[
    {
        "id": "osp-20053",
        "type": "article-journal",
        "title": "MeanVoiceFlow2: Joint Optimization of Mean Flow and Content Encoder for Fast One-Step Zero-Shot Voice Conversion",
        "author": [
            {
                "family": "Kaneko",
                "given": "Takuhiro"
            },
            {
                "family": "Kameoka",
                "given": "Hirokazu"
            },
            {
                "family": "Tanaka",
                "given": "Kou"
            },
            {
                "family": "Kondo",
                "given": "Yuto"
            }
        ],
        "URL": "https://omanscience.com/en/articles/meanvoiceflow2-joint-optimization-of-mean-flow-and-content-encoder-for-fast-one-step-zero-shot-voice-conversion",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Flow-matching approaches to voice conversion (VC) have gained attention owing to their high speech quality and strong speaker similarity. Among them, one-step models such as MeanVoiceFlow are particularly attractive because they enable efficient inference; however, their reliance on a computationally intensive content encoder remains a bottleneck. We therefore propose MeanVoiceFlow2, a framework that jointly optimizes a flow-based conversion module and a computationally efficient content encoder. The model is trained through conversion distillation using MeanVoiceFlow and the reconstruction of real data. We further incorporate diffusion-GAN training with sample mixing and teacher-guided conditioning augmentation to enhance realism and disentanglement. Experiments on zero-shot VC showed that MeanVoiceFlow2 achieved higher perceptual quality and approximately $9\\times$ faster inference than MeanVoiceFlow while maintaining comparable speaker similarity. Audio samples are available at https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/meanvoiceflow2/."
    }
]