New ways to use LVQ-codebooks together with hidden Markov models

We introduce a novel way to employ codebooks trained by learning vector quantization together with hidden Markov models. In previous work, LVQ-codebooks have been used as frame labelers. The resulting label stream has been modeled and decoded by discrete observation HMMs. We present a way to extract more information out of the LVQ stage. This is accomplished by modeling the class-wise quantization errors of LVQ by continuous density HMMs. Experiments in a speaker dependent phoneme spotting task verify that significant improvements are attainable over plain continuous density HMMs, or over the hybrid of LVQ and discrete HMMs.<<ETX>>

[1]  Jorma Laaksonen,et al.  LVQPAK: A software package for the correct application of Learning Vector Quantization algorithms , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[2]  Steve Young,et al.  COMPETITIVE TRAINING - A CONNECTIONIST APPROACH TO THE DISCRIMINATIVE TRAINING OF HIDDEN MARKOV-MODELS , 1991 .

[3]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[4]  Steve J. Young,et al.  Recurrent input transformations for hidden Markov models , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[6]  John Makhoul,et al.  Discriminant analysis and supervised vector quantization for continuous speech recognition , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[7]  Teuvo Kohonen,et al.  LVQ-based speech recognition with high-dimensional context vectors , 1992, ICSLP.

[8]  Mikko Kurimo,et al.  Status Report Of The Finnish Phonetic Typewriter Project , 1991 .

[9]  A. Dale Magoun,et al.  Decision, estimation and classification , 1989 .

[10]  M. A. Bush,et al.  Speaker-independent vowel classification using hidden Markov models and LVQ2 , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[11]  Shigeru Katagiri,et al.  Speaker-independent large vocabulary word recognition using an LVQ/HMM hybrid algorithm , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[12]  Shigeru Katagiri,et al.  A hybrid speech recognition system using HMMs with an LVQ-trained codebook , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[13]  Steve J. Young,et al.  MMI training for continuous phoneme recognition on the TIMIT database , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  Hideyuki Suzuki,et al.  A new speech recognition method based on VQ-distortion measure and HMM , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[15]  Dirk Van Compernolle,et al.  Using parallel MLPs as labelers for multiple codebook HMMs , 1993, ICASSP.

[16]  Hervé Bourlard,et al.  Neural nets and hidden Markov models: Review and generalizations , 1991, Speech Commun..

[17]  Shigeki Sagayama,et al.  Appropriate error criterion selection for continuous speech HMM minimum error training , 1992, ICSLP.

[18]  T. Kohonen,et al.  Appendix 2.4 Stopping Rule 2.3 Fine Tuning Using the Basic Lvq1 or Lvq2.1 Lvq Pak: a Program Package for the Correct Application of Learning Vector Quantization Algorithms , 1992 .

[19]  E. McDermott,et al.  A hybrid speech recognition system using HMMs with an LVQ-trained codebook , 1990 .

[20]  C. Lefebvre,et al.  A comparison of several acoustic representations for speech recognition with degraded and undegraded speech , 1989, International Conference on Acoustics, Speech, and Signal Processing,.