Separation of speech from interfering sounds based on oscillatory correlation.
DeLiang L. WangGuy J. BrownPublished in: IEEE Trans. Neural Networks (1999)
Keyphrases
- sound source
- acoustic features
- speech signal
- speech recognition
- spectral features
- audio visual
- correlation coefficient
- hidden markov models
- recurrent neural networks
- audio features
- recognition engine
- speech synthesis
- speaker verification
- spoken language
- noisy environments
- man made
- cross correlation
- linear prediction
- feature extraction
- emotion recognition
- text to speech
- single channel
- english text
- automatic speech recognition
- speaker diarization
- vocal tract
- visual speech
- probabilistic model
- environmental sounds
- audio stream