DocumentCode :
1908495
Title :
A variable duration acoustic segment HMM for hard-to-recognize words and phrases
Author :
Marcus, Jeffrey N. ; Zue, Victor W.
Author_Institution :
Lab. for Comput. Sci., MIT, Cambridge, MA, USA
fYear :
1991
fDate :
14-17 Apr 1991
Firstpage :
281
Abstract :
The authors consider how hidden Markov models (HMM) can be modified to accommodate a segment-based representation, and how word and subword models can be combined to improve recognition performance. The investigation is conducted within the context of a system that attempts to spot confusable words and phrases in the VOYAGER continuous speech corpus. Specifically, the authors describe how segments of varying duration are determined such that measurements for estimating the model parameters can be made on these segments. The word-spotting system is also described in detail
Keywords :
Markov processes; speech recognition; HMM; VOYAGER continuous speech corpus; confusable phrases; confusable words; hard-to-recognise phrases; hard-to-recognize words; hidden Markov models; parameter estimation; segment-based representation; speech recognition; variable duration acoustic segment; word-spotting system; Acoustic measurements; Computer science; Context modeling; Density measurement; Hidden Markov models; Laboratories; Loudspeakers; Natural languages; Power system modeling; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
ISSN :
1520-6149
Print_ISBN :
0-7803-0003-3
Type :
conf
DOI :
10.1109/ICASSP.1991.150332
Filename :
150332
Link To Document :
بازگشت