Improved vocabulary-independent sub-word HMM modelling
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 181-184 vol.1
- https://doi.org/10.1109/icassp.1991.150307
Abstract
The authors describe two techniques for improving the performance of subword recognition on open vocabularies using vocabulary-independent training. The first uses a subtriphone unit called a phonicle to allow triphones which have not been encountered in the training data to be built from contexts which have been sufficiently trained. The second uses linear discriminant analysis to improve discrimination between sound classes. The two techniques have been evaluated for speaker-dependent operation on an open vocabulary task. The recognizer is based on hidden Markov modeling (HMM) using continuous probabilities. The results obtained show that both techniques lead to improved recognition performance.Keywords
This publication has 5 references indexed in Scilit:
- A comparison of several acoustic representations for speech recognition with degraded and undegraded speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Allophone clustering for continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The ARM continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- On vocabulary-independent speech modelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Proceedings of the 3rd international conference on Supercomputing - ICS '89Published by Association for Computing Machinery (ACM) ,1989