Modeling speech and audio codecs reverberation artifact.
Yves ZangoRégine Le Bouquin-JeannèsCatherine QuinquisPublished in: EUSIPCO (2012)
Keyphrases
- audio visual
- audio stream
- broadcast news
- audio signals
- multimedia
- speech recognition
- emotion recognition
- cepstral features
- linear predictive coding
- low complexity
- speaker identification
- digital audio
- text to speech
- probabilistic model
- speech processing
- multi stream
- speech signal
- human computer interaction
- multi modal
- voice activity detection