SDP-Codec：一种带有音高注入的说话人解耦语音编解码器，用于低比特率编码和零样本语音转换
SDP-Codec: A Speaker-Decoupled Speech Codec with Pitch Injection for Low-Bitrate Coding and Zero-Shot Voice Conversion
AI总结：
提出SDP-Codec，通过单阶段优化从预训练自监督编码器中提取局部令牌并注入归一化F0，实现说话人解耦，在低比特率下达到竞争性重构和强零样本语音转换，且说话人泄露最少。
摘要：
说话人解耦的语音编解码器通过将全局说话人属性与局部内容和韵律分离，可以降低比特率，同时支持语音转换。现有的说话人解耦编解码器面临权衡：显式抑制说话人泄露的方法通常依赖多阶段或辅助训练，而更简单的设计可能在局部令牌中残留说话人信息。我们提出了SDP-Codec，一种使用单阶段优化流水线训练的说话人解耦、音高注入编解码器。SDP-Codec从预训练自监督编码器的连续预量化特征中导出局部令牌，并通过带有全局条件去归一化和软标签音高重建目标的音高编码器-解码器注入归一化F0。在16 kHz和24 kHz设置下，SDP-Codec在可比比特率下实现了竞争性重建和强大的零样本语音转换，并且在比较系统中具有最低的说话人探测准确率，表明说话人泄露减少。
英文摘要：
Speaker-decoupled speech codecs can reduce bitrate by separating global speaker attributes from local content and prosody, while supporting voice conversion. Existing speaker-decoupled codecs face a trade-off: methods that explicitly suppress speaker leakage often rely on multi-stage or auxiliary training, whereas simpler designs can leave residual speaker information in local tokens. We propose SDP-Codec, a speaker-decoupled, pitch-injected codec trained with a single-stage optimization pipeline. SDP-Codec derives local tokens from continuous pre-quantization features of a pretrained self-supervised encoder and injects normalized F0 via a pitch encoder-decoder with global-conditioned denormalization and soft-label pitch reconstruction objective. Across 16 kHz and 24 kHz settings, SDP-Codec achieves competitive reconstruction and strong zero-shot voice conversion at comparable bitrates, with the lowest speaker-probing accuracy among compared systems, suggesting reduced speaker leakage.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
