ReHEarSSE: Recognizing Hidden-in-the-Ear Silently Spelled Expressions

要旨

Silent speech interaction (SSI) allows users to discreetly input text without using their hands. Existing wearable SSI systems typically require custom devices and are limited to a small lexicon, limiting their utility to a small set of command words. This work proposes ReHearSSE, an earbud-based ultrasonic SSI system capable of generalizing to words that do not appear in its training dataset, providing support for nearly an entire dictionary's worth of words. As a user silently spells words, ReHearSSE uses autoregressive features to identify subtle changes in ear canal shape. ReHearSSE infers words using a deep learning model trained to optimize connectionist temporal classification (CTC) loss with an intermediate embedding that accounts for different letters and transitions between them. We find that ReHearSSE recognizes 100 unseen words with an accuracy of 89.3%.

著者
Xuefu Dong
The University of Tokyo, Tokyo, Japan
Yifei Chen
Tsinghua University, Beijing, China
Yuuki Nishiyama
The University of Tokyo, Tokyo, Japan
Kaoru Sezaki
The University of Tokyo, Tokyo, Japan
Yuntao Wang
Tsinghua University, Beijing, China
Ken Christofferson
University of Toronto, Toronto, Ontario, Canada
Alex Mariakakis
University of Toronto, Toronto, Ontario, Canada
論文URL

https://doi.org/10.1145/3613904.3642095

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Eye and Face

316B
5 件の発表
2024-05-14 18:00:00
2024-05-14 19:20:00