Rethinking derived acoustic features in speech recognition.
Kevin S. Van HornPublished in: INTERSPEECH (2002)
Keyphrases
- speech recognition
- acoustic features
- speech signal
- automatic speech recognition
- hidden markov models
- language model
- speaker identification
- pattern recognition
- mel frequency cepstral coefficients
- noisy environments
- speaker recognition
- training data
- speech recognition systems
- speaker verification
- cepstral coefficients
- information retrieval
- high dimensional
- image processing