Combined discriminative training for multi-stream HMM-based audio-visual speech recognition

Jing Huang; Karthik Visweswariah

doi:10.21437/interspeech.2009-426

ScienceGate Book Chapters

JOURNAL ARTICLE

Combined discriminative training for multi-stream HMM-based audio-visual speech recognition

Jing Huang Karthik Visweswariah

Year: 2009 Pages: 1379-1382

DOI: 10.21437/interspeech.2009-426

Get Full-Text PDF Get Analytical Report

Keywords:

Hidden Markov model Discriminative model Computer science Speech recognition Training (meteorology) Artificial intelligence Pattern recognition (psychology)

Metrics

Cited By

0.35

FWCI (Field Weighted Citation Impact)

Refs

0.57

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Speech and Audio Processing

Physical Sciences → Computer Science → Signal Processing

Combined discriminative training for multi-stream HMM-based audio-visual speech recognition

Metrics

Citation History

Topics

Related Documents

Discriminative training of HMM stream exponents for audio-visual speech recognition

Discriminative stream‐weight training for mandarin audio‐visual speech recognition

Efficient likelihood computation in multi-stream HMM based audio-visual speech recognition

Improved decision trees for multi-stream HMM-based audio-visual continuous speech recognition

Fused HMM-adaptation of multi-stream HMMs for audio-visual speech recognition