Acoustic vector sensor based reverberant speech separation with probabilistic time-frequency masking.
Xionghu ZhongXiaoyi ChenWenwu WangAtiyeh AlinaghiA. Benjamin PremkumarPublished in: EUSIPCO (2013)
Keyphrases
- speech signal
- sound source
- acoustic features
- speech recognition
- speech sounds
- source localization
- vocal tract
- speech recognition systems
- automatic speech recognition
- noisy speech
- formant frequencies
- noisy environments
- discrete valued
- speaker identification
- bayesian networks
- speech recognizers
- non stationary
- probabilistic model
- hidden markov models
- pattern recognition
- mel frequency cepstral coefficients
- speaker independent
- uncertain data
- audio features
- generative model
- speech enhancement
- emotional speech
- vowel phonemes
- bird species
- spoken language
- blind source separation
- vector space
- frequency domain
- signal processing
- multiscale