New bilingual speech databases for audio diarization.
David TavarezEva NavasDaniel ErroIbon SaratxagaInma HernáezPublished in: LREC (2014)
Keyphrases
- databases
- speaker identification
- audio stream
- speaker diarization
- broadcast news
- audio visual
- audio signals
- speech processing
- speech recognition
- speech signal
- text to speech
- language resources
- emotion recognition
- database
- cepstral features
- signal processing
- prosodic features
- acoustic signals
- digital audio
- knowledge discovery
- data model
- relational databases
- metadata
- multimedia information
- audio features
- gaussian mixture model
- speech synthesis
- noisy environments
- visual information
- multimedia
- speech music discrimination
- cross lingual
- data sources
- linear predictive coding