【资源】语音增强资源集锦

【导读】本文整理了一些语音增强的论文、数据集、工具等资源。

Github链接：

https://github.com/nanahou/Awesome-Speech-Enhancement

论文6

Survey

• A literature survey on single channel speech enhancement, 2020 

• Supervised speech separation based on deep learning: An Overview, 2017

• A review on speech enhancement techniques, 2015 

• Nonlinear speech enhancement: an overview, 2007 

Feature augmentation

• Speech enhancement using self-adaptation and multi-head attention, ICASSP 2020

• PAN: phoneme-aware network for monaural speech enhancement, ICASSP 2020

• Noise tokens: learning neural noise templates for environment-aware speech enhancement

• Speaker-aware deep denoising autoencoder with embedded speaker identity for speech enhancement, Interspeech 2019

Network design

Filter design

• Efficient trainable front-ends for neural speech enhancement, ICASSP 2020 

Fusion techniques

• Masking and inpainting: a two-stage speech enhancement approach for low snr and non-stationary noise, ICASSP 2020 

• A composite dnn architecture for speech enhancement, ICASSP 2020 

• Multi-domain processing via hybrid denoising networks for speech enhancement, 2018 

Attention

• Speech enhancement using self-adaptation and multi-head attention, ICASSP 2020 

• Channel-attention dense u-net for multichannel speech enhancement, ICASSP 2020

• T-GSA: transformer with gaussian-weighted self-attention for speech enhancement, ICASSP 2020

U-net

• Phase-aware speech enhancement with deep complex u-net, ICLR 2019 

GAN

• PAGAN: a phase-adapted generative adversarial networks for speech enhancement, ICASSP 2020 

• Time-frequency masking-based speech enhancement using generative adversarial network, ICASSP 2018 

• SEGAN: speech enhancement generative adversarial network, Interspeech 2017

Phase reconstruction

• Phase reconstruction based on recurrent phase unwrapping with deep neural networks, ICASSP 2020

• PAGAN: a phase-adapted generative adversarial networks for speech enhancement, ICASSP 2020 

• Invertible dnn-based nonlinear time-frequency transform for speech enhancement, ICASSP 2020 

• Phase-aware speech enhancement with deep complex u-net, ICLR 2019 

Learning strategy

Loss function

• Speech denoising with deep feature losses, Interspeech 2019

• End-to-end multi-task denoising for joint sdr and pesq optimization, Arxiv 2019 

Other improvements

• Improving robustness of deep learning based monaural speech enhancement against processing artifacts, ICASSP 2020 [paper]

工具

数据集

更多资源

Book or thesis

• A Study on WaveNet, GANs and General CNNRNN Architectures, 2019 

• Deep learning: method and applications, 2016 

• Deep learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville, 2016 

• Robust automatic speech recognition by Jinyu Li and Li Deng, 2015 

Video

• CCF speech seminar 2020

• Real-time Single-channel Speech Enhancement with Recurrent Neural Networks by Microsoft Research, 2019

• Deep learning in speech by Hongyi Li, 2019 

• High-Accuracy Neural-Network Models for Speech Enhancement, 2017

• DNN-Based Online Speech Enhancement Using Multitask Learning and Suppression Rule Estimation, 2015 

• Microphone array signal processing: beyond the beamformer,2011

Slides

• Deep learning in speech by Hongyi Li, 2019

• Learning-based approach to speech enhancement and separation (INTERSPEECH tutorial, 2016)

• Deep learning for speech/language processing (INTERSPEECH tutorial by Li Deng, 2015)

• Speech enhancement algorithms (Stanford University, 2013)

专知，专业可信的人工智能知识分发，让认知协作更快更好！欢迎注册登录专知www.zhuanzhi.ai，获取5000+AI主题干货知识资料！

欢迎微信扫一扫加入专知人工智能知识星球群，获取最新AI专业干货知识教程资料和与专家交流咨询！

点击“ 阅读原文 ”，了解使用 专知 ，查看获取5000+AI主题知识资源