May speech modifications in noise contribute to enhance audio-visible cues to segment perception?
Maeva GarnierPublished in: AVSP (2008)
Keyphrases
- prosodic features
- audio visual
- audio stream
- noisy environments
- speech synthesis
- broadcast news
- text to speech
- speaker identification
- digital audio
- audio signals
- speaker verification
- speech segments
- cepstral features
- missing data
- multimodal fusion
- speech recognition
- noise reduction
- automatic transcription
- audio recordings
- audio features
- spoken documents
- audio video
- speech enhancement
- linear predictive coding
- multi modal
- random noise
- emotion recognition
- speech processing
- noise level
- acoustic signals
- multimedia
- signal to noise ratio
- noisy data
- visual information
- signal processing
- speech signal
- speaker diarization
- speech music discrimination
- content based video retrieval
- human language
- spoken document retrieval
- multimodal interfaces
- speaker recognition
- cross modal
- automatic speech recognition
- video streams
- human computer interaction