A robust connected-words recognizer

Speaker-independent recognition of connected words is considered. Robustness against variations of both background noise and frequency responses of microphones and transmission lines is improved by using a high-pass filter to reduce stationary or slowly varying parts of the spectral components in the feature vectors. A method is proposed for improving the power of references generated from isolated words by combining them with duration models derived from a small set of connected words. Results of experiments to improve recognition accuracy using speaker-dependent adaptation of the hidden Markov models' transition probabilities and of feature vectors are presented. Results are given for a German corpus and the TI/NIST connected digits corpus.<<ETX>>

[1]  Biing-Hwang Juang,et al.  HMM clustering for connected word recognition , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

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

[3]  Chin-Hui Lee,et al.  Improvements in connected digit recognition using higher order spectral and energy features , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[4]  Hermann Dr Ney.  Speech recognition in a neural network framework: discriminative training of Gaussian models and mixture densities as radial basis functions , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[5]  M. Kuhn,et al.  Improvements in isolated word recognition , 1983 .

[6]  Stefan Dobler,et al.  Speech recognition in the noisy car environment , 1989, Speech Commun..

[7]  Hans-Günter Hirsch,et al.  Improved speech recognition using high-pass filtering of subband envelopes , 1991, EUROSPEECH.