nomonosound / log-wmse-audio-quality
logWMSE, an audio quality metric with support for digital silence target. Useful for evaluating audio source separation systems, even when there are many audio tracks or stems.
☆33Updated last month
Related projects ⓘ
Alternatives and complementary repositories for log-wmse-audio-quality
- A fast python library for aligning similar audio snippets passed in as NumPy arrays☆42Updated 2 months ago
- ☆51Updated 3 weeks ago
- Frechet Audio Distance evaluation in PyTorch☆35Updated last year
- Official repository for the paper "Audio xLSTMs: Learning Self-supervised audio representations with xLSTMs"☆10Updated last month
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆54Updated last year
- Project for MIDI to Audio Synthesis☆22Updated last year
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆37Updated last year
- ☆21Updated 6 months ago
- Implementation for "Music Enhancement via Image Translation and Vocoding"☆52Updated 2 years ago
- ☆42Updated last week
- Differentiable dynamic range controller in PyTorch.☆44Updated last month
- Reproducible Subjective Evaluation☆57Updated 8 months ago
- Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems☆32Updated 2 weeks ago
- Landing Page for Divide and Remaster v3☆13Updated 3 months ago
- ☆21Updated last month
- Inference codebase for "Cacophony: An Improved Contrastive Audio-Text Model". Preprint: https://arxiv.org/abs/2402.06986☆37Updated 3 weeks ago
- An implementation of "Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction", in ISMIR 2023☆19Updated 9 months ago
- Viterbi decoding in PyTorch☆26Updated last month
- ☆40Updated 4 months ago
- Code for ISMIR 2020 paper: "Multiple F0 Estimation in Vocal Ensembles using Convolutional Neural Networks"☆54Updated last year
- PodcastMix A dataset for separating music and speech in podcasts.☆43Updated 2 months ago
- code for "DDD: A Perceptually Superior Low-Response-Time DNN-Based Declipper"☆20Updated 6 months ago
- Source code for training models and using the hyperbolic interface proposed in our ICASSP 2023 paper, “Hyperbolic Audio Source Separation…☆57Updated last year
- The MIR-MLPop dataset and the official implementation of the paper "MIR-MLPop: A Multilingual Pop Music Dataset with Time-Aligned Lyrics …☆22Updated 6 months ago
- ☆79Updated last year
- ☆48Updated last year
- TAPE: An End-to-End Timbre-Aware Pitch Estimator☆20Updated 11 months ago
- pyMUSHRA is a python web application which hosts webMUSHRA experiments and collects the data with python.☆35Updated last year
- A DDSP-based neural voice synthesiser.☆107Updated last week