Extraction of Audio Features Specific to Speech Production for Multimodal Speaker Detection.
Patricia BessonVlad PopoviciJean-Marc VesinJean-Philippe ThiranMurat KuntPublished in: IEEE Trans. Multim. (2008)
Keyphrases
- audio visual
- audio features
- multi modal
- acoustic features
- speaker identification
- visual information
- speaker verification
- music recommendation
- music retrieval
- mel frequency cepstral coefficients
- speech recognition
- multimedia
- visual data
- audio stream
- image processing
- speaker recognition
- audio signal
- text data
- feature set
- low level
- data sets
- music information retrieval
- visual speech
- high level