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).
☆30Updated 4 months ago
Related projects: ⓘ
- ☆26Updated 2 years ago
- Repository of published DNN speech separation recipes for a number of datasets☆10Updated 7 months ago
- SRTNet☆24Updated last year
- ASiT: Audio Spectrogram vIsion Transformer for General Audio Representation☆20Updated 6 months ago
- Unsupervised speech enhancement using DVAEs☆19Updated 8 months ago
- TODO☆31Updated 10 months ago
- Official Pytorch implementation of PULSE: Positive–Unlabelled Learning for audio Signal Enhancement (Best Paper Award at ICASSP 2023)☆39Updated last year
- ☆10Updated last year
- Revisiting Denoising Diffusion Probabilistic Models for Speech Enhancement: Condition Collapse, Efficiency and Refinement, Thirty-Seventh…☆36Updated 9 months ago
- ☆9Updated 7 months ago
- DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement, Conference on Neural Information Processing Systems (NeurIPS), 2023☆39Updated 2 weeks ago
- Noise-Aware Speech Separation with Contrastive Learning☆14Updated 4 months ago
- Transformer based Self-Attention for Complex Numbers☆10Updated 2 years ago
- A 1D implementation of a deformable convolutional layer in PyTorch with a few tricks.☆33Updated last year
- Official implementation of EfficientLEAF, a learnable audio frontend.☆39Updated last year
- ☆17Updated 3 years ago
- [SLT'24] The official implementation of SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model☆90Updated this week
- Official implementation of Efficient Speech Separation Framework Based on Neural State-Space Models☆17Updated last year
- Accompanying code for our paper "Optimizing Short-Time Fourier Transform Parameters via Gradient Descent"☆31Updated 3 years ago
- his code is a pytorch version for CycleFlow model in "CycleFlow: Purify Information Factors by Cycle Loss"☆14Updated 2 years ago
- ☆14Updated 10 months ago
- A Diffusion Probabilistic Model for Target Sound Extraction☆29Updated 5 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
- Official code release for "RTFS-Net: Recurrent time-frequency modelling for efficient audio-visual speech separation", accepted ICLR 2024☆35Updated 6 months ago
- A self-supervised speech denoising strategy named Only-Noisy Training (ONT), which solves the speech denoising problem with only noisy au…☆61Updated last year
- ☆48Updated 2 months ago
- A toolkit for researchers in the multimodal sound separation.☆16Updated 11 months ago
- A small tool to calculate the distribution of audio durations in a directory☆13Updated last year
- Repo for source code of EBEN: Extreme Bandwidth Extension Network☆66Updated last month