SottoVoce: An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks
This addresses the need for discreet and noise-robust voice interfaces for users in public or confidential environments, representing a novel application rather than an incremental improvement.
The paper tackled the problem of voice interfaces being unsuitable in noisy or private settings by developing a silent speech interaction system using ultrasound imaging and deep neural networks to recognize unvoiced utterances, enabling control of smart speakers with generated audio signals.
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.