Exploiting the intermittency of speech for joint separation and diarization.
Dionyssos Kounades-BastianLaurent GirinXavier Alameda-PinedaRadu HoraudSharon GannotPublished in: WASPAA (2017)
Keyphrases
- speaker identification
- speaker diarization
- speech recognition
- audio visual
- speech signal
- spoken language
- speech recognizer
- broadcast news
- speaker recognition
- pattern recognition
- multi stream
- recognition engine
- automatic speech recognition
- speech processing
- text to speech
- spontaneous speech
- automatic speech recognition systems
- hearing impaired
- artificial intelligence
- joint estimation
- multi lingual
- noisy environments
- gaussian mixture model
- hidden markov models
- information systems