Evaluation on unsupervised speaker adaptation based on sufficient hmm statistics of selected speakers

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Volumn , Issue , 2001, Pages 1219-1222

  Yoshizawa, Shinichi ^a   Baba, Akira ^a   Matsunami, Kanako ^a   Mera, Yuichirou ^a   Yamada, Miichi ^a   Lee, Akinobu ^a   Shikano, Kiyohiro ^a  

^a PANASONIC CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CLUSTERING ALGORITHMS;

CLUSTERING METHODS; CLUSTERING RESULTS; MODEL PARAMETERS; SPEAKER INDEPENDENT MODEL; SUFFICIENT STATISTICS; UNSUPERVISED SPEAKER ADAPTATION;

SPEECH COMMUNICATION;

EID: 85009085878     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. Yuqing Gao, Mukund Padmanabhan and Michael Picheny, "SPEAKER ADAPTATION BASED ON PRECLUSTERING TRAINING SPEAKERS", Proceedings of the Eurospeech, pp.2091-2094, 1999.
2. M.Padmanabhan, L.R.Bahal, D.Nahamoo and M.A.Picheny, "Speaker Clustering And Transformation For Speaker Adaptation In Large-Vocabulary Speech Recognition System", Proceedings of the ICASSP, pp.701-704, 1995.
3. C.J.Leggetter and C.Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models", Computer Speech and Language, Vol.9, pp.171-185, 1995.
4. Akinobu Lee, Tatsuya Kawahara, Kazuya Takeda and Kiyohiro Shikano, "A New Phonetic Tiedmixture Model For Efficient Decoding", Proceedings of the the ICASSP, pp.1269-1272, 2000.
5. Katunobu Itou, Mikio Yamamoto, Kazuya Takeda, Toshiyuki Takezawa, Tatsuo Matsuoka, Tetsunori Kobayashi, Kiyohiro Shikano and Shuichi Itahashi, "JNAS:Japanese speech corpus for large vocabulary continuous speech recognition research", The Journal of the Acoustical Society of Japan (E), Vol.20, pp.199-206, 1999.
6. Shinichi Yoshizawa, Akira Baba, Kanako Matsunami, Yuichiro Mera, Miichi Yamada, Kiyohiro Shikano, "Unsupervised Speaker Adaptation Based on Sufficient HMM Statistics of Selected Speakers", Proceedings of the ICASSP, 2001.