Speaker adaptation of quantized parameter HMMs

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

Volumn , Issue , 2001, Pages 1265-1268

  Vasilache, Marcel ^a   Viikki, Olli ^a  

^a NOKIA RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; MARKOV PROCESSES; SPEECH COMMUNICATION; STATISTICAL TESTS;

ADAPTATION FRAMEWORK; ADAPTATION SCHEME; BAYESIAN ADAPTATION; QUANTIZED PARAMETERS; REDUCED MEMORY REQUIREMENTS; SPEAKER ADAPTATION; SPEAKER ADAPTIVE TRAININGS; SPEAKER-INDEPENDENT SPEECH RECOGNITION;

SPEECH RECOGNITION;

EID: 85009115370     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Gauvain, J.-L, Lee, C-H., "Maximum a posteriori estimation of multivariate Gaussian mixture observations of Markov chains", IEEE Trans. on Speech and Audio Processing, Vol. 2, No. 2, pp. 291-298, 1994.
2. Leggetter, C. J., Woodland, P. C., "Speaker adaptation of HMMs using linear regression", Proc. of International Conference on Spoken Language Processing, Yokohama, Japan, 1994.
3. Riis, S. K., "Hidden neural networks: Application to speech recognition'', Proc. of International Conference on Acoustics, Speech, and Signal Processing, Seattle, WA, USA, 1998.
4. Riis, S. K., Viikki, O., "Low complexity speakerindependent command word recognition in car environments", Proc. of International Conference on Acoustics, Speech, and Signal Processing, Istanbul, Turkey, 2000.
5. Vasilache, M., "Speech recognition using HMMs with quantized parameters", Proc. of International Conference on Spoken Language Processing, Beijing, China, 2000.
6. Viikki O., Bye D., and Laurila K., "A recursive feature vector normalization approach for robust speech recognition in noise", Proc. of International Conference on Acoustics, Speech, and Signal Processing, Seattle, WA, USA, 1998.
7. Pan J., Yuan B. and Yan Y., "Effective vector quantization for a highly compact acoustic model for LVCSR", Proc. of International Conference on Spoken Language Processing, Beijing, China, 2000.