Universal speech/audio coding using hybrid ACELP/TCX techniques.
Bruno BessetteRoch LefebvreRedwan SalamiPublished in: ICASSP (3) (2005)
Keyphrases
- audio visual
- audio stream
- broadcast news
- linear predictive coding
- speaker identification
- emotion recognition
- audio signals
- cepstral features
- coding scheme
- linear prediction
- text to speech
- linear predictive
- speech recognition
- speech music discrimination
- multimedia
- speech synthesis
- audio video
- audio recordings
- digital audio
- multi modal
- audio features
- prosodic features
- signal processing
- visual information
- speech signal
- speech processing
- spoken language
- acoustic signals
- automatic transcription
- spontaneous speech
- multimodal interfaces
- coding method
- spoken documents
- acoustic features
- speaker recognition