slp-rl/aero
This repo contains the official PyTorch implementation of "Audio Super Resolution in the Spectral Domain" (ICASSP 2023)
This project helps audio engineers and sound designers enhance the quality of audio recordings. It takes low-resolution speech or music audio files as input and outputs higher-resolution versions, restoring missing frequencies. Anyone working with audio that needs to sound clearer or more detailed, such as in podcast production or music mastering, would find this useful.
237 stars. No commits in the last 6 months.
Use this if you have low-quality or bandwidth-limited audio recordings and need to boost their spectral quality to sound richer and more detailed.
Not ideal if you're looking for a simple drag-and-drop tool, as this requires some technical setup and command-line operations.
Stars
237
Forks
34
Language
Python
License
MIT
Category
Last pushed
May 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/slp-rl/aero"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
descriptinc/descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz...
drethage/speech-denoising-wavenet
A neural network for end-to-end speech denoising
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
iver56/torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
lmnt-com/wavegrad
A fast, high-quality neural vocoder.