Speech recognition in a reverberant environment using matched filter array (MFA) processing and linguistic-tree maximum likelihood linear regression (LT-MLLR) adaptation.
Prabhu RaghavanRichard J. RenomeronChiWei CheDong-Suk YukJames L. FlanaganPublished in: ICASSP (1999)
Keyphrases
- speaker adaptation
- speech recognition
- linear regression
- speech signal
- maximum likelihood
- matched filter
- noisy environments
- least squares
- automatic speech recognition
- speaker independent
- speech recognizer
- hidden markov models
- language model
- speech synthesis
- pattern recognition
- signal to noise ratio
- video sequences
- speech recognition systems
- speaker identification
- vocal tract
- feature selection
- target detection
- computer vision
- wavelet transform