140 likes | 377 Views
Blind speech dereverberation using multiple microphones. Inseon JANG, Seungjin CHOI Intelligent Multimedia Lab Department of Computer Science and Engineering, POSTECH jinsn@postech.ac.kr Seungjin@postech.ac.kr. Outline. Introduction What is the Reverberant speech ?
E N D
Blind speech dereverberation using multiple microphones Inseon JANG, Seungjin CHOI Intelligent Multimedia Lab Department of Computer Science and Engineering, POSTECH jinsn@postech.ac.kr Seungjin@postech.ac.kr
Outline • Introduction • What is the Reverberant speech ? • Previous approaches for Speech dereverberation • Blind speech dereverberation using multiple microphones • Blind Equalization using multiple microphones – Single Input Multiple Output (SIMO) system • Subspace Method • Deterministic Method • Results
What is the Reverberant Speech ? • Reverberant speech cf) Noisy speech • The degrading component of the case of reverberation is dependent on previous speech data, whereas the degrading component of the case of noise speech is independent of speech.
Previous approaches for Speech dereverberation • Cepstrum based approach • Adaptive microphone array processing • Blind Deconvolution • Temporal envelope filtering • Multi-Microphone sub-band envelope estimation • Wavelet transform extrema clustering • Maximum-kurtosis subband adaptive filtering • Using LP Residual signal • Using Probabilistic Models
estimated signal source signal Impulse response received signal Inverse filter unknown Blind Equalization using multiple microphones – SIMO system (1/2)
Blind Equalization using multiple microphones – SIMO system (2/2) where is the filtering matrix • For virtual channel,
Subspace Method • By orthogonality between the noise and the signal subspace, the column of are orthogonal to any vector in the noise subspace for • Subspace-Based Parameter Estimation Scheme Minimization of the quadratic form
Deterministic Method (1/2) • Cross Relation Approach
Deterministic Method (2/2) • Channel estimate • Equivalently, the channel estimate can be obtained from the singular vector of associated with the smallest singular value
Result (2/3)Dereverberation using Subspace method • Channel length : 654 • Test size : 5000 • Result • MSE : 1.3608e-007
Result (3/3)Dereverberation using Deterministic method • Channel length : 654 • Test size : 1000 • Result • MSE : 7.7074e-018