Construction of state-dependent dynamic parameters using the maximum likelihood approach: Applications to speech recognition

DOI10.1016/S0165-1684(96)00127-2MaRDI QIDQ673356zbMATH OpenFDO

Authors Juan-Miguel Gracia

Publication date 28 February 1997

Published in Signal Processing (Search for Journal in Brave)

zbMATH Keywords

EM algorithmDelta-cepstrumHidden Markov modelLinear and nonlinear systemsSpeech signal

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Recommendations

• scientific article; zbMATH DE number 1767710
• State-dependent time warping in the trended hidden Markov model
• State duration modelling in hidden Markov models
• scientific article; zbMATH DE number 1099040

Cited in

(8)

• scientific article; zbMATH DE number 1414411 (Why is no real title available?)
• Embedded mobile phone digit-recognition
• Developments of machine learning schemes for dynamic time-wrapping-based speech recognition
• Use of voicing features in HMM-based speech recognition
• State-dependent time warping in the trended hidden Markov model
• Time and frequency filtering of filter-bank energies for robust HMM speech recognition
• scientific article; zbMATH DE number 1414413 (Why is no real title available?)
• The use of adaptive frame for speech recognition

This page was built for publication: Construction of state-dependent dynamic parameters using the maximum likelihood approach: Applications to speech recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q673356)