Discriminative training of auditory filters of different shapes for robust speech recognition.
Brian MakYik-Cheung TamRoger HsiaoPublished in: ICASSP (2) (2003)
Keyphrases
- speech recognition
- discriminative training
- automatic speech recognition
- hidden markov models
- noisy environments
- acoustic models
- speech synthesis
- speech signal
- speech recognizer
- language model
- speaker identification
- signal processing
- speech recognition technology
- probabilistic interpretation
- pattern recognition
- training data
- speech recognition systems
- feature extraction
- support vector machine
- image processing