Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Connected Digit Recognition Using Connectionist Probability Estimators and Mixture-Gaussian Densities

David M. Lubensky, Ayman O. Asadi, Jayant M. Naik

Speech Recognition and Language Understanding Laboratory, NYNEX Science & Technology, Inc., White Plains, NY, USA

We report on some recent improvements to a continuous density hidden Markov model (CDHMM) based speech recognition system which is being developed for a variety of telecommunication applications. In particular, we are concerned with computing the emission probabilities of an HMM state using a combination of multi-layer perceptrons (MLPs) as probability estimators and mixture-Gaussian densities. Using MLPs as state observation estimators has been shown to improve accuracy on a speaker verification task [11]. In this paper, we describe a connected digit recognition system which incorporates both MLPs and mixture, Gaussian densities. The results are reported on the standard Texas Instruments (TI) connected digit database [9] which was digitally filtered to the telephone bandwidth (300 Hz-3.2 kHz) and downsampled to 8 kHz. A hybrid MLP/HMM system led to 15% improvement in performance. The final string error rate is 1.7% for unknown length strings.

Full Paper

Bibliographic reference.  Lubensky, David M. / Asadi, Ayman O. / Naik, Jayant M. (1994): "Connected digit recognition using connectionist probability estimators and mixture-Gaussian densities", In ICSLP-1994, 295-298.