Do Foundational Audio Encoders Understand Music Structure?
This addresses a gap in music information retrieval for researchers by identifying key factors influencing MSA performance, though it is incremental as it builds on existing FAE trends.
The study tackled the underexplored use of pretrained foundational audio encoders (FAEs) for music structure analysis (MSA) by conducting comprehensive experiments on 11 FAE types, finding that self-supervised learning with masked language modeling on music data is particularly effective for MSA.
In music information retrieval (MIR) research, the use of pretrained foundational audio encoders (FAEs) has recently become a trend. FAEs pretrained on large amounts of music and audio data have been shown to improve performance on MIR tasks such as music tagging and automatic music transcription. However, their use for music structure analysis (MSA) remains underexplored: only a small subset of FAEs has been examined for MSA, and the impact of factors such as learning methods, training data, and model context length on MSA performance remains unclear. In this study, we conduct comprehensive experiments on 11 types of FAEs to investigate how these factors affect MSA performance. Our results demonstrate that FAEs using self-supervised learning with masked language modeling on music data are particularly effective for MSA. These findings pave the way for future research in FAE and MSA.