A preliminary examination technique for audio evidence to distinguish speech from non-speech using objective speech quality measures.
Erkam UzunHusrev T. SencarPublished in: Speech Commun. (2014)
Keyphrases
- speech recognition
- audio stream
- audio visual
- text to speech
- quality measures
- broadcast news
- speech signal
- speaker identification
- linear predictive coding
- automatic speech recognition
- emotion recognition
- speech processing
- speech synthesis
- cepstral features
- automatic transcription
- audio features
- query processing
- multi stream
- prosodic features
- acoustic signals
- emotional state
- similarity measure