Joint single-channel speech separation and speaker identification.
Pejman MowlaeeRahim SaeidiZheng-Hua TanMads Græsbøll ChristensenPasi FräntiSøren Holdt JensenPublished in: ICASSP (2010)
Keyphrases
- speaker identification
- single channel
- speech signal
- sound source
- speech enhancement
- speech recognition
- noisy environments
- audio features
- speaker recognition
- multi channel
- automatic speech recognition
- gaussian mixture model
- vocal tract
- broadcast news
- hidden markov models
- non stationary
- machine learning
- brain activity
- feature extraction
- image processing
- language model
- video sequences
- vision system
- low level