%0 Conference Paper %1 Kimura2019-tx %A Kimura, Naoki %A Kono, Michinari %A Rekimoto, Jun %B Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems %C New York, NY, USA %D 2019 %I Association for Computing Machinery %K deep human-ai imaging, integration, interaction, networks, neural silent speech speech;subvocal ultrasonic %N Paper 146 %P 1--11 %T SottoVoce: An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks %X The availability of digital devices operated by voice is expanding rapidly. However, the applications of voice interfaces are still restricted. For example, speaking in public places becomes an annoyance to the surrounding people, and secret information should not be uttered. Environmental noise may reduce the accuracy of speech recognition. To address these limitations, a system to detect a user's unvoiced utterance is proposed. From internal information observed by an ultrasonic imaging sensor attached to the underside of the jaw, our proposed system recognizes the utterance contents without the user's uttering voice. Our proposed deep neural network model is used to obtain acoustic features from a sequence of ultrasound images. We confirmed that audio signals generated by our system can control the existing smart speakers. We also observed that a user can adjust their oral movement to learn and improve the accuracy of their voice recognition.

@inproceedings{Kimura2019-tx, abstract = {The availability of digital devices operated by voice is expanding rapidly. However, the applications of voice interfaces are still restricted. For example, speaking in public places becomes an annoyance to the surrounding people, and secret information should not be uttered. Environmental noise may reduce the accuracy of speech recognition. To address these limitations, a system to detect a user's unvoiced utterance is proposed. From internal information observed by an ultrasonic imaging sensor attached to the underside of the jaw, our proposed system recognizes the utterance contents without the user's uttering voice. Our proposed deep neural network model is used to obtain acoustic features from a sequence of ultrasound images. We confirmed that audio signals generated by our system can control the existing smart speakers. We also observed that a user can adjust their oral movement to learn and improve the accuracy of their voice recognition.}, added-at = {2023-06-06T00:19:46.000+0200}, address = {New York, NY, USA}, author = {Kimura, Naoki and Kono, Michinari and Rekimoto, Jun}, biburl = {https://www.bibsonomy.org/bibtex/2ea62bc42ceb99fa8187cffdba07bce36/willwade}, booktitle = {Proceedings of the 2019 {CHI} Conference on Human Factors in Computing Systems}, interhash = {9e4d71101e024cb5ff254c7555aa6ff4}, intrahash = {ea62bc42ceb99fa8187cffdba07bce36}, keywords = {deep human-ai imaging, integration, interaction, networks, neural silent speech speech;subvocal ultrasonic}, location = {Glasgow, Scotland Uk}, month = may, number = {Paper 146}, pages = {1--11}, publisher = {Association for Computing Machinery}, series = {CHI '19}, timestamp = {2023-06-06T00:20:15.000+0200}, title = {{SottoVoce}: An Ultrasound {Imaging-Based} Silent Speech Interaction Using Deep Neural Networks}, year = 2019 }