A
Akira Baba
Publications - 10
Citations - 168
Akira Baba is an academic researcher. The author has contributed to research in topics: Speaker recognition & Speaker diarisation. The author has an hindex of 5, co-authored 10 publications receiving 158 citations.
Papers
More filters
Journal ArticleDOI
Acoustic models of the elderly for large‐vocabulary continuous speech recognition
TL;DR: It is verified experimentally that the recognition rate is further improved in speaker adaptation to elderly speech by making use of an acoustic model trained by elderly speech.
Proceedings ArticleDOI
Unsupervised speaker adaptation based on sufficient HMM statistics of selected speakers
TL;DR: The proposed method can obtain a more optimal speaker cluster because the clustering result is determined according to test speaker's data on-line, and the proposed method attains better improvement than MLLR from the speaker independent model.
Proceedings Article
Elderly Acoustic Model for Large Vocabulary Continuous Speech Recognition
TL;DR: EUROSPEECH2001: the 7th European Conference on Speech Communication and Technology, September 3-7, 2001, Aalborg, Denmark.
Proceedings Article
Evaluation on Unsupervised Speaker Adaptation Based on Sufficient HMM Statictics of Selected Speakers
Shinichi Yoshizawa,Akira Baba,Kanako Matsunami,Yuichirou Mera,Miichi Yamada,Akinobu Lee,Kiyohiro Shikano +6 more
TL;DR: This paper describes an efficient method of unsupervised speaker adaptation based on selecting a subset of speakers who are acoustically close to a test speaker and calculating adapted model parameters according to the previously stored sufficient statistics of the selected speakers’ data.
Proceedings Article
Spectral Subtraction in Noisy Environments Applied to Speaker Adaptation Based on HMM Sufficient Statistics
TL;DR: ICSLP2002: the 7th International Conference on Spoken Language Processing, September 16-20, 2002, Denver, Colorado, USA.