Three different probabilistic language models: comparison and combination
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 297-300 vol. 1
- https://doi.org/10.1109/icassp.1991.150335
Abstract
The authors outline the different problems that arise when using a statistical language model for speech recognition, especially for inflected languages such as French, Italian or German. After a brief review of two classical models (TriPOS and Trigram), the authors present a refinement of the morphological language model (Trilemma). They give the different methods used to evaluate performances. They discuss combination experiments between two of these three building blocks and present a model which takes advantage of all three models through a backing-off strategy. Assuming the same vocabulary (20000 forms), experiments show equivalent results using either a classical trigram language model or a trilemma model. The second model can be extended to a full dictionary containing all the inflected forms of each lemma, whereas the first needs a large amount of data to perform such a task.Keywords
This publication has 7 references indexed in Scilit:
- Speech recognition with very large size dictionaryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Language model and acoustic model information in probabilistic speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Recent advances in speech processingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Three probabilistic language models for a large-vocabulary speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A cache-based natural language model for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Estimation of probabilities from sparse data for the language model component of a speech recognizerIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- Natural Language Modeling for Phoneme-to-Text TranscriptionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986