Deep NMF for speech separation.
Jonathan Le RouxJohn R. HersheyFelix WeningerPublished in: ICASSP (2015)
Keyphrases
- negative matrix factorization
- nonnegative matrix factorization
- speech recognition
- speech signal
- speech synthesis
- document clustering
- audio visual
- automatic speech recognition
- endpoint detection
- text to speech
- speaker recognition
- audio stream
- matrix factorization
- matrix factorisation
- spontaneous speech
- hearing impaired
- noisy environments
- frequent sets
- spoken dialogue systems
- emotion recognition
- data mining
- least squares
- feature selection