At APSIPA 2023, Tatsunari Takagi, Nagito Shione, Keigo Hojo and Koharu Horii presented.

Oct.31-Nov.3, 2023, At APSIPA2023, Tatsunari Takagi, Nagito Shione, Keigo Hojo and Koharu Horii presented.

Streaming End-to-End ASR
Using CTC Decoder and DRA for
Linguistic Information Substitution Takagi

Construction of Automatic Speech Recognition
Model that Recognizes Linguistic Information and
Verbal/Non-verbal Phenomena Shione

Combining multiple end-to-end speech recognition
models based on density ratio approach Hojo

Language modeling for spontaneous speech
recognition based on disfluency labeling and
generation of disfluent text Horii

Break