Variable n-grams and extensions for conversational speech language modeling
- 1 January 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Speech and Audio Processing
- Vol. 8 (1) , 63-75
- https://doi.org/10.1109/89.817454
Abstract
No abstract availableKeywords
This publication has 20 references indexed in Scilit:
- Statistical language modeling using a variable context lengthPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Modeling disfluencies in conversational speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Word predictability after hesitations: a corpus-based studyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speaker normalization on conversational telephone speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An empirical study of smoothing techniques for language modelingComputer Speech & Language, 1999
- On structuring probabilistic dependences in stochastic language modellingComputer Speech & Language, 1994
- The zero-frequency problem: estimating the probabilities of novel events in adaptive text compressionIEEE Transactions on Information Theory, 1991
- A tree-based statistical language model for natural language speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Estimation of probabilities from sparse data for the language model component of a speech recognizerIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- On Turing's formula for word probabilitiesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1985