kwatcharasupat / bandit-v2
Reimplementation of Bandit for "Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support"
☆28Updated 7 months ago
Alternatives and similar repositories for bandit-v2:
Users that are interested in bandit-v2 are comparing it to the libraries listed below
- Landing Page for All Things Source Separation☆23Updated 4 months ago
- ☆35Updated 2 months ago
- ☆22Updated 11 months ago
- AudioSR-Upsampling (any -> 48kHz)☆40Updated last year
- Official implementation of "AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and sta…☆37Updated 4 months ago
- [ICASSP 2025] FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion☆57Updated last month
- ☆39Updated 11 months ago
- ☆30Updated last year
- A robust pitch tracker using synchro-squeezed fft and frequency domain autocorrelation☆34Updated last year
- Speech enhancement in noisy and reverberant environments using deep neural networks☆20Updated 3 weeks ago
- SPAUQ: Spatial Audio Quality Evaluation☆17Updated 10 months ago
- ☆63Updated 11 months ago
- PyTorch implementation of the ICASSP-24 paper: "Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Superv…☆36Updated last year
- An implementation of "Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction", in ISMIR 2023☆21Updated last year
- Pytorch implementation of the invertible CQT based on Non-stationary Gabor filters☆29Updated last year
- A fast python library for aligning similar audio snippets passed in as NumPy arrays☆44Updated last week
- ☆43Updated 9 months ago
- ☆22Updated last month
- Frechet Audio Distance evaluation in PyTorch☆35Updated last year
- Source code and demo for INTERSPEECH 2024 paper: Noise-robust Speech Separation with Fast Generative Correction☆37Updated 4 months ago
- The official implementation of TokenSynth (ICASSP 2025)☆51Updated 2 weeks ago
- Project for MIDI to Audio Synthesis☆22Updated 2 years ago
- PiCoGen (Piano Cover Generation) is an academic project aimed at developing an automatic piano cover generation system.☆27Updated 5 months ago
- PitchVC: Pitch Conditioned Any-to-Many Voice Conversion☆34Updated 9 months ago
- ☆22Updated 6 months ago
- music semantic understanding evaluation benchmark☆25Updated last year
- This is the official implementation of our multi-channel multi-speaker multi-spatial neural audio codec architecture.☆47Updated last week
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆40Updated last year
- MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing [ISMIR 2024]☆40Updated 2 months ago
- Official implementation for FlowSep☆34Updated 2 months ago