JusperLee/Conv-TasNet
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement
This project helps remove unwanted voices or noise from recordings, isolating individual speakers. It takes a mixed audio file containing multiple speakers or background noise and outputs separate, clean audio tracks for each speaker. Voice analysts, audio engineers, or researchers working with conversational data would find this useful for improving speech clarity.
535 stars. No commits in the last 6 months.
Use this if you need to cleanly separate individual speech signals from recordings where multiple people are speaking at once or there is significant background noise.
Not ideal if your primary goal is to remove non-speech noise or if you require real-time audio processing for live applications.
Stars
535
Forks
81
Language
Python
License
—
Category
Last pushed
May 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/JusperLee/Conv-TasNet"
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.