SCAN - speech content based audio navigator: a system overview.
John ChoiDonald HindleJulia HirschbergIvan Magrin-ChagnolleauChristine H. NakataniFernando C. N. PereiraAmit SinghalSteve WhittakerPublished in: ICSLP (1998)
Keyphrases
- audio stream
- audio visual
- multimedia
- broadcast news
- audio signals
- speaker identification
- cepstral features
- emotion recognition
- audio features
- digital audio
- text to speech
- image retrieval
- music genre classification
- speech recognition
- speech music discrimination
- speech processing
- video search
- prosodic features
- audio recordings
- acoustic signals
- linear predictive coding
- acoustic features
- signal processing
- automatic transcription
- video content analysis
- audio content
- audio video
- visual information
- speech synthesis
- multi modal
- human language
- video indexing and retrieval
- multi stream
- video streams
- visual data
- audio signal
- automatic speech recognition
- content based video retrieval
- voice activity detection
- speaker diarization
- spoken documents
- mel frequency cepstral coefficients
- relevance feedback
- noisy environments
- speaker recognition
- speech corpus
- gaussian mixture model
- metadata