A comparative study of continuous speech recognition using neural networks and hidden Markov models
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 369-372 vol.1
- https://doi.org/10.1109/icassp.1991.150353
Abstract
The recognition performances of two front ends are compared for two continuous speech recognition tasks. First, a neural network model (NNM) front end was used, with frame labeling performed by a radial basis function network and segmentation by a Viterbi algorithm. The second front end was a discrete hidden Markov model (HMM), featuring explicit state duration probability distributions. Two experiments were performed. The first used a speaker-dependent database, with a lexicon of 571 words. Using a low-perplexity grammar, the NNM front end produced a word accuracy of 94% and a sentence accuracy of 86%. This was slightly inferior to the HMM front end, which produced word accuracies of 96% and sentence accuracies of 88%. Without a grammar, word accuracies of 58% (NNM) and 49% (HMM) were recorded. The second set of experiments used the MIT portion of the TIMIT database (415 speakers and 2072 sentences in total). Results were poor for both front ends, with the NNM producing marginally better results.Keywords
This publication has 7 references indexed in Scilit:
- Maximum mutual information estimation of hidden Markov model parameters for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Learning phoneme recognition using neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Continuous speech recognition for the TIMIT database using neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Alpha-nets: A recurrent ‘neural’ network architecture with a hidden Markov model interpretationSpeech Communication, 1990
- Speech pattern discrimination and multilayer perceptronsComputer Speech & Language, 1989
- The 'neural' phonetic typewriterComputer, 1988
- An acoustic-phonetic data baseThe Journal of the Acoustical Society of America, 1987