Heterogeneous measurements and multiple classifiers for speech recognition

This paper addresses the problem of acoustic phonetic modeling. First, heterogeneous acoustic measurements are chosen in order to maximize the acoustic-phonetic information extracted from the speech signal in preprocessing. Second, classifier systems are presented for successfully utilizing high-dimensional acoustic measurement spaces. The techniques used for achieving these two goals can be broadly categorized as hierarchical, committeebased, or a hybrid of these two. This paper presents committeebased and hybrid approaches. In context-independent classification and context-dependent recognition on the TIMIT core test set using 39 classes, the system achieved error rates of 18.3% and 24.4%, respectively. These error rates are the lowest we have seen reported on these tasks. In addition, experiments with a telephone-based weather information word recognition task led to word error rate reductions of 10–16%.

[1]  Hsiao-Wuen Hon,et al.  Speaker-independent phone recognition using hidden Markov models , 1989, IEEE Trans. Acoust. Speech Signal Process..

[2]  Jean-Luc Gauvain,et al.  High performance speaker-independent phone recognition using CDHMM , 1993, EUROSPEECH.

[3]  James R. Glass,et al.  A probabilistic framework for feature-based speech recognition , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[4]  Richard Lippmann,et al.  Speech recognition by machines and humans , 1997, Speech Commun..

[5]  James R. Glass,et al.  HETEROGENEOUS ACOUSTIC MEASUREMENTS FOR PHONETIC CLASSIFICATION , 1997 .

[6]  Stephen A. Zahorian,et al.  Phone classification with segmental features and a binary-pair partitioned neural network classifier , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  James R. Glass,et al.  Segmentation and modeling in segment-based recognition , 1997, EUROSPEECH.

[8]  Steven C. Lee.  Probabilistic segmentation for segment-based speech recognition , 1998 .

[9]  James R. Glass,et al.  Telephone-based conversational speech recognition in the JUPITER domain , 1998, ICSLP.

[10]  Jane W. Chang,et al.  Near-miss modeling: a segment-based approach to speech recognition , 1998 .

[11]  Andrew K. Halberstadt,et al.  Using aggregation to improve the performance of mixture Gaussian acoustic models , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[12]  Francis Jack Smith,et al.  Improved phone recognition using Bayesian triphone models , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).