search

slp-rl / aero

This repo contains the official PyTorch implementation of "Audio Super Resolution in the Spectral Domain" (ICASSP 2023)
MIT License
190 stars 24 forks source link

Restore old tape recordings #1

Closed hobodrifterdavid closed 1 year ago

hobodrifterdavid commented 1 year ago

Hello, I wondered if you might have a comment on how to improve the clarity of recordings such as these: https://fsi-languages.yojik.eu/languages/FSI/fsi-french-basic.html

They are from old (reel-to-reel) tapes, with some kind of NR/noise gate, and low-bitrate compression.

Maybe I could make a dataset of original and (simulated) degraded recordings by running clean recordings through this cassette-tape simulator VST plugin?

https://www.wavesfactory.com/audio-plugins/cassette/ https://github.com/teragonaudio/MrsWatson

Thanks for your time.

m-mandel commented 1 year ago

Hi, You can try to train the model on datasets with similar noise. Alternatively, you can try to run the predict pipeline as is, but this may not work as AERO is not robust to audio from different sources.