Comparison of discrete and continuous HMMs in a CSR task over the telephone
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 253-256 vol. 1
- https://doi.org/10.1109/icassp.1991.150325
Abstract
Attention is given to a comparison of the performance of discrete and continuous density hidden Markov models (DDHMMs and CDHMMs) on a 786-word E-mail inquiry task performed by the speaker-independent word recognition component of a speech understanding system. This comparison between DDHMMs and CDHMMs has also been carried out by training speaker-dependent models. The authors also present the results of a set of experiments carried out with the aim at automatically selecting a suitable set of subword unit models by a clustering procedure. The recognizer gives word accuracy (WA) rates of 67.8% and 75.3% by using DDHMMs and CDHMMs, respectively, without any linguistic constraints. On the same task, WA rates of 87.1% and 85.9% have been obtained in the speaker-dependent mode.Keywords
This publication has 8 references indexed in Scilit:
- Experimental results on large-vocabulary continuous speech recognition and understandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Acoustic modeling of subword units for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Context-Dependent Phonetic Hidden Markov Models for Speaker-Independent Continuous Speech RecognitionPublished by Springer Nature ,1992
- Lexical access to large vocabularies for speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- A Segmentalk-Means Training Procedure for Connected Word RecognitionAT&T Technical Journal, 1986
- Speaker-independent isolated word recognition using dynamic features of speech spectrumIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986
- A Maximum Likelihood Approach to Continuous Speech RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980