← CHI 2026 map

CHI '26 · Honorable mention · full-paper review · confidence medium-high

Sensing Your Vocals: Exploring the Activity of Vocal Cord Muscles for Pitch Assessment Using Electromyography and Ultrasonography

Kanyu Chen , Rebecca Panskus , Erwin Wu , Yichen Peng , Daichi Saito , Emiko Kamiyama , Ruiteng Li , Chen-Chieh Liao , Karola Marky , Kato Akira , Hideki Koike , Kai Kunze

DOI PDF Program page Page JSON

This is a credible CHI systems-and-study paper: the core move is to make vocal muscle activity visible with EMG and ultrasonography, then test whether that visibility helps training and feedback. The contribution is strongest as a mixed-methods sensing/feedback system with clear practical limits, not as a universal vocal pedagogy solution.

Axes Lens

Rare contribution shape, typical evidence profile. The point here is not a score. It is to show what kind of claim the paper makes, and whether the evidence pattern is unusual or baseline in this 268 -review set.

Review Summary

This paper’s main contribution is not a new theory of singing, but a concrete HCI reframing of vocal training feedback: instead of treating pitch assessment as something that can be inferred adequately from audio alone, it makes the internal muscle activity itself the object of sensing and visualization. That is a sensible departure from common practice because the paper explicitly motivates the problem as one of invisibility and internal control, then responds with EMG and ultrasonography as complementary modalities. The novelty is therefore system-level and methodological: an accessible EMG+UI pipeline, a reference visualization of expert muscle activity, and a comparative look at how different user groups interpret the modalities. The validation is reasonably broad for a CHI paper, spanning a 16-singer data analysis, a 12-novice user study, and a 15-experienced-singer focus group, which supports claims about modality-specific usefulness rather than a single narrow demo. At the same time, the paper itself is careful about limits: it acknowledges short-term evaluation, cognitive load in reading raw signals, Bluetooth interference, small samples, and confounds in the comparison baseline. So the right reading is that this is a strong, well-grounded exploratory systems paper with promising evidence for EMG as a training aid, but not yet a fully mature deployment-ready vocal coaching platform.

What Changed

Canon before

Before this work, vocal training feedback was largely external and sound-based, leaving the internal muscle mechanisms that produce pitch hard to observe directly.

Departure from common sense

The paper argues that vocal training should not rely only on external sound-based feedback, because the relevant muscle activity is internal and invisible; instead, EMG and ultrasonography can expose the physical mechanisms behind pitch control for learners.

Actual novelty

The paper’s novelty is an accessible EMG+UI approach for collecting and evaluating vocal pitch, plus a reference-visualization system built from real-world data to make expert muscle activity visible for training and comparison. It also contributes a dual-modality dataset and a comparative analysis of how EMG, UI, and traditional coaching differ in usefulness, workload, and interpretability across novice and experienced singers.

Evidence

The paper frames the problem as one where singers typically receive only sound-based feedback and cannot directly observe the muscles controlling pitch. It then reports three studies: a 16-singer EMG/UI data analysis, a 12-novice user study of a visualization system, and a 15-experienced-singer focus group comparing the approach with traditional feedback. The discussion and limitations note short-term evaluation, cognitive load, Bluetooth interference, sample-size variability, and gender/developmental confounds.

Limits

Method limits

Immediate post-training evaluation may not capture long-term learning effects; interpreting raw EMG and UI can impose cognitive load; Bluetooth interference is noted as a practical issue; sample sizes are small and group variability is limited.

Deployment limits

The approach depends on sensing setups that may be less practical outside controlled or coached settings, and the paper notes usability and interference concerns that could affect real-world deployment.

Boundary conditions

Findings are bounded by the reported participant groups and modalities: beginners, experienced singers, professionals, novices, and experienced singers in focus groups. The authors also note gender and developmental confounds when comparing male adolescent participants against a female expert baseline.

Manual check: No additional manual check required beyond standard merge QA; evidence is grounded in the provided abstract and full text excerpts, but the exact full-text offsets were not independently re-verified here.

Position in field

This work sits at the intersection of HCI, sensing, and vocal training, extending feedback systems from external audio representations toward internal physiological visualization for skill development. It is best read as a mixed-methods CHI systems paper that strengthens a design direction rather than closing the question of long-term pedagogical impact.

Abstract

Vocal training is difficult because the muscles that control pitch, resonance, and phonation are internal and invisible to learners. This paper investigates how Electromyography (EMG) and ultrasonic imaging (UI) can make these muscles observable for training purposes. We report three studies. First, we analyze the EMG and UI data from 16 singers (beginners, experienced \& professionals), revealing differences among three vocal groups of the muscle control proficiency. Second, we use the collected data to create a system that visualizes an expert's muscle activity as reference. This system is tested in a user study with 12 novices, showing that EMG highlighted muscle activation nuances, while UI provided insights into vocal cord length and dynamics. Third, to compare our approach to traditional methods (audio analysis and coach instructions), we conducted a focus group study with 15 experienced singers. Our results suggest that EMG is promising for improving vocal skill development and enhancing feedback systems. We conclude the paper with a detailed comparison of the analyzed modalities (EMG, UI and traditional methods), resulting in recommendations to improve vocal muscle training systems.