MAJL: A Model-Agnostic Joint Learning Framework for Music Source Separation and Pitch Estimation

TL;DR

The paper introduces MAJL, a flexible joint learning framework for music source separation and pitch estimation that overcomes data scarcity and optimization challenges, achieving state-of-the-art results.

Contribution

It proposes a model-agnostic, two-stage training framework with dynamic weighting to enhance joint learning in music information retrieval tasks.

Findings

MAJL outperforms existing methods with 0.92 SDR improvement.

MAJL achieves 2.71% higher Raw Pitch Accuracy.

The framework demonstrates strong adaptability across different models.

Abstract

Music source separation and pitch estimation are two vital tasks in music information retrieval. Typically, the input of pitch estimation is obtained from the output of music source separation. Therefore, existing methods have tried to perform these two tasks simultaneously, so as to leverage the mutually beneficial relationship between both tasks. However, these methods still face two critical challenges that limit the improvement of both tasks: the lack of labeled data and joint learning optimization. To address these challenges, we propose a Model-Agnostic Joint Learning (MAJL) framework for both tasks. MAJL is a generic framework and can use variant models for each task. It includes a two-stage training method and a dynamic weighting method named Dynamic Weights on Hard Samples (DWHS), which addresses the lack of labeled data and joint learning optimization, respectively. Experimental results on public music datasets show that MAJL outperforms state-of-the-art methods on both tasks, with significant improvements of 0.92 in Signal-to-Distortion Ratio (SDR) for music source separation and 2.71% in Raw Pitch Accuracy (RPA) for pitch estimation. Furthermore, comprehensive studies not only validate the effectiveness of each component of MAJL, but also indicate the great generality of MAJL in adapting to different model architectures.