Hybrid HMM/ANN systems for training independent tasks: experiments on Phonebook and related improvements
- 22 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (15206149) , 1767-1770 vol.3
- https://doi.org/10.1109/icassp.1997.598872
Abstract
In this paper, we evaluate multi-Gaussian HMM systems and hybrid HMM/ANN systems in the framework of task independent training for small size (75 words) and medium size (600 words) vocabularies. To do this, we use the Phonebook database (Pitrelli et al., 1995) which is particularly well suited to this kind of experiment since (1) it is a very large telephone database and (2) the size and content of the test vocabulary is very flexible. For each system, different HMM topologies are compared to test the influence of state tying (with a number of parameters approximately kept constant) on the recognition performance. Two lexica (Phonebook and CMU) are also compared and it is shown that the CMU lexicon leads to significantly better performance. Finally, it is shown that with a quite simple system and a few adaptations to the basic HMM/ANN scheme, recognition performance of 98.5% and 94.7% can easily be achieved, respectively on a lexicon of 75 and 600 words (isolated words, telephone speech and lexicon words not present in the training data).Keywords
This publication has 6 references indexed in Scilit:
- On vocabulary-independent speech modelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- PhoneBook: a phonetically-rich isolated-word telephone-speech databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Digit recognition with stochastic perceptual speech modelsPublished by International Speech Communication Association ,1995
- Connectionist Speech RecognitionPublished by Springer Nature ,1994
- RASTA processing of speechIEEE Transactions on Speech and Audio Processing, 1994
- Maximum likelihood estimation for multivariate mixture observations of markov chains (Corresp.)IEEE Transactions on Information Theory, 1986