58 citations · 335 across the 31 of their papers we have counts for
8 papers · 1 filter
Efficient End-to-End Speech Recognition Using Performers in Conformers
Peidong Wang, DeLiang Wang
On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the comp…
Complex ratio masking for singing voice separation
Yixuan Zhang, Yuzhou Liu, DeLiang Wang
Music source separation is important for applications such as karaoke and remixing. Much of previous research focuses on estimating short-time Fourier transform (STFT) magnitude an…
Speaker Separation Using Speaker Inventories and Estimated Speech
Peidong Wang, Zhuo Chen, DeLiang Wang +2
We propose speaker separation using speaker inventories and estimated speech (SSUSIES), a framework leveraging speaker profiles and estimated speech for speaker separation. SSUSIES…
Dual-path Self-Attention RNN for Real-Time Speech Enhancement
Ashutosh Pandey, DeLiang Wang
We propose a dual-path self-attention recurrent neural network (DP-SARNN) for time-domain speech enhancement. We improve dual-path RNN (DP-RNN) by augmenting inter-chunk and intra-…
Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation
Zhong-Qiu Wang, Peidong Wang, DeLiang Wang
We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditio…
Dense CNN with Self-Attention for Time-Domain Speech Enhancement
Ashutosh Pandey, DeLiang Wang
Speech enhancement in the time domain is becoming increasingly popular in recent years, due to its capability to jointly enhance both the magnitude and the phase of speech. In this…
Multi-Microphone Complex Spectral Mapping for Speech Dereverberation
Zhong-Qiu Wang, DeLiang Wang
This study proposes a multi-microphone complex spectral mapping approach for speech dereverberation on a fixed array geometry. In the proposed approach, a deep neural network (DNN)…
On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement
Ashutosh Pandey, DeLiang Wang
In recent years, supervised approaches using deep neural networks (DNNs) have become the mainstream for speech enhancement. It has been established that DNNs generalize well to unt…