Z
Zhong-Qiu Wang
Researcher at Ohio State University
Publications - 48
Citations - 2349
Zhong-Qiu Wang is an academic researcher from Ohio State University. The author has contributed to research in topics: Speech enhancement & Beamforming. The author has an hindex of 23, co-authored 48 publications receiving 1548 citations. Previous affiliations of Zhong-Qiu Wang include Google & Mitsubishi Electric Research Laboratories.
Papers
More filters
Proceedings ArticleDOI
Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation
TL;DR: It is found that simply encoding inter-microphone phase patterns as additional input features during deep clustering provides a significant improvement in separation performance, even with random microphone array geometry.
Proceedings ArticleDOI
Alternative Objective Functions for Deep Clustering
TL;DR: The best proposed method achieves a state-of-the-art 11.5 dB signal-to-distortion ratio result on the publicly available wsj0-2mix dataset, with a much simpler architecture than the previous best approach.
Proceedings ArticleDOI
End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction
TL;DR: In this paper, the authors proposed an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within a deep network.
Journal ArticleDOI
Complex Spectral Mapping for Single- and Multi-Channel Speech Enhancement and Robust ASR
TL;DR: A novel method of time-varying beamforming with estimated complex spectra for single- and multi-channel speech enhancement, where deep neural networks are used to predict the real and imaginary components of the direct-path signal from noisy and reverberant ones.
Journal ArticleDOI
A joint training framework for robust automatic speech recognition
Zhong-Qiu Wang,DeLiang Wang +1 more
TL;DR: A novel joint training framework for speech separation and recognition to concatenate a deep neural network based speech separation frontend and a DNN-based acoustic model to build a larger neural network, and jointly adjust the weights in each module.