CPJKU / composer_concept
Supervised and unsupervised Concept-based explanation of pretrained music classifiers
☆12Updated last year
Related projects ⓘ
Alternatives and complementary repositories for composer_concept
- Frechet Audio Distance evaluation in PyTorch☆35Updated last year
- Project for MIDI to Audio Synthesis☆22Updated last year
- Polyphonic generalisation of DDSP☆16Updated 6 months ago
- ☆21Updated last month
- A piano music dataset with Audio, Symbolic and Text labels☆14Updated this week
- DExter: Learning and Controlling Performance Expression through Diffusion models☆16Updated 4 months ago
- A collection of metrics for evaluating timbre dissimilarity using the TorchMetrics API☆23Updated 2 years ago
- 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
- Official Implementation of Jointist☆32Updated last year
- "Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks", ICASSP 2022 (Data Generation Pipeline)☆35Updated 2 years ago
- Audio Prompt Adapter: Unleashing music editing abilities for text-to-music with lightweight finetuning [ISMIR 2024]☆34Updated last month
- music semantic understanding evaluation benchmark☆25Updated last year
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆37Updated last year
- This is the accompanying repository to the paper - Automatic Estimation of Singing Voice Musical Dynamics☆11Updated last week
- ☆21Updated 2 years ago
- This repository is for an implementation of the accepted paper "Sketching the Expression: Flexible Rendering of Expressive Piano Performa…☆20Updated last year
- MiRA (Music Replication Assessment) tool is a model-independent open evaluation method based on four diverse audio music similarity metri…☆23Updated 3 months ago
- ISMIR 24 Supplementary Material☆12Updated last week
- Codes and MIDI demos of ISMIR 2022 paper: Domain Adversarial Training on Conditional Variational Auto-Encoder for Controllable Music Gene…☆19Updated last year
- The ArtificialSongGenerator automatically composes and compiles the Artifical Audio Multitrack dataset (AAM).☆17Updated last year
- Deep Performer: Score-to-audio music performance synthesis☆42Updated last year
- Repository for Semi-supervised Synthesizer Sound Matching with Differentiable DSP☆20Updated 2 years ago
- ScorePerformer: Expressive Piano Performance Rendering with Fine-Grained Control (ISMIR 2023)☆35Updated last year
- ☆10Updated 4 months ago
- We propose a novel approach for reconstructing human expressiveness in piano performance with a multi-layer bi-directional Transformer. (…☆17Updated 5 months ago
- ☆27Updated 11 months ago
- Code for "A diffusion-inspired training strategy for singing voice extraction in the waveform domain" (ISMIR 2022)☆16Updated last year
- Code accompayning ISMIR23 paper; TriAD: Capturing harmonics with 3D convolutions☆13Updated 3 months ago
- Code for running experiments in our ISMIR'21 paper titled: "Is Disentanglement enough? On Latent Representations for Controllable Music G …☆12Updated 3 years ago
- MuChoMusic is a benchmark for evaluating music understanding in multimodal audio-language models.☆23Updated 3 months ago