In a large vocabulary isolated word automatic speech recognition system, using Hidden Markov Models(HMM), it is time consuming to perform a detailed likelihood computation of an input utterance for all the words of the dictionary. A tree based A* search algorithm is presented for finding the N best word hypotheses, using a new likelihood estimator to drive time asyncronously the search. The proposed likelihood estimator has been tested with two different tasks: a large vocabulary (5000 words) multi-speaker radiological reports recognizer, and a 94 word speaker-independent command language recognizer. In both cases, the speed performance was improved by a factor of about 6, without losing admissibility. Using discrete models, the mean word hypothesis evaluation time is 8 ms on Sun4/330 workstation, the recognition rates vary from 94% to 98% depending on the speaker in the 5000 word task with a bigram language model, and 91% in the speaker-independent task.
Cite as: Antoniol, G., Brugnara, F., Giuliani, D. (1991) Admissible strategies for acoustic matching with a large vocabulary. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 589-592, doi: 10.21437/Eurospeech.1991-151
@inproceedings{antoniol91_eurospeech,
author={G. Antoniol and F. Brugnara and D. Giuliani},
title={{Admissible strategies for acoustic matching with a large vocabulary}},
year=1991,
booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)},
pages={589--592},
doi={10.21437/Eurospeech.1991-151}
}