Reverberant speech separation with probabilistic time-frequency masking for B-format recordings.
Xiaoyi ChenWenwu WangYingmin WangXionghu ZhongAtiyeh AlinaghiPublished in: Speech Commun. (2015)
Keyphrases
- speech signal
- spontaneous speech
- audio visual
- speech recognition
- acoustic features
- audio recordings
- bayesian networks
- generative model
- probabilistic model
- multi modal
- metadata
- automatic speech recognition
- databases
- multiscale
- probabilistic logic
- uncertain data
- signal processing
- speech synthesis
- dialogue system
- pattern recognition
- wavelet transform
- noisy environments
- conditional probabilities
- sound source
- audio features
- speaker identification
- human machine interaction
- text to speech
- human visual system
- fourier transform
- multimedia
- non stationary