Two-Microphone Separation of Speech Mixtures.
Michael Syskind PedersenDeLiang WangJan LarsenUlrik KjemsPublished in: IEEE Trans. Neural Networks (2008)
Keyphrases
- automatic speech recognition
- sound source
- speech signal
- speech recognition
- blind source separation
- blind separation
- speaker diarization
- audio visual
- source signals
- source separation
- audio features
- hidden markov models
- speech synthesis
- mixture model
- recognition engine
- mixtures of gaussians
- noisy environments
- gaussian mixture
- emotion recognition
- broadcast news
- speaker identification
- speaker recognition
- endpoint detection
- neural network
- vocal tract
- factor analyzers
- multi stream
- speech processing
- text to speech
- spoken language
- language acquisition
- human computer interaction
- em algorithm
- pattern recognition
- image segmentation