KITAOKA LAB 音声言語処理研究室 豊橋技術科学大学 情報・知能工学系 北岡研 北岡研究室



Streaming End-to-End ASR
Using CTC Decoder and DRA for
Linguistic Information Substitution 高城
Construction of Automatic Speech Recognition
Model that Recognizes Linguistic Information and
Verbal/Non-verbal Phenomena 塩根
Combining multiple end-to-end speech recognition
models based on density ratio approach 北條
Language modeling for spontaneous speech
recognition based on disfluency labeling and
generation of disfluent text 堀井