Convolutional Recurrent MetriCGAN With Spectral Dimension Compression For Full-Band Speech Enhancement-Reference-Cited by-同舟云学术

Convolutional Recurrent MetriCGAN With Spectral Dimension Compression For Full-Band Speech Enhancement

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Hou Zhongshu¹,Hu Qinwen¹,Sun Tianchi¹,Hu Yuxiang²,Zhu Changbao²,Chen Kai¹

Affiliation:

1. Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093

2. NJU-Horizon Intelligent Audio Lab,Horizon Robotics,Beijing,China,100094

Funder

National Natural Science Foundation of China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10094559/10094560/10095906.pdf?arnumber=10095906

Reference6 articles.

1. On the importance of power compression and phase estimation in monaural speech dereverberation

2. Learnable spectral dimension compression mapping for full-band speech enhancement

3. Dnsmos P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors

4. Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs

5. MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement;fu;International Conference on Machine Learning,2019

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. General Speech Restoration Using Two-Stage Generative Adversarial Networks;2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2024-04-14

2. ICASSP 2023 Deep Noise Suppression Challenge;IEEE Open Journal of Signal Processing;2024