D
DeLiang Wang
Researcher at Ohio State University
Publications - 475
Citations - 28623
DeLiang Wang is an academic researcher from Ohio State University. The author has contributed to research in topics: Speech processing & Speech enhancement. The author has an hindex of 82, co-authored 440 publications receiving 23687 citations. Previous affiliations of DeLiang Wang include Massachusetts Institute of Technology & Tsinghua University.
Papers
More filters
Proceedings ArticleDOI
Complex Ratio Masking For Singing Voice Separation
TL;DR: In this article, a complex ratio masking method was proposed for singing voice separation, which employs DenseUNet with self attention to estimate the real and imaginary components of STFT for each sound source.
Proceedings Article
Acoustic Features for Classification Based Speech Separation.
Yuxuan Wang,Kun Han,DeLiang Wang +2 more
TL;DR: Other acoustic features are studied and it is shown that they can improve both voiced and unvoiced speech separation performance and a group Lasso approach for feature combination is proposed.
Journal ArticleDOI
Modeling neural mechanisms of vertebrate habituation: locus specificity and pattern discrimination.
TL;DR: A neural mechanism is proposed whereby neural circuitry for pattern discrimination is shared by a spatial memory system, and such learning processes are argued to occur in the medial pallium, the anuran's homolog of mammalian hippocampus.
Proceedings ArticleDOI
Robust speech recognition by integrating speech separation and hypothesis testing
TL;DR: This work proposes a two stage recognition system for speech separation mask estimation that shows significant improvement in recognition performance compared to that using speech separation.
Proceedings ArticleDOI
Locally excitatory globally inhibitory oscillator networks: theory and application to pattern segmentation
DeLiang Wang,David Terman +1 more
TL;DR: This model lays a physical foundation for the oscillatory correlation theory of feature binding, and may provide an effective computational framework for pattern segmentation and figure/ground segregation.