Overlapping speech detection using long-term conversational features for speaker diarization in meeting room conversations.
Sree Harsha YellaHervé BourlardPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2014)
Keyphrases
- speaker diarization
- meeting room
- speech recognition
- conversational speech
- audio visual
- low level
- feature set
- feature extraction
- multi modal
- feature vectors
- speaker identification
- audio stream
- natural language processing
- hidden markov models
- speech signal
- automatic speech recognition
- broadcast news
- video sequences
- computer vision