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]

49
/ 100
Emerging

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.

audio-enhancement speech-processing acoustic-analysis speech-recognition room-acoustics
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

31

Forks

6

Language

Python

License

MIT

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.