Network-based connected digit recognition

A system for speaker-independent connected digit recognition is described in which explicit acoustic-phonetic features and constraints play a significant role. The digit vocabulary is modeled using a finite-state pronunciation network whose branches correspond to meaningful acoustic-phonetic units. Each branch is associated with an acoustic pattern matcher which employs a combination of whole-spectrum and feature-based metrics. The system has been evaluated using 17 000 utterances from the Texas Instruments (TI) multidialect, connected digits database. The best configurations of the recognizer achieve string recognition accuracies of approximately 96 and 97 percent when the length of the input string is unknown and known, respectively, and when different talkers are used for training and testing.

[1]  F. Itakura,et al.  Minimum prediction residual principle applied to speech recognition , 1975 .

[2]  F. Jelinek,et al.  Continuous speech recognition by statistical methods , 1976, Proceedings of the IEEE.

[3]  R. Gray,et al.  Speech coding based upon vector quantization , 1980, ICASSP.

[4]  G. R. Doddington,et al.  Computers: Speech recognition: Turning theory to practice: New ICs have brought the requisite computer power to speech technology; an evaluation of equipment shows where it stands today , 1981, IEEE Spectrum.

[5]  L. Rabiner,et al.  Isolated and Connected Word Recognition - Theory and Selected Applications , 1981, IEEE Transactions on Communications.

[6]  Ronald A. Cole,et al.  Feature-based speaker-independent recognition of isolated english letters , 1983, ICASSP.

[7]  Pietro Laface,et al.  Computer recognition of plosive sounds using contextual information , 1983 .

[8]  L. R. Rabiner,et al.  On the application of vector quantization and hidden Markov models to speaker-independent, isolated word recognition , 1983, The Bell System Technical Journal.

[9]  M. Tomlinson,et al.  The discriminative network: A mechanism for focusing recognition in whole-word pattern matching , 1983, ICASSP.

[10]  Akira Ichikawa,et al.  Speaker-independent connected digit recognition , 1984, ICASSP.

[11]  Victor Zue,et al.  Application of allophonic and lexical constraints in continuous digit recognition , 1984, ICASSP.

[12]  Hermann Ney,et al.  The use of a one-stage dynamic programming algorithm for connected word recognition , 1984 .

[13]  J. A. Naylor,et al.  Effect of vector quantization on a continuous speech recognition system , 1984, ICASSP.

[14]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.

[15]  R. G. Leonard,et al.  A database for speaker-independent digit recognition , 1984, ICASSP.

[16]  Lawrence R. Rabiner,et al.  On the application of embedded digit training to speaker independent connected digit recognition , 1984 .

[17]  L. R. Rabiner,et al.  On the application of energy contours to the recognition of connected word sequences , 1984, AT&T Bell Laboratories Technical Journal.

[18]  Comparative study of several distortion measures for speech recognition , 1985, Speech Commun..

[19]  D. Burton,et al.  Isolated-word speech recognition using multisection vector quantization codebooks , 1984, IEEE Trans. Acoust. Speech Signal Process..

[20]  Dennis H. Klatt,et al.  Comparative study of several distortion measures for speech recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[21]  Biing-Hwang Juang,et al.  Mixture autoregressive hidden Markov models for speech signals , 1985, IEEE Trans. Acoust. Speech Signal Process..

[22]  M. Bush,et al.  Network-based connected digit recognition using vector quantization , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[23]  Carlo Scagliola,et al.  A connected speech recognition system using a diphone-based language model , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[24]  J. Damestoy,et al.  A frame language for the control of phonetic decoding in continuous speech recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[25]  Gary E. Kopec,et al.  Network-based isolated digit recognition using vector quantization , 1985, IEEE Trans. Acoust. Speech Signal Process..

[26]  Hervé Bourlard,et al.  Speaker dependent connected speech recognition via phonetic Markov models , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[27]  George R. Doddington,et al.  Frame-specific statistical features for speaker independent speech recognition , 1986, IEEE Trans. Acoust. Speech Signal Process..

[28]  Gary E. Kopec.  Formant tracking using hidden Markov models and vector quantization , 1986, IEEE Trans. Acoust. Speech Signal Process..

[29]  Stephen E. Levinson,et al.  Continuously variable duration hidden Markov models for speech analysis , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[30]  Sadaoki Furui,et al.  Speaker-independent isolated word recognition using dynamic features of speech spectrum , 1986, IEEE Trans. Acoust. Speech Signal Process..