Large margin training of semi-Markov model for phonetic recognition

  • Sungwoong Kim*
  • , Sungrack Yun
  • , Chang D. Yoo
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper considers a large margin training of semi-Markov model (SMM) for phonetic recognition. The SMM framework is better suited for phonetic recognition than the hidden Markov model (HMM) framework in that the SMM framework is capable of simultaneously segmenting the uttered speech into phones and labeling the segment-based features. In this paper, the SMM framework is used to define a discriminant function that is linear in the joint feature map which attempts to capture the long-range statistical dependencies within a segment and between adjacent segments of variable length. The parameters of the discriminant function are estimated by a large margin learning criterion for structured prediction. The parameter estimation problem, which is an optimization problem with many margin constraints, is solved by using a stochastic subgradient descent algorithm. The proposed large margin SMM outperforms the large margin HMM on the TIMIT corpus.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1910-1913
Number of pages4
ISBN (Print)9781424442966
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Dallas, TX, United States
Duration: 2010 Mar 142010 Mar 19

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Other

Other2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
Country/TerritoryUnited States
CityDallas, TX
Period10/3/1410/3/19

Keywords

  • Hidden markov model
  • Phonetic recognition
  • Semi-Markov model
  • Structured support vector machine

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Large margin training of semi-Markov model for phonetic recognition'. Together they form a unique fingerprint.

Cite this