DocumentCode
417135
Title
Combination of hidden Markov models with dynamic time warping for speech recognition
Author
Axelrod, Scott ; Maison, Beno It
Author_Institution
IBM T. J. Watson Res. Center, Yorktown Heights, NY, USA
Volume
1
fYear
2004
fDate
17-21 May 2004
Abstract
We combine hidden Markov models of various topologies and nearest neighbor classification techniques in an exponential modeling framework with a model selection algorithm to obtain significant error rate reductions on an isolated word digit recognition task. This work is a preliminary investigation of large scale modeling techniques to be applied to large vocabulary continuous speech recognition.
Keywords
hidden Markov models; pattern classification; speech recognition; dynamic time warping; error rate reductions; exponential modeling framework; hidden Markov models; isolated word digit recognition task; large scale modeling; large vocabulary continuous speech recognition; model selection algorithm; nearest neighbor classification; Automatic speech recognition; Data mining; Error analysis; Hidden Markov models; Power system modeling; Speech recognition; Testing; Topology; Training data; Vocabulary;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
ISSN
1520-6149
Print_ISBN
0-7803-8484-9
Type
conf
DOI
10.1109/ICASSP.2004.1325950
Filename
1325950
Link To Document