Obtaining candidate words by polling in a large vocabulary speech recognition system
- 6 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 489-492
- https://doi.org/10.1109/icassp.1988.196626
Abstract
Considers the problem of rapidly obtaining a short list of candidate words for more detailed inspection in a large vocabulary, vector-quantizing speech recognition system. An approach called polling is advocated, in which each label produced by the vector quantizer casts a varying, real-valed vote for each word in the vocabulary. The words receiving the highest votes are placed on a short list to be matched in detail at a later stage of processing. Expressions are derived for these votes under the assumption that for any given word, the observed label frequencies have Poisson distributions. Although the method is more general, particular attention is paid to the implementation of polling in speech recognition systems which use hidden Markov models during the acoustic match computation. Results are presented of experiments with speaker-dependent and speaker-independent Markov models on two different isolated word recognition tasks.Keywords
This publication has 13 references indexed in Scilit:
- BYBLOS: The BBN continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Acoustic Markov models used in the Tangora speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Incorporation of Temporal Structure Into a Vector-Quantization-Based Preprocessor for Speaker-Independent, Isolated-Word RecognitionAT&T Technical Journal, 1985
- Vector quantization in speech codingProceedings of the IEEE, 1985
- Vector quantizationIEEE ASSP Magazine, 1984
- Discrete utterance speech recognition without time alignmentIEEE Transactions on Information Theory, 1983
- A statistical approach to the design of an adaptive self-normalizing silence detectorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1983
- An improved endpoint detector for isolated word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- Continuous speech recognition by statistical methodsProceedings of the IEEE, 1976
- [Back cover]IEEE Transactions on Acoustics, Speech, and Signal Processing, 1974