bernardo-torres / 1d-spectral-optimal-transport
An 1D optimal transport inspired loss function in the spectral domain. Can be used for improving frequency localization/estimation in differentiable digital signal processing. Experiments from paper: "Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport".
☆19Updated 9 months ago
Alternatives and similar repositories for 1d-spectral-optimal-transport:
Users that are interested in 1d-spectral-optimal-transport are comparing it to the libraries listed below
- Tips for best practices with filterbanks☆36Updated last year
- Unsupervised blind source separation of mixed images and sounds with variational auto-encoders.☆45Updated last year
- Official implementation of the ICASSP 2023 paper "HRTF Field: Unifying Measured HRTF Magnitude Representation with Neural Fields"☆22Updated last year
- Pytorch implementation of the invertible CQT based on Non-stationary Gabor filters☆29Updated last year
- Fast and differentiable time domain all-pole filter in PyTorch.☆55Updated 3 weeks ago
- BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models☆38Updated 4 months ago
- Unsupervised Music Source Separation Using Differentiable Parametric Source Models☆61Updated last year
- Neural IIR Filter Field for HRTF Upsampling and Personalization☆23Updated 11 months ago
- Gaussian processes for sound field reconstruction☆21Updated 4 years ago
- A multizone sound field control method to synthesize a desired amplitude (or magnitude) distributions over a target region with multiple …☆12Updated last year
- ☆11Updated last week
- Official Pytorch implementation of PULSE: Positive–Unlabelled Learning for audio Signal Enhancement (Best Paper Award at ICASSP 2023)☆41Updated last year
- The LAP Challenge aims at advancing spatial audio technologies through the personalization of HRTFs.☆13Updated 3 weeks ago
- Implementation of FiNS model for RIR estimation☆28Updated last year
- Da - ECHO - RetrievAl - daTasEt☆25Updated 7 months ago
- Acoustic impulse response generation using diffusion models☆68Updated last year
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆57Updated 2 years ago
- ☆48Updated 3 months ago
- Official PyTorch implementation for "Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations".☆21Updated 3 years ago
- Acoustic signal processing demos with jupyter notebooks☆12Updated last year
- Official repository of the paper "Solving Audio Inverse Problems with a Diffusion Model", submitted to ICASSP 23☆112Updated last year
- Accompanying code for our paper "Optimizing Short-Time Fourier Transform Parameters via Gradient Descent"☆31Updated 4 years ago
- Github repository for the paper accepted in ICASSP 2024 : Blind estimation of audio effects using an auto-encoder approach and differenti…☆13Updated 10 months ago
- An extended TSP (Time Stretched Pulse). CAPRICEP substantially replaces FVN. CAPRICEP enables interactive and real-time measurement of th…☆28Updated last year
- Direct and Residual Subspace Decomposition of Spatial Room Impulse Responses☆21Updated 2 years ago
- (ICASSP 2025) Learning Source Disentanglement in Neural Audio Codec☆25Updated 2 months ago
- Deep generative models for extending the bandwidth of reconstructed room impulse responses corrupted by undersampling.☆11Updated 2 years ago
- A PyTorch implementation: "LASAFT-Net-v2: Listen, Attend and Separate by Attentively aggregating Frequency Transformation"☆33Updated 2 years ago
- Learning and controlling the source-filter representation of speech with a variational autoencoder☆45Updated last year