maxime-leiber / dstft
Differentiable short-time Fourier transform (DSTFT): Gradient-based parameters tuning for adaptive time-frequency representation. DSTFT is a neural network layer whose weights are its parameters (e.g. window and hop lengths).
☆34Updated last year
Alternatives and similar repositories for dstft:
Users that are interested in dstft are comparing it to the libraries listed below
- ☆28Updated 3 years ago
- (TASLP 2022) Unsupervised speech enhancement using DVAEs☆21Updated 4 months ago
- Official implementation of Efficient Speech Separation Framework Based on Neural State-Space Models☆21Updated last year
- A 1D implementation of a deformable convolutional layer in PyTorch with a few tricks.☆41Updated last year
- Official Pytorch implementation of PULSE: Positive–Unlabelled Learning for audio Signal Enhancement (Best Paper Award at ICASSP 2023)☆41Updated last year
- Repository of published DNN speech separation recipes for a number of datasets☆12Updated last year
- An 1D optimal transport inspired loss function in the spectral domain. Can be used for improving frequency localization/estimation in dif…☆19Updated last year
- Directional sparse filtering for blind speech separation☆10Updated 3 years ago
- ☆18Updated 3 years ago
- AudioLDM training, finetuning, evaluation and inference.☆14Updated last year
- ASiT: Audio Spectrogram vIsion Transformer for General Audio Representation☆26Updated last year
- SRTNet☆24Updated 2 years ago
- ☆10Updated 2 years ago
- Accompanying code for our paper "Optimizing Short-Time Fourier Transform Parameters via Gradient Descent"☆33Updated 4 years ago
- Transformer based Self-Attention for Complex Numbers☆12Updated 3 years ago
- Tips for best practices with filterbanks☆38Updated last year
- A neural speech codec based on discrete WavLM representations☆24Updated 8 months ago
- ☆29Updated 11 months ago
- ☆14Updated 2 years ago
- A STFT/iSTFT written up in PyTorch using 1D Convolutions☆28Updated 10 months ago
- Reference implementation of DecDTW in PyTorch (ICLR 2023)☆21Updated last year
- ICASSP 2024 paper - A Fully Differentiable Model for Unsupervised Singing Voice Separation☆11Updated 2 months ago
- A self-supervised speech denoising strategy named Only-Noisy Training (ONT), which solves the speech denoising problem with only noisy au…☆68Updated 2 years ago
- Official implementation of EfficientLEAF, a learnable audio frontend.☆40Updated 2 years ago
- A toolkit for researchers in the multimodal sound separation.☆16Updated last year
- Official source code of the INTERSPEECH 2023 paper: "Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Mo…☆19Updated last year
- PyTorch-based implementations of short-time Fourier transform☆15Updated 2 years ago
- Repo for source code of EBEN: Extreme Bandwidth Extension Network☆73Updated 3 months ago
- Da - ECHO - RetrievAl - daTasEt☆26Updated 10 months ago
- TODO☆38Updated last year