
Hongo Campus
Assistive technology for speech communication using computers that can talk with, listen to, and support users
Speech-to-text (speech recognition) and text-to-speech (speech synthesis) are working well even on smartphones. In our laboratory, using these speech technologies, we are developing frameworks that can aid humans to realize high-quality speech communication with other humans or with machines. By acquiring various kinds of knowlege such as acoustic phonetics, cognitive science, linguistics, and brain sciences as well as speech technologies, we are trying to improve the QoL of individuals who are communicating orally with others.
Monitoring listening behaviors and its application to realize high-quality speech communication

Monitoring speaking behaviors and its application to realize high-quality speech communication

Analysis and modeling of international speech communication with World Englishes

Acoustic embodiment of information on speech such as speech synthesis, emotion synthesis, voice convertion, accent convertion, etc

Information extraction from speech acoustics such as speech recognition, speaker recognition, emotion recognition, speech assessment, etc
