Combining eigenvoice speaker modeling and VTS-based environment compensation for robust speech recognition.
Zhijian OuKan DengPublished in: ICASSP (2012)
Keyphrases
- speech recognition
- noisy environments
- speaker identification
- hidden markov models
- automatic speech recognition
- language model
- speaker verification
- speech recognizer
- speech synthesis
- speech processing
- pattern recognition
- speech signal
- speaker dependent
- speech understanding
- speaker diarization
- digit recognition
- speaker independent
- speech recognition technology
- speech enhancement
- keyword spotting
- speech retrieval
- speech recognizers
- speaker recognition
- speech recognition errors
- cepstral coefficients
- acoustic models
- machine learning
- speaker adaptation
- background noise