Multilevel decoding for very-large-size-dictionary speech recognition
IBM Journal of Research and Development
Automatic discovery of contextual factors describing phonological variation
HLT '89 Proceedings of the workshop on Speech and Natural Language
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Tree-based state tying for high accuracy acoustic modelling
HLT '94 Proceedings of the workshop on Human Language Technology
High-accuracy large-vocabulary speech recognition using mixture tying and consistency modeling
HLT '94 Proceedings of the workshop on Human Language Technology
Evolution of the ASR decoder design
TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue
Task independent wordspotting using decision tree based allophone clustering
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Automatic rule extraction for modeling pronunciation variation
CICLing'11 Proceedings of the 12th international conference on Computational linguistics and intelligent text processing - Volume Part II
Direct construction of compact context-dependency transducers from data
Computer Speech and Language
Hi-index | 0.00 |
In a continuous speech recognition system it is important to model the context dependent variations in the pronunciations of words. In this paper we present an automatic method for modeling phonological variation using decision trees. For each phone we construct a decision tree that specifies the acoustic realization of the phone as a function of the context in which it appears. Several thousand sentences from a natural language corpus spoken by several talkers are used to construct these decision trees. Experimental results on a 5000-word vocabulary natural language speech recognition task are presented.