paper-with-me

홈 › Papers

Towards Training Music Taggers on Synthetic Data

2024-07-02 · Nadine Kroher, Steven Manangu, Aggelos Pikrakis

Most contemporary music tagging systems rely on large volumes of annotated data. As an alternative, we investigate the extent to which synthetically generated music excerpts can improve tagging systems when only small annotated collections are available. To this end, we release GTZAN-synth, a synthetic dataset that follows the taxonomy of the well-known GTZAN dataset while being ten times larger in data volume. We first observe that simply adding this synthetic dataset to the training split of GTZAN does not result into performance improvements. We then proceed to investigating domain adaptation, transfer learning and fine-tuning strategies for the task at hand and draw the conclusion that the last two options yield an increase in accuracy. Overall, the proposed approach can be considered as a first guide in a promising field for future research.

📄 PDF Abstract BibTeX arXiv:2407.02156

Code (1)

nadinekroher/music-tagging-synthetic-data-cbmi-2024 공식 구현 tf

Tasks

Domain AdaptationMusic TaggingTransfer Learning

Similar Papers 제목 키워드 기반

Exploiting Device and Audio Data to Tag Music with User-Aware Listening Contexts

2022-11-14 · Karim M. Ibrahim, Elena V. Epure, Geoffroy Peeters, Gaël Richard

As music has become more available especially on music streaming platforms, people have started to have distinct preferences to fit to their varying listening situations, also known as context. Hence, there has been a gr…

RetrievalTAG

musicnn: Pre-trained convolutional neural networks for music audio tagging

2019-09-14 · Jordi Pons, Xavier Serra

Pronounced as "musician", the musicnn library contains a set of pre-trained musically motivated convolutional neural networks for music audio tagging: https://github.com/jordipons/musicnn. This repository also includes s…

Audio TaggingTransfer Learning

Unsupervised Source Separation By Steering Pretrained Music Models

2021-10-25 · Ethan Manilow, Patrick O'Reilly, Prem Seetharaman, Bryan Pardo

We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining. An audio generation model is conditioned on an input mixt…

Audio GenerationAudio Source SeparationMusic GenerationMusic Tagging+1

MuScriptor: An Open Model for Multi-Instrument Music Transcription

2026-07-09 · Simon Rouard, Michael Krause, Axel Roebel, Carl-Johann Simon-Gabriel 외 arxiv

Existing methods for automatic music transcription are often limited to single-instrument recordings or fail on complex, real music mixes. Although previous work utilizes synthetic training data, the resulting models gen…

Multi-instrument Music TranscriptionReinforcement Learning

Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning

2025-09-04 · Zhilin Wang, Zhe Yang, Yun Luo, Yafu Li 외 arxiv

Enhancing the ability of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) to interpret sheet music is a crucial step toward building AI musicians. However, current research lacks both evaluation …