Generating Expressive Summaries for Speech and Musical Audio using Self-Similarity Clues.
Mustafa SertBuyurman BaykalAdnan YaziciPublished in: ICME (2006)
Keyphrases
- audio recordings
- audio stream
- acoustic features
- audio visual
- audio signal
- music information retrieval
- audio signals
- audio features
- speaker identification
- automatic music genre classification
- broadcast news
- text to speech
- digital audio
- music genre classification
- emotion recognition
- cepstral features
- speech recognition
- speech signal
- music retrieval
- genre classification
- prosodic features
- audio video
- visual information
- speech processing
- spoken documents
- multimedia
- natural images
- polyphonic music
- visual data
- automatic speech recognition
- speech music discrimination
- multi modal
- acoustic signals
- linear predictive coding
- human language
- speaker verification
- visual features
- speech synthesis
- video streams
- fractal dimension
- signal processing