Shoei Sato

发表

Consideration of Class Labels for Japanese End-to-End Speech Recognition

Aiko Hagiwara, Hitoshi Ito, Manon Ichiki, 2017 .

Low-latency speaker diarization based on Bayesian information criterion with multiple phoneme classes

Shoei Sato, Akio Kobayashi, Shinichi Homma, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech recognition with a seamlessly updated language model for real-time closed-captioning

Shoei Sato, Akio Kobayashi, Shinichi Homma, 2010, INTERSPEECH.

Speech Detection and Dual-G Captioning Broad

Shoei Sato, A. Kobayashi, T. Imai, 2006 .

Real-Time Closed-Captioning Using Speech Recognition

Satoshi Hara, Shoei Sato, A. Kobayashi, 2007 .

Acoustic model adaptation by selective training using two‐stage clustering

Hiroyuki Segi, Kazuo Onoe, Shoei Sato, 2005 .

Selective training of HMMs by using two-stage clustering

Shoei Sato, Akio Ando, Hideki Tanaka, 2000, INTERSPEECH.

Text-Only Domain Adaptation Based on Intermediate CTC

Tetsuji Ogawa, Shoei Sato, Tomoyasu Komori, 2022, INTERSPEECH.

Low-Frequency Character Clustering for End-to-End ASR System

Shoei Sato, Akio Kobayashi, Takeshi Mishima, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Word Error Rate Minimization Using an Integrated Confidence Measure

Kazuo Onoe, Shoei Sato, Akio Kobayashi, 2007, IEICE Trans. Inf. Syst..

Bi-Spectral Acoustic Features for Robust Speech Recognition

Kazuo Onoe, Shoei Sato, Akio Kobayashi, 2008, IEICE Trans. Inf. Syst..