Repositories list

• Mel-McNet

  Public
  The Official PyTorch Implementation of "Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement" [Interspeech 2025]

  Python

  •11 fork•2626 stars•22 issues•00 pull requests•Updated May 14, 2026May 14, 2026

• FS-EEND

  Public
  The official Pytorch implementation of "Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors". [ICASSP 20…

  end-to-endpytorchspeaker-diarization+ 4

  end-to-endpytorchspeaker-diarizationself-attentionlong-formonline-inferenceframe-wise

  Python

  •1717 forks•179179 stars•99 issues•00 pull requests•Updated May 7, 2026May 7, 2026

• ATST-SED

  Public
  This repo includes the official implementations of "Fine-tune the pretrained ATST model for sound event detection".

  semi-supervised-learningsedsound-event-detection+ 3

  semi-supervised-learningsedsound-event-detectionfine-tuningself-supervised-learningatst

  Jupyter Notebook

  •

  MIT License

  •1515 forks•167167 stars•22 issues•00 pull requests•Updated Apr 22, 2026Apr 22, 2026

• VING

  Public
  Official implementation of VING: Variational Bayesian Inference with Multi-Aspect Neural Guidance for Speech Dereverberation

  MIT License

  •11 fork•44 stars•00 issues•00 pull requests•Updated Apr 17, 2026Apr 17, 2026

• FN-SSL

  Public
  The Official PyTorch Implementation of FN-SSL & IPDnet for Sound Source Localization [INTERSPEECH2023 & TASLP2024]

  speechnarrow-bandsound-source-localization+ 1

  speechnarrow-bandsound-source-localizationmicrophone-array-generalization

  Python

  •1818 forks•154154 stars•33 issues•00 pull requests•Updated Mar 10, 2026Mar 10, 2026

• VINP

  Public
  Official PyTorch implementation of 'VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR I…

  speechrirasr+ 1

  speechrirasrdereverberation

  Python

  •

  MIT License

  •66 forks•3333 stars•11 issue•00 pull requests•Updated Feb 23, 2026Feb 23, 2026

• CleanMel

  Public
  Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".

  Python

  •

  Apache License 2.0

  •1212 forks•9292 stars•22 issues•00 pull requests•Updated Feb 2, 2026Feb 2, 2026

• Rec-RIR

  Public
  Official PyTorch implementation of 'Rec-RIR: Monaural Blind Room Impulse Response Identification via DNN-based Reverberant Speech Reconstruction in STFT Domain'

  rirdrrc50+ 1

  rirdrrc50t60

  Python

  •

  MIT License

  •22 forks•3333 stars•00 issues•00 pull requests•Updated Dec 25, 2025Dec 25, 2025

• audiossl

  Public
  A library built for easier audio self-supervised training, downstream tasks evaluation

  pytorchaudio-classificationaudioset+ 10

  pytorchaudio-classificationaudiosetnsynthspeech-commandsaudio-datasetsself-supervised-learningvoxceleb1urbansound8kpytorch-lightning+ 3

  Python

  •

  Other

  •1111 forks•139139 stars•66 issues•11 pull request•Updated Sep 25, 2025Sep 25, 2025

• RealMAN

  Public
  A description of "RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization" [NeurIPS 2024]

  multi-channelspeech-enhancementmicrophone-array-processing+ 5

  multi-channelspeech-enhancementmicrophone-array-processingdoa-estimationaudio-datasetssound-source-localizationmicrophone-audio-capturereal-world-datasets

  Python

  •1616 forks•164164 stars•44 issues•00 pull requests•Updated Apr 29, 2025Apr 29, 2025

• RVAE-EM

  Public
  Official PyTorch implementation of "RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function" [I…

  vaebayesian-inferencespeech-processing+ 2

  vaebayesian-inferencespeech-processingspeech-enhancementdereverberation

  Python

  •

  MIT License

  •55 forks•5252 stars•11 issue•00 pull requests•Updated Mar 6, 2025Mar 6, 2025

• NBSS

  Public
  The official repo of NBC & SpatialNet for multichannel speech separation, denoising, and dereverberation

  speechpytorchmulti-channel+ 6

  speechpytorchmulti-channelenhancementdenoisingseparationdereverberationnarrow-bandfull-band

  Python

  •

  MIT License

  •4343 forks•348348 stars•2828 issues•00 pull requests•Updated Jan 1, 2025Jan 1, 2025

• UMA-ASR

  Public
  This repository is the official implementation of unimodal aggregation (UMA) for automaticspeech recognition (ASR).

  speech-recognitionasr

  speech-recognitionasr

  Shell

  •66 forks•3535 stars•11 issue•00 pull requests•Updated Dec 17, 2024Dec 17, 2024

• SAR-SSL

  Public
  A python implementation of “Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Multi-Channel Conformer” [T…

  multi-channelmicrophone-arrayreal-world-data+ 11

  multi-channelmicrophone-arrayreal-world-dataroom-acousticsconformerfine-tuningtdoaarray-signal-processingself-supervised-learningdownstream-tasks+ 4

  Python

  •

  MIT License

  •11 fork•4040 stars•22 issues•00 pull requests•Updated Oct 11, 2024Oct 11, 2024

• ATST-RCT

  Public
  ATST-RCT model for DCASE 2022 task4.

  Python

  •00 forks•33 stars•00 issues•00 pull requests•Updated Sep 19, 2024Sep 19, 2024

• Microphone-Array-Generalization-for-Multichannel-Narrowband-Deep-Speech-Enhancement-

  Public
  Python

  •

  MIT License

  •00 forks•55 stars•00 issues•00 pull requests•Updated Mar 12, 2024Mar 12, 2024

• pytorch_lightning_template_for_beginners

  Public
  A pytorch template for beginners based on pytorch_lightning

  Python

  •77 forks•4949 stars•00 issues•00 pull requests•Updated Feb 1, 2024Feb 1, 2024

• FullSubNet

  Public
  PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

  audioreproducible-researchpaper+ 13

  audioreproducible-researchpaperspeechpytorchbandspeech-processingnoise-reductiondenoisingspeech-separation+ 6

  Python

  •

  MIT License

  •161161 forks•602602 stars•4040 issues•11 pull request•Updated Aug 19, 2023Aug 19, 2023

• McNet

  Public
  The official repo: "McNet: Fuse Multiple Cues for Multichannel Speech Enhancement", ICASSP 2023

  signal-processingpytorchspeech-enhancement+ 3

  signal-processingpytorchspeech-enhancementarray-signal-processingmulti-channel-speech-enhancementpytorch-lightning

  Python

  •1717 forks•130130 stars•33 issues•00 pull requests•Updated Mar 24, 2023Mar 24, 2023

• RCT

  Public
  This repo gives the code for the official implementation of RCT.

  Python

  •11 fork•1414 stars•00 issues•00 pull requests•Updated Jun 28, 2022Jun 28, 2022

• Microphone-Array-Generalization-for-Multichannel-Narrowband-Deep-Speech-Enhancement

  Public
  Python

  •

  MIT License

  •99 forks•88 stars•00 issues•00 pull requests•Updated Sep 30, 2021Sep 30, 2021

• Audio-WestlakeU.github.io

  Public
  Audio and Signal Information Processing Lab in Westlake University concentrates on speech processing algorithm

  MIT License

  •11 fork•33 stars•00 issues•00 pull requests•Updated Jul 8, 2021Jul 8, 2021

• Narrowband_DeepFiltering

  Public
  Python

  •66 forks•1919 stars•00 issues•00 pull requests•Updated Apr 1, 2020Apr 1, 2020

• RTF_InterFrameSpecSub

  Public
  MATLAB

  •33 forks•11 star•00 issues•00 pull requests•Updated Apr 1, 2020Apr 1, 2020

• RS_noisePSD

  Public
  MATLAB

  •00 forks•11 star•00 issues•00 pull requests•Updated Apr 1, 2020Apr 1, 2020

• DP_RTF_SSL

  Public
  MATLAB

  •33 forks•44 stars•11 issue•00 pull requests•Updated Apr 1, 2020Apr 1, 2020

• bss_ctf_lasso

  Public
  MATLAB

  •33 forks•55 stars•00 issues•00 pull requests•Updated Apr 1, 2020Apr 1, 2020

• dereverb_ctf_nonneg

  Public
  MATLAB

  •22 forks•11 star•00 issues•00 pull requests•Updated Apr 1, 2020Apr 1, 2020

• BSS_CTF_EM

  Public
  MATLAB

  •11 fork•00 stars•00 issues•00 pull requests•Updated Apr 1, 2020Apr 1, 2020

• LSTM-noisePSD

  Public
  Python

  •22 forks•88 stars•00 issues•00 pull requests•Updated Apr 1, 2020Apr 1, 2020