发表机构
Beijing Logic Intelligence Technology; University of Washington; Beijing University of Posts and Telecommunications; University of California, USA; Northwestern University, USA（北京逻辑智能科技有限公司; 华盛顿大学; 北京邮电大学; 加州大学; 西北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低资源TTS适配中伪标签噪声问题，提出信任感知渐进式适配，先合成后真实并利用双ASR一致性加权，在缅甸语和老挝语上提升内容准确性与说话人相似度。
AI 中文摘要
低资源文本到语音（TTS）适配受限于稀缺的配对数据和昂贵的人工转录。现有的固定语音TTS系统能提供相对准确的发音，但其合成语音的说话人多样性有限，且可能表现出平淡的韵律。真实录音提供自然的韵律和多样的声音，然而其自动语音识别（ASR）伪标签可能包含转录错误。我们发现监督顺序影响内容准确性和说话人相似度。我们提出信任感知渐进式适配：先进行合成到真实的适配以建立文本-语音对应关系，然后使用真实语音恢复参考说话人控制。转录一致性加权利用两个固定ASR系统之间的一致性作为伪标签可靠性的代理，以限制噪声监督。在FireRedTTS3上针对缅甸语和老挝语，以及在OmniVoice上针对缅甸语的实验表明，内容准确性得到提升，同时保持高自然度和有竞争力的说话人相似度。在结合合成和真实语音时，联合考虑监督顺序和伪标签可靠性，为低资源语言中的零样本声音克隆提供了一条实用路径，减少了人工转录的需求。音频演示可在该https URL获取。
英文摘要
Low-resource text-to-speech (TTS) adaptation is constrained by scarce paired data and costly manual transcription. Existing fixed-voice TTS systems can provide relatively accurate pronunciation, but their synthetic speech offers limited speaker diversity and may exhibit flat prosody. Real recordings provide natural prosody and diverse voices, yet their automatic speech recognition (ASR) pseudo-labels may contain transcription errors. We find that supervision order affects content accuracy and speaker similarity. We propose trust-aware progressive adaptation: synthetic-to-real adaptation first establishes text-speech correspondences, then restores reference-speaker control using real speech. Transcript-agreement weighting uses agreement between two fixed ASR systems as a proxy for pseudo-label reliability to limit noisy supervision. Experiments with FireRedTTS3 on Burmese and Lao and OmniVoice on Burmese show improved content accuracy with high naturalness and competitive speaker similarity. Jointly considering supervision order and pseudo-label reliability when combining synthetic and real speech offers a practical path to zero-shot voice cloning in low-resource languages with less manual transcription. Audio demos are available at https://insiderx-pro.github.io/S2R-Adaptation-TTS/
Comments5 pages, 2 figures, 3 tables. Jiayi Lu and Yizhong Geng contributed equally. Corresponding author: Ya Li
