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).
☆32Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for dstft
- Official implementation of Efficient Speech Separation Framework Based on Neural State-Space Models☆18Updated last year
- ☆27Updated 3 years ago
- Transformer based Self-Attention for Complex Numbers☆11Updated 3 years ago
- Unsupervised speech enhancement using DVAEs☆19Updated 10 months ago
- ASiT: Audio Spectrogram vIsion Transformer for General Audio Representation☆21Updated 8 months ago
- Noise-Aware Speech Separation with Contrastive Learning☆16Updated 6 months ago
- ☆10Updated last year
- Official Pytorch implementation of PULSE: Positive–Unlabelled Learning for audio Signal Enhancement (Best Paper Award at ICASSP 2023)☆39Updated last year
- SRTNet☆24Updated last year
- Directional sparse filtering for blind speech separation☆9Updated 3 years ago
- Accompanying code for our paper "Optimizing Short-Time Fourier Transform Parameters via Gradient Descent"☆31Updated 4 years ago
- Repository of published DNN speech separation recipes for a number of datasets☆10Updated 10 months ago
- ☆17Updated 3 years ago
- ☆16Updated last year
- ☆14Updated last year
- TODO☆34Updated last year
- ☆9Updated 9 months ago
- A self-supervised speech denoising strategy named Only-Noisy Training (ONT), which solves the speech denoising problem with only noisy au…☆63Updated last year
- Repo for source code of EBEN: Extreme Bandwidth Extension Network☆69Updated last month
- A neural speech codec based on discrete WavLM representations☆21Updated 2 months ago
- Official source code of the INTERSPEECH 2023 paper: "Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Mo…☆19Updated last year
- Official Implementation of "Inference and Denoise: Causal Inference-based Neural Speech Enhancement"☆27Updated last year
- An unofficial code reproduction of Channel Attention Dense U-Net for Multichannel Speech Enhancement☆11Updated last year
- An 1D optimal transport inspired loss function in the spectral domain. Can be used for improving frequency localization/estimation in dif…☆19Updated 6 months ago
- Da - ECHO - RetrievAl - daTasEt☆24Updated 4 months ago
- A small tool to calculate the distribution of audio durations in a directory☆14Updated last year
- ☆28Updated 6 months ago
- PyTorch-based implementations of short-time Fourier transform☆15Updated 2 years ago
- ☆20Updated last month
- A STFT/iSTFT written up in PyTorch using 1D Convolutions☆25Updated 4 months ago