GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → funcwj → voice-filter

funcwj / voice-filter

Licence: other
A unofficial Pytorch implementation of Google's VoiceFilter

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

pytorchspeech-separation

Projects that are alternatives of or similar to voice-filter

speech separation
Constrained Permutation Invariant Training, Speech Separation
Stars: ✭ 27 (-64%)
Mutual labels:  speech-separation
UtterancePIT-Speech-Separation
According to funcwj's uPIT, the training code supporting multi-gpu is written, and the Dataloader is reconstructed.
Stars: ✭ 55 (-26.67%)
Mutual labels:  speech-separation
TasNet
A PyTorch implementation of Time-domain Audio Separation Network (TasNet) with Permutation Invariant Training (PIT) for speech separation.
Stars: ✭ 81 (+8%)
Mutual labels:  speech-separation
UniSpeech
UniSpeech - Large Scale Self-Supervised Learning for Speech
Stars: ✭ 224 (+198.67%)
Mutual labels:  speech-separation
Voice-Separation-and-Enhancement
A framework for quick testing and comparing multi-channel speech enhancement and separation methods, such as DSB, MVDR, LCMV, GEVD beamforming and ICA, FastICA, IVA, AuxIVA, OverIVA, ILRMA, FastMNMF.
Stars: ✭ 60 (-20%)
Mutual labels:  speech-separation
open-speech-corpora
💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
Stars: ✭ 841 (+1021.33%)
Mutual labels:  speech-separation
awesome-speech-enhancement
A curated list of awesome Speech Enhancement papers, libraries, datasets, and other resources.
Stars: ✭ 48 (-36%)
Mutual labels:  speech-separation
Deep-Clustering-for-Speech-Separation
Pytorch implements Deep Clustering: Discriminative Embeddings For Segmentation And Separation
Stars: ✭ 99 (+32%)
Mutual labels:  speech-separation
mann-for-speech-separation
Neural Turing machine for source separation in Tensorflow
Stars: ✭ 18 (-76%)
Mutual labels:  speech-separation
Calculate-SNR-SDR
Script to calculate SNR and SDR using python
Stars: ✭ 76 (+1.33%)
Mutual labels:  speech-separation
Espnet
End-to-End Speech Processing Toolkit
Stars: ✭ 4,533 (+5944%)
Mutual labels:  speech-separation

VoiceFilter

A Pytorch implementation of Google's VoiceFilter System

Usage

  1. Data simulation

    ./nnet/data_simulate.py --dump-dir simu/train /path/to/librispeech/train.scp asset/train_tuples.csv
./nnet/data_simulate.py --dump-dir simu/dev /path/to/librispeech/dev.scp asset/dev_tuples.csv

  2. Speaker embedding (I used public xvector from here)

  3. Data prepare

    Prepare data as {mix,ref,emb}.scp and the format of scp file follows Kaldi's recipe, egs <key> <path> pair in each line.

  4. Confugure nnet/conf.py and train the model (see train.sh for details).

  5. Use nnet/separate.py for inference.

Note

  1. I used Si-SNR loss instead of MSE of spectrogram, which could achieve better perfermance.
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].