Speech recognition with very large size dictionary
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 12, 364-367
- https://doi.org/10.1109/icassp.1987.1169731
Abstract
This paper proposes a new strategy, the Multi-Level Decoding (MLD), that allows to use a Very Large Size Dictionary (VLSD, size more than 100,000 words) in speech recognition. MLD proceeds in three steps:\bulleta Syllable Match procedure uses an acoustic model to build a list of the most probable syllables that match the acoustic signal from a given time frame.\bulletfrom this list, a Word Match procedure uses the dictionary to build partial word hypothesis.\bulletthen a Sentence Match procedure uses a probabilistic language model to build partial sentence hypothesis until total sentences are found. An original matching algorithm is proposed for the Syllable Match procedure. This strategy is experimented on a dictation task of French texts. Two different dictionaries are tested,\bulletone composed of the 10,000 most frequent words,\bulletthe other composed of 200,000 words. The recognition results are given and compared. The error rate on words with 10,000 words is 17.3%. If the errors due to the lack of coverage are not counted, the error rate with 10,000 words is reduced to 10.6%. The error rate with 200,000 words is 12.7%.Keywords
This publication has 5 references indexed in Scilit:
- An IBM PC based large-vocabulary isolated-utterance speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Context-dependent phonetic Markov models for large vocabulary speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Natural Language Modeling for Phoneme-to-Text TranscriptionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- A Maximum Likelihood Approach to Continuous Speech RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1983
- Continuous speech recognition by statistical methodsProceedings of the IEEE, 1976