40 citations · 128 across the 28 of their papers we have counts for
8 papers · 1 filter
Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning
Cunhang Fan, Bin Liu, Jianhua Tao +3
Recurrent neural networks (RNNs) have shown significant improvements in recent years for speech enhancement. However, the model complexity and inference time cost of RNNs are much…
Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition
Cunhang Fan, Jiangyan Yi, Jianhua Tao +3
The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However,…
Dynamic Attention Based Generative Adversarial Network with Phase Post-Processing for Speech Enhancement
Andong Li, Chengshi Zheng, Renhua Peng +2
The generative adversarial networks (GANs) have facilitated the development of speech enhancement recently. Nevertheless, the performance advantage is still limited when compared w…
Simultaneous Denoising and Dereverberation Using Deep Embedding Features
Cunhang Fan, Jianhua Tao, Bin Liu +2
Monaural speech dereverberation is a very challenging task because no spatial cues can be used. When the additive noises exist, this task becomes more challenging. In this paper, w…
Adversarial Transfer Learning for Punctuation Restoration
Jiangyan Yi, Jianhua Tao, Ye Bai +2
Previous studies demonstrate that word embeddings and part-of-speech (POS) tags are helpful for punctuation restoration tasks. However, two drawbacks still exist. One is that word…
A Recursive Network with Dynamic Attention for Monaural Speech Enhancement
Andong Li, Chengshi Zheng, Cunhang Fan +2
A person tends to generate dynamic attention towards speech under complicated environments. Based on this phenomenon, we propose a framework combining dynamic attention and recursi…
Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method
Cunhang Fan, Jianhua Tao, Bin Liu +3
In this paper, we propose an end-to-end post-filter method with deep attention fusion features for monaural speaker-independent speech separation. At first, a time-frequency domain…
Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features
Cunhang Fan, Bin Liu, Jianhua Tao +2
Multi-channel deep clustering (MDC) has acquired a good performance for speech separation. However, MDC only applies the spatial features as the additional information. So it is di…