Singing Voice Conversion with Accompaniment Using Self-Supervised Representation-Based Melody Features
This addresses a domain-specific problem for audio processing and music technology applications, offering an incremental improvement over previous methods by enhancing melody modeling in the presence of accompaniment.
The paper tackles the problem of singing voice conversion with background music, which often degrades performance due to audio distortion and interference in melody extraction, by introducing a method using self-supervised representation-based melody features. The result is a model that significantly outperforms baselines in melody accuracy, similarity, and naturalness in both noisy and clean audio environments.
Melody preservation is crucial in singing voice conversion (SVC). However, in many scenarios, audio is often accompanied with background music (BGM), which can cause audio distortion and interfere with the extraction of melody and other key features, significantly degrading SVC performance. Previous methods have attempted to address this by using more robust neural network-based melody extractors, but their performance drops sharply in the presence of complex accompaniment. Other approaches involve performing source separation before conversion, but this often introduces noticeable artifacts, leading to a significant drop in conversion quality and increasing the user's operational costs. To address these issues, we introduce a novel SVC method that uses self-supervised representation-based melody features to improve melody modeling accuracy in the presence of BGM. In our experiments, we compare the effectiveness of different self-supervised learning (SSL) models for melody extraction and explore for the first time how SSL benefits the task of melody extraction. The experimental results demonstrate that our proposed SVC model significantly outperforms existing baseline methods in terms of melody accuracy and shows higher similarity and naturalness in both subjective and objective evaluations across noisy and clean audio environments.