Robust smoothing methods for discrete hidden Markov models
Richard M. Schwartz, Owen Kimball, Francis Kubala, M.-W. Feng, Y.-L. Chow, Chris J. Barry, J. Makhoul · International Conference on Acoustics, Speech, and Signal Processing · 2003
Three methods for smoothing discrete probability functions in discrete hidden Markov models for large-vocabulary continuous-speech recognition are presented. The smoothing is based on deriving a probabilistic co-occurrence matrix between the different vector-quantized spectra. Each estimated probability density is then multiplied by this matrix, ensuring that none of the probabilities are severely underestimated due to lack of training data. Experimental results show a 20-30% reduction in error rate when this smoothing is used. A word error rate of 3.0% is achieved with the DARPA 1000-word continuous speech recognition database and a word-pair grammar with a perplexity of 60.>