mulab-mir / muchomusicLinks
MuChoMusic is a benchmark for evaluating music understanding in multimodal audio-language models.
☆40Updated 10 months ago
Alternatives and similar repositories for muchomusic
Users that are interested in muchomusic are comparing it to the libraries listed below
Sorting:
- A piano music dataset with Audio, Symbolic and Text labels☆33Updated 7 months ago
- Official implementation of "Learning Music Audio Representations Via Weak Language Supervision" (ICASSP 2022)☆47Updated 10 months ago
- Repository for ISMIR 2022 tutorial T3(M): Designing Controllable Synthesis System for Musical Signals☆28Updated 2 years ago
- "Enhancing Neural Audio Fingerprint Robustness to Audio Degradation for Music Identification" ISMIR2025☆27Updated last month
- ☆30Updated 2 years ago
- Codes for ICASSP 2024 paper: BEAST: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer. An online beat tracking syste…☆39Updated last year
- JEPAs for audio representation learning☆16Updated 4 months ago
- Frechet Audio Distance evaluation in PyTorch☆35Updated 2 years ago
- Repository for the paper "Combining audio control and style transfer using latent diffusion", accepted at ISMIR 2024☆54Updated 8 months ago
- The official implementation of TokenSynth (ICASSP 2025)☆75Updated 5 months ago
- Official Implementation of Jointist☆37Updated 2 years ago
- ☆85Updated 2 years ago
- MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing [ISMIR 2024]☆45Updated 9 months ago
- Audio production style transfer with inference-time optimization☆45Updated 11 months ago
- Using Word embeddings for automatic EQ mixing☆13Updated 3 years ago
- Polyphonic generalisation of DDSP☆22Updated last year
- ☆12Updated 2 years ago
- Supplementary code for the experiments described in the 2021 ISMIR submission: Leveraging Hierarchical Structures for Few Shot Musical In…☆41Updated 3 years ago
- list of MIR dataset papers presented at ISMIR 2022☆61Updated 2 years ago
- The ArtificialSongGenerator automatically composes and compiles the Artifical Audio Multitrack dataset (AAM).☆22Updated 8 months ago
- Code for the paper "Toward Fully Self-Supervised Multi-Pitch Estimation".☆23Updated last month
- JamendoMaxCaps is a large-scale dataset of 362,000 instrumental creative commons tracks☆44Updated 5 months ago
- Training, validation, and inference code for various SSL approaches and architectures.☆67Updated this week
- ☆64Updated 2 weeks ago
- The code repository for our paper "Interpreting Song Lyrics with a Music-Informed Pre-trained Language Model".☆24Updated 2 years ago
- A standardized toolkit of Kernel Audio Distance (KAD)—a distribution-free, unbiased, and computationally efficient metric for evaluating …☆88Updated 4 months ago
- MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage☆48Updated 4 months ago
- Encode and decode audio samples to/from continuous and discrete compressed representations!☆70Updated last month
- A repo that builds text to music datasets from scratch, used in MuseContorlLite [ICML2025]☆26Updated 5 months ago
- Estimating musical surprisal/information content in Audio☆20Updated 3 weeks ago