Audio-WestlakeU/VINP
Official PyTorch implementation of 'VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification' [IEEE TASLP]
This project helps audio engineers and researchers improve the clarity of speech recordings and understand the acoustic properties of a recording environment. It takes in reverberant speech audio and outputs a much clearer version of the speech, along with an estimated room impulse response (RIR) that describes how sound behaves in that space. This is ideal for professionals working with audio analysis or speech recognition.
Use this if you need to clean up noisy, echoey speech recordings to make them more understandable or to improve the accuracy of automatic speech recognition systems.
Not ideal if your primary goal is general noise reduction from sources other than reverberation, or if you do not require detailed room acoustic identification.
Stars
31
Forks
6
Language
Python
License
MIT
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Audio-WestlakeU/VINP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project