Combining missing-feature theory, speech enhancement, and speaker-dependent/-independent modeling for speech separation.
Ji MingTimothy J. HazenJames R. GlassPublished in: Comput. Speech Lang. (2010)
Keyphrases
- speech enhancement
- speaker dependent
- speech recognition
- speech signal
- speaker identification
- noisy environments
- phoneme recognition
- noisy speech
- noise reduction
- vocal tract
- signal to noise ratio
- speech synthesis
- speaker independent
- single channel
- hidden markov models
- background noise
- speech recognizer
- linear prediction
- speaker verification
- gaussian mixture model
- language model
- pattern recognition
- image processing
- automatic speech recognition
- multi channel
- multiscale