restoration-a-review,
  title = {Silent Speech Interfaces for Speech Restoration: A Review},
  author = {José A. González and Alejandro Gomez-Alanis and Juan M. Martín-Doñas and José L. Pérez-Córdoba and Ángel M. Gómez},
  year = {2020},
  note = {arXiv / imported corpus page},
  doi = {10.1109/ACCESS.2020.3026579},
  eprint = {2009.02110},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1109/ACCESS.2020.3026579},
}

@misc{an-overview-of-deep-learning-based-audio-visual-speech-enhancement-and-separation,
  title = {An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation},
  author = {Daniel Michelsanti and Zheng‐Hua Tan and Shi-Xiong Zhang and Yong Xu and Meng Yu and Dong Yu and Jesper Jensen},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2008.09586},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2008.09586v2},
}

@misc{citisen-a-deep-learning-based-speech-signal-processing-mobile-application,
  title = {CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application},
  author = {Yu-Wen Chen and Kuo-Hsuan Hung and You-Jin Li and Alexander Kang and Ya‐Hsin Lai and Kai-Chun Liu and Szu‐Wei Fu and Syu‐Siang Wang and Yu Tsao},
  year = {2020},
  note = {arXiv / imported corpus page},
  doi = {10.1109/ACCESS.2022.3153469},
  eprint = {2008.09264},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1109/ACCESS.2022.3153469},
}

@misc{foley-music-learning-to-generate-music-from-videos,
  title = {Foley Music: Learning to Generate Music from Videos},
  author = {Chuang Gan and Deng Huang and Peihao Chen and Joshua B. Tenenbaum and Antonio Torralba},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2007.10984},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2007.10984v1},
}

@misc{learning-frame-level-attention-for-environmental-sound-classification,
  title = {Learning Frame Level Attention for Environmental Sound Classification},
  author = {Zhichao Zhang and Shugong Xu and Shunqing Zhang and Tianhao Qiao and Shan Cao},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2007.07241},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2007.07241v1},
}

@misc{ultra2speech-a-deep-learning-framework-for-formant-frequency-estimation-and-tracking-from-ultrasound-tongue-images,
  title = {Ultra2Speech -- A Deep Learning Framework for Formant Frequency Estimation and Tracking from Ultrasound Tongue Images},
  author = {Pramit Saha and Yadong Liu and Bryan Gick and Sidney Fels},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2006.16367},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2006.16367v1},
}

@misc{application-of-just-noticeable-difference-in-quality-as-environment-suitability-test-for-crowdsourcing-speech-quality-assessment-task,
  title = {Application of Just-Noticeable Difference in Quality as Environment Suitability Test for Crowdsourcing Speech Quality Assessment Task},
  author = {Babak Naderi and Sebastian Möller},
  year = {2020},
  note = {arXiv / imported corpus page},
  doi = {10.1109/QoMEX48832.2020.9123093},
  eprint = {2004.05502},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1109/QoMEX48832.2020.9123093},
}

@misc{vocoder-based-speech-synthesis-from-silent-videos,
  title = {Vocoder-Based Speech Synthesis from Silent Videos},
  author = {Daniel Michelsanti and Olga Slizovskaia and Gloria Haro and Emília Gómez and Zheng‐Hua Tan and Jesper Jensen},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2004.02541},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2004.02541v2},
}

@misc{continuous-silent-speech-recognition-using-eeg,
  title = {Continuous Silent Speech Recognition using EEG},
  author = {Gautam Krishna and Co Tran and Mason Carnahan and Ahmed H. Tewfik},
  year = {2020},
  note = {arXiv / imported corpus page},
  eprint = {2002.03851},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/2002.03851v7},
}

@misc{brain2char-a-deep-architecture-for-decoding-text-from-brain-recordings,
  title = {Brain2Char: A Deep Architecture for Decoding Text from Brain Recordings},
  author = {Pengfei Sun and Gopala K. Anumanchipalli and Edward F. Chang},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1909.01401},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1909.01401v1},
}

@misc{demucs-deep-extractor-for-music-sources-with-extra-unlabeled-data-remixed,
  title = {Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed},
  author = {Alexandre Défossez and Nicolas Usunier and Léon Bottou and Francis R. Bach},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1909.01174},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1909.01174v1},
}

@misc{attention-based-convolutional-recurrent-neural-network-for-environmental-sound-classification,
  title = {Attention based Convolutional Recurrent Neural Network for Environmental Sound Classification},
  author = {Zhichao Zhang and Shugong Xu and Shunqing Zhang and Tianhao Qiao and Shan Cao},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1907.02230},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1907.02230v1},
}

@misc{lipper-synthesizing-thy-speech-using-multi-view-lipreading,
  title = {Lipper: Synthesizing Thy Speech using Multi-View Lipreading},
  author = {Yaman Kumar and Rohit Jain and Khwaja Mohd. Salik and Rajiv Ratn Shah and Yifang Yin and Roger Zimmermann},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1907.01367},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1907.01367v1},
}

@misc{ultrasound-based-silent-speech-interface-built-on-a-continuous-vocoder,
  title = {Ultrasound-based Silent Speech Interface Built on a Continuous Vocoder},
  author = {Tamás Gábor Csapó and Mohammed Salah Al-Radhi and Géza Németh and Gábor Gosztolya and Tamás Grósz and László Tóth and Alexandra Markó},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1906.09885},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1906.09885v1},
}

@misc{video-driven-speech-reconstruction-using-generative-adversarial-networks,
  title = {Video-Driven Speech Reconstruction using Generative Adversarial Networks},
  author = {Konstantinos Vougioukas and Pingchuan Ma and Stavros Petridis and Maja Pantić},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1906.06301},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1906.06301v1},
}

@misc{a-novel-task-oriented-text-corpus-in-silent-speech-recognition-and-its-natural-language-generation-construction-method,
  title = {A Novel Task-Oriented Text Corpus in Silent Speech Recognition and its Natural Language Generation Construction Method},
  author = {Dong Cao and Dongdong Zhang and Haibo Chen},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1905.01974},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1905.01974v1},
}

@misc{autoencoder-based-articulatory-to-acoustic-mapping-for-ultrasound-silent-speech-interfaces,
  title = {Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces},
  author = {Gábor Gosztolya and Ádám Pintér and László Tóth and Tamás Grósz and Alexandra Markó and Tamás Gábor Csapó},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1904.05259},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1904.05259v1},
}

@misc{denoising-convolutional-autoencoder-based-b-mode-ultrasound-tongue-image-feature-extraction,
  title = {Denoising convolutional autoencoder based B-mode ultrasound tongue image feature extraction},
  author = {Bo Li and Kele Xu and Dawei Feng and Haibo Mi and Huaimin Wang and Jian Zhu},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1903.00888},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1903.00888v1},
}

@misc{all-neural-online-source-separation-counting-and-diarization-for-meeting-analysis,
  title = {All-neural online source separation, counting, and diarization for meeting analysis},
  author = {Thilo von Neumann and Keisuke Kinoshita and Marc Delcroix and Shoko Araki and Tomohiro Nakatani and Reinhold Haeb‐Umbach},
  year = {2019},
  note = {arXiv / imported corpus page},
  eprint = {1902.07881},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1902.07881v1},
}

@misc{sottovoce,
  title = {SottoVoce: An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks},
  author = {Naoki Kimura and Michinari Kono and Jun Rekimoto},
  year = {2019},
  note = {CHI '19},
  doi = {10.1145/3290605.3300376},
  url = {https://doi.org/10.1145/3290605.3300376},
}

@misc{audio-spectrogram-factorization-for-classification-of-telephony-signals-below-the-auditory-threshold,
  title = {Audio Spectrogram Factorization for Classification of Telephony Signals below the Auditory Threshold},
  author = {Iroro Orife and Shane Walker and Jason Flaks},
  year = {2018},
  note = {arXiv / imported corpus page},
  eprint = {1811.04139},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1811.04139v1},
}

@misc{proactive-security-embedded-ai-solution-for-violent-and-abusive-speech-recognition,
  title = {Proactive Security: Embedded AI Solution for Violent and Abusive Speech Recognition},
  author = {Christopher Shulby and Leonardo Pombal and Vitor Jordão and Guilherme Ziolle and Bruno Martho and Antônio Postal and Thiago Prochnow},
  year = {2018},
  note = {arXiv / imported corpus page},
  eprint = {1810.09431},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1810.09431v1},
}

@misc{harnessing-ai-for-speech-reconstruction-using-multi-view-silent-video-feed,
  title = {Harnessing AI for Speech Reconstruction using Multi-view Silent Video Feed},
  author = {Yaman Kumar and Mayank Aggarwal and Pratham Nawal and Shin'ichi Satoh and Rajiv Ratn Shah and Roger Zimmermann},
  year = {2018},
  note = {arXiv / imported corpus page},
  doi = {10.1145/3240508.3241911},
  eprint = {1807.00619},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1145/3240508.3241911},
}

@misc{visual-only-recognition-of-normal-whispered-and-silent-speech,
  title = {Visual-Only Recognition of Normal, Whispered and Silent Speech},
  author = {Stavros Petridis and Jie Shen and Doruk Cetin and Maja Pantić},
  year = {2018},
  note = {arXiv / imported corpus page},
  eprint = {1802.06399},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1802.06399v1},
}

@misc{cross-modal-embeddings-for-video-and-audio-retrieval,
  title = {Cross-modal Embeddings for Video and Audio Retrieval},
  author = {Dídac Surís and Amanda Duarte and Amaia Salvador and Jordi Torres and Giró Nieto, Xavier},
  year = {2018},
  note = {arXiv / imported corpus page},
  eprint = {1801.02200},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1801.02200v1},
}

@misc{lip2audspec-speech-reconstruction-from-silent-lip-movements-video,
  title = {Lip2AudSpec: Speech reconstruction from silent lip movements video},
  author = {Hassan Akbari and Himani Arora and Liangliang Cao and Nima Mesgarani},
  year = {2017},
  note = {arXiv / imported corpus page},
  eprint = {1710.09798},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1710.09798v1},
}

@misc{updating-the-silent-speech-challenge-benchmark-with-deep-learning,
  title = {Updating the silent speech challenge benchmark with deep learning},
  author = {Yan Ji and Licheng Liu and Hongcui Wang and Zhilei Liu and Zhibin Niu and B. Denby},
  year = {2017},
  note = {arXiv / imported corpus page},
  eprint = {1709.06818},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1709.06818v1},
}

@misc{seeing-through-noise-visually-driven-speaker-separation-and-enhancement,
  title = {Seeing Through Noise: Visually Driven Speaker Separation and Enhancement},
  author = {Aviv Gabbay and Ariel Ephrat and Tavi Halperin and Shmuel Peleg},
  year = {2017},
  note = {arXiv / imported corpus page},
  eprint = {1708.06767},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1708.06767v3},
}

@misc{improved-speech-reconstruction-from-silent-video,
  title = {Improved Speech Reconstruction from Silent Video},
  author = {Ariel Ephrat and Tavi Halperin and Shmuel Peleg},
  year = {2017},
  note = {arXiv / imported corpus page},
  eprint = {1708.01204},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1708.01204v3},
}

@misc{vid2speech-speech-reconstruction-from-silent-video,
  title = {Vid2speech: Speech Reconstruction from Silent Video},
  author = {Ariel Ephrat and Shmuel Peleg},
  year = {2017},
  note = {arXiv / imported corpus page},
  eprint = {1701.00495},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1701.00495v2},
}

@misc{contour-based-3d-tongue-motion-visualization-using-ultrasound-image-sequences,
  title = {Contour-based 3d tongue motion visualization using ultrasound image sequences},
  author = {Kele Xu and Yin Yang and Clémence Leboullenger and Pierre Roussel and B. Denby},
  year = {2016},
  note = {arXiv / imported corpus page},
  eprint = {1605.05967},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1605.05967v1},
}

@misc{optimal-power-control-for-analog-bidirectional-relaying-with-long-term-relay-power-constraint,
  title = {Optimal Power Control for Analog Bidirectional Relaying with Long-Term Relay Power Constraint},
  author = {Zoran Hadzi-Velkov and Nikola Zlatanov and Robert Schober},
  year = {2014},
  note = {arXiv / imported corpus page},
  doi = {10.1109/GLOCOM.2013.6831710},
  eprint = {1404.0906},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.1109/GLOCOM.2013.6831710},
}