merlresearch / cocktail-fork-separation
Baseline multi-resolution cross network model trained using the Divide and Remaster Dataset
☆80Updated last year
Alternatives and similar repositories for cocktail-fork-separation:
Users that are interested in cocktail-fork-separation are comparing it to the libraries listed below
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement☆155Updated 2 years ago
- PAM is a no-reference audio quality metric for audio generation tasks☆57Updated 8 months ago
- BandIt: Cinematic Audio Source Separation☆112Updated 8 months ago
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆91Updated 7 months ago
- Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'☆95Updated 8 months ago
- ☆43Updated 9 months ago
- Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation…☆64Updated last year
- AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)☆96Updated 4 months ago
- Evaluation and Benchmarking of Speech Super-resolution Methods☆149Updated 2 years ago
- SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)☆68Updated 2 months ago
- An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation☆85Updated last year
- ☆78Updated last year
- Unofficial PyTorch implementation of "SCNet: Sparse Compression Network for Music Source Separation"☆53Updated 11 months ago
- Speech Human Evaluation Estimation Toolkit (SHEET)☆61Updated 4 months ago
- A DDSP-based neural voice synthesiser.☆114Updated 4 months ago
- The official PyTorch implementation of "Inter-SubNet: Speech Enhancement with Subband Interaction", accepted by ICASSP 2023.☆95Updated last year
- Sound Demixing Challenge 2023☆79Updated last year
- High-Fidelity Neural Phonetic Posteriorgrams☆108Updated last month
- ☆88Updated 3 months ago
- ☆64Updated 11 months ago
- logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source…☆38Updated 8 months ago
- Pytorch implementation of subband decomposition☆92Updated 2 years ago
- ☆65Updated last year
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆59Updated 2 months ago
- Reference-aware automatic speech evaluation toolkit☆145Updated 3 months ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆58Updated 2 years ago
- ☆123Updated 2 months ago
- Pitch Estimating Neural Networks (PENN)☆248Updated 8 months ago
- Official data preparation scripts for the URGENT 2024 Challenge☆76Updated 2 months ago
- High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec☆96Updated 2 months ago