DocumentCode :
3004094
Title :
The role of word-dependent coarticulatory effects in a phoneme-based speech recognition system
Author :
Chow, Yen-Lu ; Schwartz, Richard ; Roucos, Salim ; Kimball, Owen ; Price, Patti ; Kubala, Francis ; Dunham, Mari O. ; Krasner, Michael ; Makhoul, John
Author_Institution :
BBN Laboratories, Cambridge, MA
Volume :
11
fYear :
1986
fDate :
31503
Firstpage :
1593
Lastpage :
1596
Abstract :
This paper describes the results of our work in designing a system for large-vocabulary word recognition of continuous speech. We generalize the use of context-dependent Hidden Markov Models (HMM) of phonemes to take into account word-dependent coarticulatory effects, Robustness is assured by smoothing the detailed word-dependent models with less detailed but more robust models. We describe training and recognition algorithms for HMMs of phonemes-in-context. On a task with a 334-word vocabulary and no grammar (i.e., a branching factor of 334), in speaker-dependent mode, we show an average reduction in word error rate from 24% using context-independent phoneme models, to 10% when using robust context-dependent phoneme models.
Keywords :
Context modeling; Databases; Error analysis; Hidden Markov models; Laboratories; Robustness; Smoothing methods; Speech recognition; Testing; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '86.
Type :
conf
DOI :
10.1109/ICASSP.1986.1168931
Filename :
1168931
Link To Document :
بازگشت