Statistics for topic speech-enhancement

RepositoryStats tracks 584,797 Github repositories, of these 74 are tagged with the speech-enhancement topic. The most common primary language for repositories using this topic is Python (60).

Stargazers over time for topic speech-enhancement

Most starred repositories for topic speech-enhancement (view more)

speechbrain
speechbrain speechbrain
1.4k
8.9k
apache-2.0
136
A PyTorch-based Speech Toolkit
asr audio pytorch huggingface transformers deep-learning language-model speech-to-text speech-toolkit audio-processing speech-processing speech-separation speechrecognition voice-recognition speech-enhancement speech-recognition speaker-diarization speaker-recognition speaker-verification spoken-language-understanding
Created 2020-04-28
10,276 commits to develop branch, last one 6 days ago
espnet
espnet espnet
2.2k
8.5k
apache-2.0
181
End-to-End Speech Processing Toolkit
kaldi chainer pytorch end-to-end deep-learning text-to-speech speech-synthesis voice-conversion speech-separation speech-enhancement speech-recognition speech-translation machine-translation speaker-diarization singing-voice-synthesis spoken-language-understanding
Created 2017-12-13
22,298 commits to master branch, last one 6 days ago
Rikorose
DeepFilterNet Rikorose
237
2.5k
other
30
Noise supression using deep filtering
rust audio speech pytorch deep-learning noise-suppression speech-enhancement
Created 2021-10-10
1,602 commits to main branch, last one about a month ago
asteroid-team
asteroid asteroid-team
423
2.3k
mit
52
The PyTorch-based audio source separation toolkit for researchers
pytorch deep-learning audio-separation pretrained-models source-separation speech-separation speech-enhancement
Created 2019-10-18
916 commits to master branch, last one 4 months ago
resemble-ai
resemble-enhance resemble-ai
143
1.4k
mit
18
AI powered speech denoising and enhancement
denoise speech-denoising speech-processing speech-enhancement
Created 2023-11-15
10 commits to main branch, last one 5 months ago
haoheliu
voicefixer haoheliu
133
1.0k
mit
17
General Speech Restoration
mel tts speech denoise vocoder declipping dereverberation speech-analysis speech-synthesis super-resolution speech-processing speech-enhancement
Created 2021-09-06
92 commits to main branch, last one 7 months ago

Trending repositories for topic speech-enhancement (view more)

Last 3 days (new repositories)
no newly created repositories trending in the last 3 days
Last 3 days (absolute gain)
speechbrain
speechbrain/speechbrain

A PyTorch-based Speech Toolkit

8,948 (+19)
apache-2.0
resemble-ai
resemble-ai/resemble-enhance

AI powered speech denoising and enhancement

1,440 (+11)
mit
espnet
espnet/espnet

End-to-End Speech Processing Toolkit

8,512 (+7)
apache-2.0
ictnlp
ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

959 (+4)
mit
yxlu-0102
yxlu-0102/MP-SENet

Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement

318 (+2)
mit
Last 3 days (relative gain)
Speech-Interaction-Technology-Aalto-U
Speech-Interaction-Technology-Aalto-U/itsp

Introduction to Speech Processing

72 (+1%)
cc-by-sa-4.0
Audio-WestlakeU
Audio-WestlakeU/RealMAN

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

95 (+1%)
resemble-ai
resemble-ai/resemble-enhance

AI powered speech denoising and enhancement

1,440 (+0.8%)
mit
yxlu-0102
yxlu-0102/MP-SENet

Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement

318 (+0.6%)
mit
ictnlp
ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

959 (+0.4%)
mit
Last week (new repositories)
no newly created repositories trending in the last week
Last week (absolute gain)
speechbrain
speechbrain/speechbrain

A PyTorch-based Speech Toolkit

8,948 (+31)
apache-2.0
resemble-ai
resemble-ai/resemble-enhance

AI powered speech denoising and enhancement

1,440 (+19)
mit
espnet
espnet/espnet

End-to-End Speech Processing Toolkit

8,512 (+14)
apache-2.0
Rikorose
Rikorose/DeepFilterNet

Noise supression using deep filtering

2,545 (+10)
ictnlp
ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

959 (+8)
mit
Last week (relative gain)
Speech-Interaction-Technology-Aalto-U
Speech-Interaction-Technology-Aalto-U/itsp

Introduction to Speech Processing

72 (+3%)
cc-by-sa-4.0
Audio-WestlakeU
Audio-WestlakeU/RealMAN

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

95 (+2%)
claritychallenge
claritychallenge/clarity

Clarity Challenge toolkit - software for building Clarity Challenge systems

135 (+2%)
mit
resemble-ai
resemble-ai/resemble-enhance

AI powered speech denoising and enhancement

1,440 (+1%)
mit
skirdey
skirdey/voicerestore

VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration

84 (+1%)
mit
Last month (new repositories)
no newly created repositories trending in the last month
Last month (absolute gain)
speechbrain
speechbrain/speechbrain

A PyTorch-based Speech Toolkit

8,948 (+184)
apache-2.0
espnet
espnet/espnet

End-to-End Speech Processing Toolkit

8,512 (+98)
apache-2.0
resemble-ai
resemble-ai/resemble-enhance

AI powered speech denoising and enhancement

1,440 (+82)
mit
Rikorose
Rikorose/DeepFilterNet

Noise supression using deep filtering

2,545 (+76)
ictnlp
ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

959 (+56)
mit
Last month (relative gain)
Audio-WestlakeU
Audio-WestlakeU/RealMAN

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

95 (+19%)
nanless
nanless/universal-speech-enhancement

Apply Score diffusion to improve speech signals recorded under various adverse conditions and distortions, including noise, reverberation, clipping, equalization (EQ) distortion, packet loss, codec lo...

40 (+11%)
mit
Xiaobin-Rong
Xiaobin-Rong/deepvqe

An unofficial implementation of DeepVQE proposed by Microsoft Corp.

71 (+11%)
haoxiangsnr
haoxiangsnr/spiking-fullsubnet

Official repository of Spiking-FullSubNet, the Intel N-DNS Challenge Algorithmic Track Winner.

75 (+10%)
mit
Speech-Interaction-Technology-Aalto-U
Speech-Interaction-Technology-Aalto-U/itsp

Introduction to Speech Processing

72 (+9%)
cc-by-sa-4.0
Last 12-months (new repositories)
ictnlp
ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

959
mit
Audio-WestlakeU
Audio-WestlakeU/RealMAN

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

95
skirdey
skirdey/voicerestore

VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration

84
mit
line
line/open-universe

Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.

72
apache-2.0
Xiaobin-Rong
Xiaobin-Rong/SEtrain

A training code template for DNN-based speech enhancement.

53
Last 12-months (absolute gain)
speechbrain
speechbrain/speechbrain

A PyTorch-based Speech Toolkit

8,948 (+2,098)
apache-2.0
resemble-ai
resemble-ai/resemble-enhance

AI powered speech denoising and enhancement

1,440 (+1,417)
mit
espnet
espnet/espnet

End-to-End Speech Processing Toolkit

8,512 (+1,141)
apache-2.0
Rikorose
Rikorose/DeepFilterNet

Noise supression using deep filtering

2,545 (+1,034)
ictnlp
ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

959 (+953)
mit
Last 12-months (relative gain)
ictnlp
ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

959 (+15,883%)
mit
resemble-ai
resemble-ai/resemble-enhance

AI powered speech denoising and enhancement

1,440 (+6,161%)
mit
line
line/open-universe

Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.

72 (+929%)
apache-2.0
haoxiangsnr
haoxiangsnr/spiking-fullsubnet

Official repository of Spiking-FullSubNet, the Intel N-DNS Challenge Algorithmic Track Winner.

75 (+733%)
mit
yuyun2000
yuyun2000/SpeechDenoiser

SpeechDenoiser: Real-Time Speech Denoising with ONNX Welcome to SpeechDenoiser, a simple and effective solution for real-time speech denoising using an ONNX model. This repository contains everything...

44 (+529%)