Robustness is critical in zero-shot singing voice conversion (SVC). This paper introduces two novel methods to strengthen the robustness of the kNN-VC framework for SVC. First, kNN-VC's core representation, WavLM, lacks harmonic emphasis, resulting in dull sounds and ringing artifacts. To address this, we leverage the bijection between WavLM, pitch contours, and spectrograms to perform additive synthesis, integrating the resulting waveform into the model to mitigate these issues. Second, kNN-VC overlooks concatenative smoothness, a key perceptual factor in SVC. To enhance smoothness, we propose a new distance metric that filters out unsuitable kNN candidates and optimize the summing weights of the candidates during inference. Although our techniques are built on the kNN-VC framework for implementation convenience, they are broadly applicable to general concatenative neural synthesis models. Experimental results validate the effectiveness of these modifications in achieving robust SVC. Demo:this http URLCode:this https URL
View on arXiv@article{shao2025_2504.05686,
title={ kNN-SVC: Robust Zero-Shot Singing Voice Conversion with Additive Synthesis and Concatenation Smoothness Optimization },
author={ Keren Shao and Ke Chen and Matthew Baas and Shlomo Dubnov },
journal={arXiv preprint arXiv:2504.05686},
year={ 2025 }
}