DocumentCode
454583
Title
Isolated-Word Recognition with Penalized Logistic Regression Machines
Author
Birkenes, OYstein ; Matsui, Tomoko ; Tanabe, Kunio
Author_Institution
Inst. of Stat. Math., Tokyo
Volume
1
fYear
2006
fDate
14-19 May 2006
Abstract
We propose a new approach to isolated-word speech recognition based on penalized logistic regression machines (PLRMs). With this approach we combine the hidden Markov model (HMM) with multiclass logistic regression resulting in a powerful speech recognizer which provides us with the posterior probability for each word. Experiments on the English E-set show significant improvements compared to conventional HMM-based speech recognition
Keywords
hidden Markov models; regression analysis; speech recognition; English E-set; HMM-based speech recognition; hidden Markov model; isolated-word speech recognition; multiclass logistic regression; penalized logistic regression machines; posterior probability; Cepstral analysis; Error analysis; Hidden Markov models; Logistics; Mathematics; Maximum likelihood estimation; Predictive models; Probability distribution; Speech recognition; Vocabulary;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location
Toulouse
ISSN
1520-6149
Print_ISBN
1-4244-0469-X
Type
conf
DOI
10.1109/ICASSP.2006.1660043
Filename
1660043
Link To Document