Candidate proposal for ITU-T super-wideband speech and audio coding.
Bernd GeiserHauke KrügerHeinrich W. LöllmannPeter VaryDeming ZhangHualin WanHai Ting LiLi Bin ZhangPublished in: ICASSP (2009)
Keyphrases
- speech signal
- audio visual
- audio stream
- linear prediction
- speaker identification
- linear predictive
- speech recognition
- linear predictive coding
- cepstral coefficients
- broadcast news
- audio signals
- speech quality
- audio features
- acoustic features
- text to speech
- speech processing
- automatic speech recognition
- cepstral features
- emotion recognition
- audio recordings
- coding scheme
- mel frequency cepstral coefficients
- prosodic features
- digital audio
- multi modal
- video signals
- noisy environments
- automatic transcription
- multimedia
- spoken documents
- speech synthesis
- visual information
- signal processing
- multi stream
- acoustic signals
- coding method
- speech music discrimination
- speaker recognition
- audio video
- non stationary
- hidden markov models
- compression standards
- visual features
- spontaneous speech
- speaker verification
- sound source
- visual data
- signal to noise ratio