Diphone subspace mixture trajectory models for HMM complementation

DOI10.1016/S0167-6393(01)00054-1MaRDI QIDQ4794858zbMATH OpenOpenAlexFDO

Authors

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)00054-1

zbMATH Keywords

\(N\)-best rescoringdiphonesPCAspeech dynamicssubspace trajectorytime-constraint

Mathematics Subject Classification ID

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

Recommendations

• Segmental acoustic modeling for speech recognition
• Improving phoneme classification performance using observation context-dependent segment models
• scientific article; zbMATH DE number 4082696
• Trajectory representations and acoustic descriptions for segment-modelling approach to automatic speech recognition
• A segmental-feature HMM for continuous speech recognition based on a parametric trajectory model

This page was built for publication: Diphone subspace mixture trajectory models for HMM complementation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4794858)