65 citations · 102 across the 8 of their papers we have counts for
8 papers
TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio
Anurag Kumar, Ke Tan, Zhaoheng Ni +4
Measuring quality and intelligibility of a speech signal is usually a critical step in development of speech processing systems. To enable this, a variety of metrics to measure qua…
Rethinking complex-valued deep neural networks for monaural speech enhancement
Haibin Wu, Ke Tan, Buye Xu +2
Despite multiple efforts made towards adopting complex-valued deep neural networks (DNNs), it remains an open question whether complex-valued DNNs are generally more effective than…
Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement
Kuan-Lin Chen, Daniel D. E. Wong, Ke Tan +3
Most speech enhancement (SE) models learn a point estimate and do not make use of uncertainty estimation in the learning process. In this paper, we show that modeling heteroscedast…
Location-based training for multi-channel talker-independent speaker separation
Hassan Taherian, Ke Tan, DeLiang Wang
Permutation-invariant training (PIT) is a dominant approach for addressing the permutation ambiguity problem in talker-independent speaker separation. Leveraging spatial informatio…
SAGRNN: Self-Attentive Gated RNN for Binaural Speaker Separation with Interaural Cue Preservation
Ke Tan, Buye Xu, Anurag Kumar +2
Most existing deep learning based binaural speaker separation systems focus on producing a monaural estimate for each of the target speakers, and thus do not preserve the interaura…
Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network
Ke Tan, Yong Xu, Shi-Xiong Zhang +2
Background noise, interfering speech and room reverberation frequently distort target speech in real listening environments. In this study, we address joint speech separation and d…
Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling
Peidong Wang, Ke Tan, DeLiang Wang
Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intell…
Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective
Zhong-Qiu Wang, Ke Tan, DeLiang Wang
This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain. The key obser…