DocumentCode :
3017174
Title :
A stochastic segment model for phoneme-based continuous speech recognition
Author :
Roucos, S. ; Dunham, M.O.
Author_Institution :
BBN Laboratories Incorporated, Cambridge, MA
Volume :
12
fYear :
1987
fDate :
31868
Firstpage :
73
Lastpage :
76
Abstract :
Developing accurate and robust phonetic models for the different speech sounds is a major challenge for high performance continuous speech recognition. In this paper, we introduce a new approach, called the stochastic segment model, for modelling a variable-length phonetic segment X, an L-long sequence of feature vectors. The stochastic segment model consists of 1) time-warping the variable-length segment X into a fixed-length segment Y called a resampled segment, and 2) a joint density function of the parameters of the resampled segment Y, which in this work is assumed Gaussian. In this paper, we describe the stochastic segment model, the recognition algorithm, and the iterative training algorithm for estimating segment models from continuous speech. For speaker-dependent continuous speech recognition, the segment model reduces the word error rate by one third over a hidden Markov phonetic model.
Keywords :
Density functional theory; Dictionaries; Error analysis; Hidden Markov models; Iterative algorithms; Laboratories; Robustness; Speech recognition; Stochastic processes; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '87.
Type :
conf
DOI :
10.1109/ICASSP.1987.1169700
Filename :
1169700
Link To Document :
بازگشت