HMM COMPOSITION OF SEGMENTAL UNIT INPUT HMM FOR NOISY SPEECH RECOGNITION

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 2865-2868

  Yamamoto, Kazumasa ^a   Nakagawa, Seiichi ^a  

^a TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ADDITIVE NOISE; SPEECH COMMUNICATION; SPEECH RECOGNITION;

CEPSTRAL DOMAIN; COVARIANCE MATRICES; INPUT MODELS; INPUT VECTOR; INVERSE TRANSFORMATIONS; KARHUNEN LOEVE EXPANSION; NOISY ENVIRONMENT; NOISY SPEECH RECOGNITION; PARALLEL MODEL COMBINATIONS; ROBUST SPEECH RECOGNITION;

COVARIANCE MATRIX;

EID: 0011448901     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. J.Koehler, N.Morgan, H.Hermansky, H.Gunter-Hirsh and G.Tong, "Integrating RASTA-PLP into speech recognition," Proc.ICASSP-94, pp.I-421-I-424, Apr. 1994.
2. K.Aikawa, H.Singer, H.Kawahara and Y.Tohkura, "Cepstral representation of speech motivated by time-frequency masking: An application to speech recogni-
3. S.F.Boll, "Suppression of acoustic noise in speech using spectral subtraction," IEEE Trans. Acoust., Speech & Signal Process., Vol.27, no.2, pp.113-120, Feb. 1979.
4. M.Rahim and B.-H.Juang, "Signal bias removal for robust telephone based speech recognition in adverse environments," Proc.ICASSP-94, pp.I-445-I-448, Apr. 1994.
5. A.Acero and R.M.Stern, "Environmental robustness in automatic speech recognition," Proc.ICASSP-90, pp.849-852, Apr. 1990.
6. A.P.Varga and P.K.Moore, "Hidden Markov model decomposition of speech and noise," Proc.ICASSP-90, pp.845-848, Apr. 1990.
7. K.Takagi, H.Hattori and T.Watanabe, "Rapid environment adaptation for speech recognition," J. Acoust. Soc. Jpn.(E), Vol.16, no.5, pp.273-281, Sep. 1995.
8. M.J.F.Gales and S.J.Young: Cepstral parameter compensation for HMM recognition in noise, Speech Communication, vol.12, no.3, pp.231-239(1993)
9. S.Nakagawa and K.Yamamoto, "Evaluation of segmental unit input HMM," ICASSP-96, pp.439-442, 1996.
10. K.Yamamoto and S.Nakagawa, "Evaluation of segmental unit input HMM in noisy environments," Proc. ICSP'97, pp.643-648, Aug. 1997.
11. Y.Tsurumi and S.Nakagawa, "An unsupervised speaker adaptation method for continuous parameter HMM by maximum a posteriori probability estimation," ICSLP-94, pp.431-434, Sept. 1994.
12. S.Itahashi, "Recent speech database projects in Japan, " ICSLP-90, pp.1081-1084, 1990.