Spatial and coherence cues based time-frequency masking for binaural reverberant speech separation.
Atiyeh AlinaghiWenwu WangPhilip J. B. JacksonPublished in: ICASSP (2013)
Keyphrases
- speech signal
- sound source
- speech recognition
- automatic speech recognition
- spatial information
- spatial and temporal
- spatio temporal
- noisy environments
- space time
- motion cues
- hidden markov models
- non stationary
- frequency domain
- speaker identification
- signal processing
- visual cues
- prosodic features
- fourier transform
- speech synthesis
- transfer function
- audio visual
- spatial databases
- multiscale
- video frames
- spatial data
- pattern recognition