40 citations · 191 across the 46 of their papers we have counts for
12 papers · 1 filter
EmotionBox: a music-element-driven emotional music generation system using Recurrent Neural Network
Kaitong Zheng, Ruijie Meng, Chengshi Zheng +4
With the development of deep neural networks, automatic music composition has made great progress. Although emotional music can evoke listeners' different emotions and it is import…
Noise-robust blind reverberation time estimation using noise-aware time-frequency masking
Kaitong Zheng, Chengshi Zheng, Jinqiu Sang +2
The reverberation time is one of the most important parameters used to characterize the acoustic property of an enclosure. In real-world scenarios, it is much more convenient to es…
Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement
Guochen Yu, Andong Li, Chengshi Zheng +3
Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performa…
A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement
Guochen Yu, Yutian Wang, Hui Wang +2
Cycle-consistent generative adversarial networks (CycleGAN) have shown their promising performance for speech enhancement (SE), while one intractable shortcoming of these CycleGAN-…
Embedding and Beamforming: All-neural Causal Beamformer for Multichannel Speech Enhancement
Andong Li, Wenzhe Liu, Chengshi Zheng +1
The spatial covariance matrix has been considered to be significant for beamformers. Standing upon the intersection of traditional beamformers and deep neural networks, we propose…
Joint magnitude estimation and phase recovery using Cycle-in-Cycle GAN for non-parallel speech enhancement
Guochen Yu, Andong Li, Yutian Wang +3
For the lack of adequate paired noisy-clean speech corpus in many real scenarios, non-parallel training is a promising task for DNN-based speech enhancement methods. However, becau…
CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism
Guochen Yu, Yutian Wang, Chengshi Zheng +2
Non-parallel training is a difficult but essential task for DNN-based speech enhancement methods, for the lack of adequate noisy and paired clean speech corpus in many real scenari…
A Simultaneous Denoising and Dereverberation Framework with Target Decoupling
Andong Li, Wenzhe Liu, Xiaoxue Luo +3
Background noise and room reverberation are regarded as two major factors to degrade the subjective speech quality. In this paper, we propose an integrated framework to address sim…
Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancement
Andong Li, Chengshi Zheng, Lu Zhang +1
The capability of the human to pay attention to both coarse and fine-grained regions has been applied to computer vision tasks. Motivated by that, we propose a collaborative learni…
Learning to Inference with Early Exit in the Progressive Speech Enhancement
Andong Li, Chengshi Zheng, Lu Zhang +1
In real scenarios, it is often necessary and significant to control the inference speed of speech enhancement systems under different conditions. To this end, we propose a stage-wi…
ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network
Andong Li, Wenzhe Liu, Xiaoxue Luo +2
It remains a tough challenge to recover the speech signals contaminated by various noises under real acoustic environments. To this end, we propose a novel system for denoising in…
A Robust Maximum Likelihood Distortionless Response Beamformer based on a Complex Generalized Gaussian Distribution
Weixin Meng, Chengshi Zheng, Xiaodong Li
For multichannel speech enhancement, this letter derives a robust maximum likelihood distortionless response beamformer by modeling speech sparse priors with a complex generalized…