Combining missing-feature theory, speech enhancement and speaker-dependent/-independent modeling for speech separation.
Ji MingTimothy J. HazenJames R. GlassPublished in: INTERSPEECH (2006)
Keyphrases
- speech enhancement
- speaker dependent
- speech signal
- speaker identification
- speech recognition
- noisy environments
- noise reduction
- noisy speech
- phoneme recognition
- signal to noise ratio
- single channel
- vocal tract
- hidden markov models
- speaker independent
- linear prediction
- speech recognizer
- background noise
- smoothing algorithm
- automatic speech recognition
- feature vectors
- wiener filter
- neural network
- sound source
- information retrieval
- speech synthesis
- speaker recognition
- digit recognition
- speaker verification
- pattern recognition
- image processing