Postfiltering Using Log-Magnitude Spectrum for Speech and Audio Coding.
Sneha DasTom BäckströmPublished in: INTERSPEECH (2018)
Keyphrases
- audio stream
- audio visual
- broadcast news
- linear predictive coding
- audio signals
- speaker identification
- linear predictive
- cepstral features
- emotion recognition
- linear prediction
- text to speech
- speech recognition
- digital audio
- speech processing
- speech music discrimination
- audio recordings
- speech signal
- prosodic features
- audio features
- speech synthesis
- automatic transcription
- multimedia
- acoustic features
- multi modal
- visual information
- automatic speech recognition
- acoustic signals
- coding scheme
- spoken documents
- multi stream
- audio video
- signal processing
- mel frequency cepstral coefficients
- multimodal interfaces
- spoken language
- coding method
- visual speech
- video signals
- speaker recognition
- digital video