A 8-32 KBIT/S Scalable Wideband Speech and Audio Coding Candidate for ITU-T G729EV Standardization.
Stéphane RagotBalázs KövesiDavid ViretteRomain TrillingDominique MassalouxPublished in: ICASSP (1) (2006)
Keyphrases
- speech signal
- speaker dependent
- speaker identification
- linear prediction
- audio stream
- audio visual
- speech recognition
- mel frequency cepstral coefficients
- linear predictive
- linear predictive coding
- audio signals
- broadcast news
- speech quality
- acoustic features
- coding scheme
- audio features
- automatic speech recognition
- noisy environments
- emotion recognition
- text to speech
- digital audio
- audio recordings
- speech music discrimination
- cepstral coefficients
- speaker recognition
- gaussian mixture model
- scalable video coding
- coding method
- cepstral features
- prosodic features
- multi stream
- speaker independent
- hidden markov models
- multimedia
- non stationary
- visual speech
- frequency band
- speech synthesis
- visual information
- spoken documents
- speech recognizer
- audio signal
- acoustic signals
- automatic transcription
- pattern recognition
- bitstream
- compression standards
- video signals
- spoken language
- speaker verification