Discriminative feature weighting for HMM-based continuous speech recognizers

DOI10.1016/S0167-6393(01)00068-1MaRDI QIDQ4794863zbMATH OpenFDO

Authors Ángel de la Torre, Antonio Peinado, Antonio J. Rubio, José C. Segura, Carmen Benítez

Publication date 20 February 2003

Published in Speech Communication (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0167-6393(01)00068-1

zbMATH Keywords

continuous speech recognitioncost functiondiscriminative feature extractiondiscriminative feature weightingdiscriminative weighting by transformationerror-ratehidden Markov modelminimum classification errorpartial probability weightingprobability density function

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Recommendations

• scientific article; zbMATH DE number 1414401
• A variable weighting based training data selection method for discriminative training of acoustic models
• scientific article; zbMATH DE number 6401111
• Component-based discriminative classification for hidden Markov models
• A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction

Cited in

(4)

• An improved method for voice pathology detection by means of a HMM-based feature space transformation
• scientific article; zbMATH DE number 5630369 (Why is no real title available?)
• scientific article; zbMATH DE number 1414401 (Why is no real title available?)
• A variable weighting based training data selection method for discriminative training of acoustic models

This page was built for publication: Discriminative feature weighting for HMM-based continuous speech recognizers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4794863)