A Joint Approach for Single-Channel Speaker Identification and Speech Separation.
Pejman MowlaeeRahim SaeidiMads Græsbøll ChristensenZheng-Hua TanTomi KinnunenPasi FräntiSøren Holdt JensenPublished in: IEEE Trans. Speech Audio Process. (2012)
Keyphrases
- speaker identification
- single channel
- speech signal
- sound source
- speech enhancement
- noisy environments
- speech recognition
- multi channel
- audio features
- speaker recognition
- automatic speech recognition
- broadcast news
- gaussian mixture model
- vocal tract
- non stationary
- feature extraction
- hidden markov models
- independent component analysis
- brain activity
- noise reduction
- prior information
- frequency domain
- high level
- super resolution
- pattern recognition
- wiener filter
- neural network
- multiscale