Video assisted speech source separation.
Wenwu WangDarren CoskerYulia HicksSaeid SaneiJonathon A. ChambersPublished in: ICASSP (5) (2005)
Keyphrases
- source separation
- audio features
- temporal structure
- audio visual
- low level
- blind source separation
- video data
- feature set
- video sequences
- speaker identification
- visual features
- video streams
- video content
- independent component analysis
- broadcast news
- multimedia
- music information retrieval
- video clips
- text data
- speech recognition
- speech signal
- audio signal
- multimedia data
- denoising
- feature vectors
- music retrieval
- video retrieval
- single channel
- spatio temporal
- face recognition