LibriMix

An open source dataset for source separation

MIT License

Stars

331

View Code on GitHub

Ecosystems: Python

Statistics for this project are still being loaded, please check back later.

Related Projects

demucs

Code for the paper Hybrid Spectrogram and Waveform Source Separation

25 Oct 2019 7,984

open-unmix-pytorch

Open-Unmix - Music Source Separation for PyTorch

14 May 2019 1,245

create_wsj1_2345_db

Collection of scripts to create a dataset of noisy multi-channel reverberant mixtures based on ws...

15 Oct 2021 7

dswav

23 Nov 2023 15

parler-tts

Inference and training library for high-quality TTS models.

13 Feb 2024 2,623

ASR_benchmark

Program to benchmark various speech recognition APIs

11 Dec 2017 78

music_source_separation

Music source separation

19 May 2021 1,258

VCTK-2Mix

07 May 2020 15

VoiceSplit

VoiceSplit: Targeted Voice Separation by Speaker-Conditioned Spectrogram

21 May 2020 203

2020_interspeech_gmdp

Generalized Minimal Distortion Principle for Blind Source Separation

07 Aug 2020 19

Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Genera...

07 Aug 2020 10,385

svoice

We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multi...

19 Nov 2020 1,227

SparseLibriMix

14 May 2020 52

pywsj0-mix

wsj0-{2, 3, 4, 5} mix generation scripts, in Python.

10 Mar 2021 44

Dir_SrcMic_DOA

Codebase of the submitted work in ICASSP 2023

02 Nov 2022 9