/awesome-speech-enhancement

speech enhancement\speech seperation\sound source localization

GNU General Public License v2.0GPL-2.0

Awesome Speech Enhancement

This repository summarizes the papers, codes and tools for single-/multi-channel speech enhancement/speech seperation task, which aims to create a list of open source projects rather than pursuing the completeness of the papers. You are kindly invited to pull requests.

Contents

Speech_Enhancement

Magnitude spectrogram

IRM

Magnitude spectrogram mapping

  • An Experimental Study on Speech Enhancement Based on Deep Neural Networks, Xu, 2014. [Paper]
  • A Regression Approach to Speech Enhancement Based on Deep Neural Networks, Xu, 2014. [Paper] [sednn] [DNN-SE-Xu] [DNN-SE-Li]
  • Other DNN magnitude spectrum mapping-based SE repositories: [SE toolkit] [TensorFlow-SE] [UNetSE]
  • Speech enhancement with LSTM recurrent neuralnetworks and its application to noise-robust ASR, Weninger, 2015. [Paper]
  • Long short-term memory for speaker generalizationin supervised speech separation, Chen, 2017. [Paper]
  • Online Monaural Speech Enhancement using Delayed Subband LSTM, Li, 2020. [Paper]
  • FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement, Hao, 2020. [Paper] [FullSubNet]
  • A Fully Convolutional Neural Network for Speech Enhancement, Park, 2016. [Paper] [CNN4SE]
  • A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement, Tan, 2018. [Paper] [CRN-Tan]
  • Convolutional-Recurrent Neural Networks for Speech Enhancement, Zhao, 2018. [Paper] [CRN-Hao]

Complex domain

  • Complex spectrogram enhancement by convolutional neural network with multi-metrics learning, Fu, 2017. [Paper]
  • Learning Complex Spectral Mapping With GatedConvolutional Recurrent Networks forMonaural Speech Enhancement, Tan, 2020. [Paper] [GCRN]
  • Phase-aware Speech Enhancement with Deep Complex U-Net, Choi, 2019. [Paper] [DC-UNet]
  • DCCRN: Deep Complex Convolution Recurrent Network for Phase-AwareSpeech Enhancement, Hu, 2020. [Paper] [DCCRN]
  • T-GSA: Transformer with Gaussian-Weighted Self-Attention for Speech Enhancement, Kim, 2020. [Paper]
  • PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network, Yin, 2019. [Paper] [PHASEN]
  • Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising, Williamson, 2017. [Paper]
  • Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net, Choi, 2020. [Paper]

Time domain

  • Real Time Speech Enhancement in the Waveform Domain, Defossez, 2020. [Paper] [facebookDenoiser]
  • Improved Speech Enhancement with the Wave-U-Net, Macartney, 2018. [Paper] [WaveUNet]
  • Monaural speech enhancement through deep wave-U-net, Guimarães, 2020. [Paper] [SEWUNet]
  • A New Framework for CNN-Based Speech Enhancement in the Time Domain, Pandey, 2019. [Paper]
  • Speech Enhancement Using Dilated Wave-U-Net: an Experimental Analysis, Ali, 2020. [Paper]
  • TCNN: Temporal Convolutional Neural Network for Real-time Speech Enhancement in the Time Domain, Pandey, 2019. [Paper]
  • Densely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in the Time Domain, Pandey, 2020. [Paper] [DDAEC]
  • Dense CNN With Self-Attention for Time-Domain Speech Enhancement, Pandey, 2021. [Paper]
  • Dual-path Self-Attention RNN for Real-Time Speech Enhancement, Pandey, 2021. [Paper]

GAN

  • SEGAN: Speech Enhancement Generative Adversarial Network, Pascual, 2017. [Paper] [SEGAN]
  • SERGAN: Speech enhancement using relativistic generative adversarial networks with gradient penalty, Deepak Baby, 2019. [Paper] [SERGAN]
  • MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement, Fu, 2019. [Paper] [MetricGAN]
  • MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement, Fu, 2019. [Paper] [MetricGAN+]
  • HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks, Su, 2020. [Paper] [HifiGAN]

Hybrid SE

  • Deep Xi as a Front-End for Robust Automatic Speech Recognition, Nicolson, 2019. [Paper] [DeepXi]
  • Deep Residual-Dense Lattice Network for Speech Enhancement, Nikzad, 2020. [Paper] [RDL-SE]
  • DeepMMSE: A Deep Learning Approach to MMSE-based Noise Power Spectral Density Estimation, Zhang, 2020. [Paper]
  • Using Generalized Gaussian Distributions to Improve Regression Error Modeling for Deep-Learning-Based Speech Enhancement, Li, 2019. [Paper] [SE-MLC]
  • Speech Enhancement Using a DNN-Augmented Colored-Noise Kalman Filter, Yu, 2020. [Paper] [DNN-Kalman]

Multi-stage

  • A Recursive Network with Dynamic Attention for Monaural Speech Enhancement, Li, 2020. [Paper] [DARCN]
  • Masking and Inpainting: A Two-Stage Speech Enhancement Approach for Low SNR and Non-Stationary Noise, Hao, 2020. [Paper]
  • A Joint Framework of Denoising Autoencoder and Generative Vocoder for Monaural Speech Enhancement, Du, 2020. [Paper]
  • Dual-Signal Transformation LSTM Network for Real-Time Noise Suppression, Westhausen, 2020. [Paper] [DTLN]
  • Listening to Sounds of Silence for Speech Denoising, Xu, 2020. [Paper] [LSS]
  • ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network, Li, 2021. [Paper]

Data collection

Loss

Challenge

Other repositories

  • Collection of papers, datasets and tools on the topic of Speech Dereverberation and Speech Enhancement [Link]

Dereverberation

Traditional method

Hybrid method

NN-based Derev

Speech Seperation (single channel)

  • Tasnet: time-domain audio separation network for real-time, single-channel speech separation [Code]
  • Conv-TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation [Code]
  • Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation [Code1] [Code2]
  • DANet:Deep Attractor Network (DANet) for single-channel speech separation [Code]
  • TAC end-to-end microphone permutation and number invariant multi-channel speech separation [Code]
  • uPIT-for-speech-separation:Speech separation with utterance-level PIT [Code]
  • LSTM_PIT_Speech_Separation [Code]
  • Deep-Clustering [Code] [Code] [Code]
  • sound separation(Google) [Code]
  • sound separation: Deep learning based speech source separation using Pytorch [Code]
  • music-source-separation [Code]
  • Singing-Voice-Separation [Code]
  • Comparison-of-Blind-Source-Separation-techniques[Code]
  • FastICA[Code]
  • A localisation- and precedence-based binaural separation algorithm[Download]
  • Convolutive Transfer Function Invariant SDR [Code]

Array Signal Processing

  • MASP:Microphone Array Speech Processing [Code]
  • BeamformingSpeechEnhancer [Code]
  • TSENet [Code]
  • steernet [Code]
  • DNN_Localization_And_Separation [Code]
  • nn-gev:Neural network supported GEV beamformer CHiME3 [Code]
  • chime4-nn-mask:Implementation of NN based mask estimator in pytorch(reuse some programming from nn-gev)[Code]
  • beamformit_matlab:A MATLAB implementation of CHiME4 baseline Beamformit [Code]
  • pb_chime5:Speech enhancement system for the CHiME-5 dinner party scenario [Code]
  • beamformit:麦克风阵列算法 [Code]
  • Beamforming-for-speech-enhancement [Code]
  • deepBeam [Code]
  • NN_MASK [Code]
  • Cone-of-Silence [Code]

  • binauralLocalization [Code]
  • robotaudition_examples:Some Robot Audition simplified examples (sound source localization and separation), coded in Octave/Matlab [Code]
  • WSCM-MUSIC [Code]
  • doa-tools [Code]
  • Regression and Classification for Direction-of-Arrival Estimation with Convolutional Recurrent Neural Networks [Code] [PDF]
  • messl:Model-based EM Source Separation and Localization [Code]
  • messlJsalt15:MESSL wrappers etc for JSALT 2015, including CHiME3 [Code]
  • fast_sound_source_localization_using_TLSSC:Fast Sound Source Localization Using Two-Level Search Space Clustering [Code]
  • Binaural-Auditory-Localization-System [Code]
  • Binaural_Localization:ITD-based localization of sound sources in complex acoustic environments [Code]
  • Dual_Channel_Beamformer_and_Postfilter [Code]
  • 麦克风声源定位 [Code]
  • RTF-based-LCMV-GSC [Code]
  • DOA [Code]

Sound Event Detection

  • sed_eval - Evaluation toolbox for Sound Event Detection [Code]
  • Benchmark for sound event localization task of DCASE 2019 challenge [Code]
  • sed-crnn DCASE 2017 real-life sound event detection winning method. [Code]
  • seld-net [Code]

Tools

  • APS:A workspace for single/multi-channel speech recognition & enhancement & separation. [Code]
  • AKtools:the open software toolbox for signal acquisition, processing, and inspection in acoustics [SVN Code](username: aktools; password: ak)
  • espnet [Code]
  • asteroid:The PyTorch-based audio source separation toolkit for researchers[PDF][Code]
  • pytorch_complex [Code]
  • ONSSEN: An Open-source Speech Separation and Enhancement Library [Code]
  • separation_data_preparation[Code]
  • MatlabToolbox [Code]
  • athena-signal [[Code]](https://github.com/athena-team/athena-signal)
  • python_speech_features [Code]
  • speechFeatures:语音处理,声源定位中的一些基本特征 [Code]
  • sap-voicebox [Code]
  • Calculate-SNR-SDR [Code]
  • RIR-Generator [Code]
  • Python library for Room Impulse Response (RIR) simulation with GPU acceleration [Code]
  • ROOMSIM:binaural image source simulation [Code]
  • binaural-image-source-model [Code]
  • PESQ [Code]
  • SETK: Speech Enhancement Tools integrated with Kaldi [Code]
  • pb_chime5:Speech enhancement system for the CHiME-5 dinner party scenario [Code]

Resources

  • Speech Signal Processing Course(ZH) [Link]
  • Speech Algorithms(ZH) [Link]
  • CCF语音对话与听觉专业组语音对话与听觉前沿研讨会(ZH) [Link]