maxime-leiber / dstftLinks
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).
☆48Updated 7 months ago
Alternatives and similar repositories for dstft
Users that are interested in dstft are comparing it to the libraries listed below
Sorting:
- A 1D implementation of a deformable convolutional layer in PyTorch with a few tricks.☆46Updated 2 years ago
- A self-supervised speech denoising strategy named Only-Noisy Training (ONT), which solves the speech denoising problem with only noisy au…☆74Updated 2 years ago
- ☆13Updated last week
- A pip installable package for optimal transport inspired loss functions in the spectral domain. Can be used for audio applications such a…☆28Updated 2 months ago
- (TASLP 2022) Unsupervised speech enhancement using DVAEs☆23Updated last year
- Tips for best practices with filterbanks☆43Updated 8 months ago
- Directional sparse filtering for blind speech separation☆10Updated 4 years ago
- Revisiting Denoising Diffusion Probabilistic Models for Speech Enhancement: Condition Collapse, Efficiency and Refinement, Thirty-Seventh…☆47Updated 2 years ago
- [SLT'24] The official implementation of SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model☆134Updated 3 months ago
- ☆30Updated 4 years ago
- [Not Official] Implementation DC-UNet, ICLR 2019☆56Updated last year
- DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement, Conference on Neural Information Processing Systems (NeurIPS), 2023☆59Updated 8 months ago
- CST-former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detection (ICASSP 2024)☆35Updated 8 months ago
- ASiT: Audio Spectrogram vIsion Transformer for General Audio Representation☆28Updated last year
- Learning discriminative and robust time-frequency representations for environmental sound classification: Convolutional neural networks (…☆30Updated 6 years ago
- Official implementation of Efficient Speech Separation Framework Based on Neural State-Space Models☆22Updated 2 years ago
- An official documentation of the paper <Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolution>.☆24Updated 3 months ago
- Official Pytorch implementation of PULSE: Positive–Unlabelled Learning for audio Signal Enhancement (Best Paper Award at ICASSP 2023)☆43Updated 2 years ago
- Codebase of the submitted work in ICASSP 2023☆14Updated 3 years ago
- Tutorial on using machine learning for acoustics. This tutorial covers a wide range of machine learning approaches for acoustic applicati…☆112Updated 4 months ago
- AudioLDM training, finetuning, evaluation and inference.☆14Updated last year
- Full-frequency dynamic convolution: a physical frequency-dependent convolution for sound event detection☆22Updated last year
- Joint Estimation of Frequency, Amplitude and Spectrum☆34Updated 3 years ago
- Short-Time Discrete Cosine Transform (DCT) for Python. SciPy, TensorFlow and PyTorch implementations.☆28Updated 4 years ago
- 把 wave-u-net 网络应用于语音增强领域中☆14Updated 5 years ago
- Repository of published DNN speech separation recipes for a number of datasets☆12Updated 2 years ago
- ☆23Updated 2 years ago
- A python implementation of “Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Mult…☆39Updated last year
- ☆35Updated last year
- his code is a pytorch version for CycleFlow model in "CycleFlow: Purify Information Factors by Cycle Loss"☆15Updated 4 years ago