Subphonetic modeling with Markov states-Senone
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 33-36 vol.1
- https://doi.org/10.1109/icassp.1992.225979
Abstract
There will never be sufficient training data to model all the various acoustic-phonetic phenomena. How to capture important clues and estimate those needed parameters reliably is one of the central issues in speech recognition. Successful examples include subword models, fenones and many other smoothing techniques. In comparison with subword models, subphonetic modeling may provide a finer level of details. The authors propose to model subphonetic events with Markov states and treat the state in phonetic hidden Markov models as the basic subphonetic unit-senone. Senones generalize fenones in several ways. A word model is a concatenation of senones and senones can be shared across different word models. Senone models not only allow parameter sharing, but also enable pronunciation optimization. The authors report preliminary senone modeling results, which have significantly reduced the word error rate for speaker-independent continuous speech recognition.Keywords
This publication has 11 references indexed in Scilit:
- Context-dependent modeling for acoustic-phonetic recognition of continuous speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Robust smoothing methods for discrete hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The Lincoln robust continuous speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Acoustic Markov models used in the Tangora speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Improved acoustic modeling with the SPHINX speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Automatic phonetic baseform determinationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Context-independent phonetic hidden Markov models for speaker-independent continuous speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
- The Lincoln tied-mixture HMM continuous speech recognizerPublished by Association for Computational Linguistics (ACL) ,1990
- An overview of the SPHINX speech recognition systemIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
- Improved acoustic modeling for continuous speech recognitionPublished by Association for Computational Linguistics (ACL) ,1990