XMLLR for improved speaker adaptation in speech recognition.
Daniel PoveyHong-Kwang Jeff KuoPublished in: INTERSPEECH (2008)
Keyphrases
- speech recognition
- speaker adaptation
- speaker independent
- speaker dependent
- automatic speech recognition
- hidden markov models
- speech recognizer
- language model
- speech synthesis
- speech signal
- pattern recognition
- noisy environments
- maximum likelihood
- speaker identification
- multi modal
- speaker diarization
- speech recognition systems