mulab-mir / muchomusic
MuChoMusic is a benchmark for evaluating music understanding in multimodal audio-language models.
☆23Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for muchomusic
- Code accompayning ISMIR23 paper; TriAD: Capturing harmonics with 3D convolutions☆13Updated 3 months ago
- MiRA (Music Replication Assessment) tool is a model-independent open evaluation method based on four diverse audio music similarity metri…☆23Updated 3 months ago
- Codes for ICASSP 2024 paper: BEAST: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer. An online beat tracking syste…☆32Updated last month
- Repository for ISMIR 2022 tutorial T3(M): Designing Controllable Synthesis System for Musical Signals☆28Updated last year
- Audio Prompt Adapter: Unleashing music editing abilities for text-to-music with lightweight finetuning [ISMIR 2024]☆34Updated last month
- ☆21Updated 2 years ago
- Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems☆32Updated 2 weeks ago
- This repository is for an implementation of the accepted paper "Sketching the Expression: Flexible Rendering of Expressive Piano Performa…☆20Updated last year
- The code repository for our paper "Interpreting Song Lyrics with a Music-Informed Pre-trained Language Model".☆22Updated last year
- ISMIR 24 Supplementary Material☆12Updated last week
- Using Word embeddings for automatic EQ mixing☆11Updated 2 years ago
- "Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks", ICASSP 2022 (Data Generation Pipeline)☆35Updated 2 years ago
- MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing [ISMIR 2024]☆37Updated 2 months ago
- music semantic understanding evaluation benchmark☆25Updated last year
- DExter: Learning and Controlling Performance Expression through Diffusion models☆16Updated 4 months ago
- list of MIR dataset papers presented at ISMIR 2022☆60Updated last year
- Supplementary code for the experiments described in the 2021 ISMIR submission: Leveraging Hierarchical Structures for Few Shot Musical In…☆40Updated 2 years ago
- Frechet Audio Distance evaluation in PyTorch☆35Updated last year
- ☆73Updated last year
- Supervised and unsupervised Concept-based explanation of pretrained music classifiers☆12Updated last year
- Project for MIDI to Audio Synthesis☆22Updated last year
- Official Implementation of Jointist☆32Updated last year
- A collection of metrics for evaluating timbre dissimilarity using the TorchMetrics API☆23Updated 2 years ago
- ☆27Updated 11 months ago
- Official implementation of "Learning Music Audio Representations Via Weak Language Supervision" (ICASSP 2022)☆46Updated 2 years ago
- MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage☆36Updated 3 months ago
- The ArtificialSongGenerator automatically composes and compiles the Artifical Audio Multitrack dataset (AAM).☆17Updated last year
- Polyphonic generalisation of DDSP☆16Updated 6 months ago
- A minimum JukeMIR branch for feature extraction.☆31Updated 2 years ago
- Source Separation training codebase for the Sound Demixing Challenge 2023.☆37Updated last year