A new time-frequency approach for underdetermined convolutive blind speech separation.
Mariem BouafifZied LachiriPublished in: ICASSP (2016)
Keyphrases
- human computer interaction
- emotion recognition
- speech recognition
- source signals
- speech signal
- signal processing
- speech synthesis
- text to speech
- wavelet transform
- frequency domain
- multiresolution
- automatic speech recognition
- vocal tract
- blind separation
- broadcast news
- audio visual
- independent component analysis
- dialogue system
- spoken language
- spoken dialogue systems
- multi modal
- probabilistic model
- motion deblurring
- neural network
- data sets