Toward Leveraging Pre-Trained Self-Supervised Frontends for Automatic Singing Voice Understanding Tasks: Three Case Studies

TL;DR

This paper explores the use of self-supervised learning models as pre-trained frontends for singing voice understanding tasks, demonstrating their effectiveness across multiple tasks with limited labeled data and providing insights through layer-wise analysis.

Contribution

It investigates the application of SSL models for singing voice tasks, showing they can match or outperform state-of-the-art methods and offering a layer-wise analysis of model behavior.

Findings

SSL models achieve comparable or better performance than state-of-the-art methods.

Layer-wise analysis provides insights into SSL model behavior in singing tasks.

SSL models are effective even with limited labeled data.

Abstract

Automatic singing voice understanding tasks, such as singer identification, singing voice transcription, and singing technique classification, benefit from data-driven approaches that utilize deep learning techniques. These approaches work well even under the rich diversity of vocal and noisy samples owing to their representation ability. However, the limited availability of labeled data remains a significant obstacle to achieving satisfactory performance. In recent years, self-supervised learning models (SSL models) have been trained using large amounts of unlabeled data in the field of speech processing and music classification. By fine-tuning these models for the target tasks, comparable performance to conventional supervised learning can be achieved with limited training data. Therefore, in this paper, we investigate the effectiveness of SSL models for various singing voice recognition tasks. We report the results of experiments comparing SSL models for three different tasks (i.e., singer identification, singing voice transcription, and singing technique classification) as initial exploration and aim to discuss these findings. Experimental results show that each SSL model achieves comparable performance and sometimes outperforms compared to state-of-the-art methods on each task. We also conducted a layer-wise analysis to further understand the behavior of the SSL models.