Towards Training Music Taggers on Synthetic Data
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.
Code (1)
Tasks
Domain AdaptationMusic TaggingTransfer LearningSimilar Papers 제목 키워드 기반
Exploiting Device and Audio Data to Tag Music with User-Aware Listening Contexts
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…
RetrievalTAGmusicnn: Pre-trained convolutional neural networks for music audio tagging
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 LearningUnsupervised Source Separation By Steering Pretrained Music Models
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+1MuScriptor: An Open Model for Multi-Instrument Music Transcription
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 LearningTowards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning
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 …