A Mamba-based Network for Semi-supervised Singing Melody Extraction Using Confidence Binary Regularization

TL;DR

This paper introduces SpectMamba, a semi-supervised singing melody extraction network that uses vision mamba for efficiency, a note-f0 decoder for musical accuracy, and confidence binary regularization to leverage unlabeled data, outperforming prior models.

Contribution

The paper presents a novel mamba-based network with a linear-complexity architecture, a note-f0 decoder, and a confidence regularization module for semi-supervised singing melody extraction.

Findings

Effective on multiple public datasets

Outperforms existing methods in accuracy and efficiency

Leverages unlabeled data successfully

Abstract

Singing melody extraction (SME) is a key task in the field of music information retrieval. However, existing methods are facing several limitations: firstly, prior models use transformers to capture the contextual dependencies, which requires quadratic computation resulting in low efficiency in the inference stage. Secondly, prior works typically rely on frequencysupervised methods to estimate the fundamental frequency (f0), which ignores that the musical performance is actually based on notes. Thirdly, transformers typically require large amounts of labeled data to achieve optimal performances, but the SME task lacks of sufficient annotated data. To address these issues, in this paper, we propose a mamba-based network, called SpectMamba, for semi-supervised singing melody extraction using confidence binary regularization. In particular, we begin by introducing vision mamba to achieve computational linear complexity. Then, we propose a novel note-f0 decoder that allows the model to better mimic the musical performance. Further, to alleviate the scarcity of the labeled data, we introduce a confidence binary regularization (CBR) module to leverage the unlabeled data by maximizing the probability of the correct classes. The proposed method is evaluated on several public datasets and the conducted experiments demonstrate the effectiveness of our proposed method.