Browsing by Author "Chen, Tzu-Hao"

Now showing 1 - 2 of 2

DEREVERBERATION BASED ON BIN-WISE TEMPORAL VARIATIONS OF COMPLEX SPECTROGRAM
(2017-01-01)
Chen, Tzu-Hao
;
Huang, Chun
;
Chi, Tai-Shih
;
電機工程學系
;
Department of Electrical and Computer Engineering
Humans analyze sounds not only based on their frequency contents, but also on the temporal variations of the frequency contents. Inspired by auditory perception, we propose a deep neural network (DNN) based dereverberation algorithm in the rate domain, which presents the temporal variations of frequency contents, in this paper. We show convolutional noise in the time domain can be approximated to multiplicative noise in the rate domain. To remove the multiplicative noise, we adopt the rate-domain complex-valued ideal ratio mask (RDcIRM) as the training target of the DNN. Simulation results show that the proposed rate-domain DNN algorithm is more capable of recovering high-intelligible and high-quality speech from reverberant speech than the compared state-ofthe- art dereverberation algorithm. Hence, it is highly suitable for speech applications involving human listeners.
Interaural Coherence Induced Ideal Binary Mask for Binaural Speech Separation and Dereverberation
(2016-01-01)
Chen, Yi-Ting
;
Chen, Tzu-Hao
;
Huang, Mao-Chang
;
Chi, Tai-Shih
;
電機工程學系
We have proposed a spatial-cue based binaural noise reduction algorithm for hearing aids. However, in that algorithm, decision parameters are empirically selected. In this paper, we extend the work and propose a supervised classification algorithm for binaural speech enhancement/separation and dereverberation using a modified ideal binary mask (mIBM) as the training target and simple neural networks (NNs) as classifiers. The low complexity of the simple NNs makes the proposed algorithm practical for binaural hearing aids. The interaural time difference (ITD) and the interaural level difference (ILD) of each T-F unit are extracted as the basic binaural features. For the purpose of dereverberation, the interaural coherence (IC) is also considered when building the target mIBM and training the NNs. For separation evaluations, our method yields comparable performance to a more complicated benchmark system, which cannot de-reverb the signal. For concurrent separation and dereverberation, our method offers 4 to 5 dB improvement on the frequencyweighted segmental speech-to-noise ratio (SNRfw) over unprocessed speech.