作为黄金语音生成器的零样本文本转语音：一个系统化框架及其在自动发音评估中的适用性
Zero-Shot Text-to-Speech as Golden Speech Generator: A Systematic Framework and its Applicability in Automatic Pronunciation Assessment
AI总结：
提出利用ZS-TTS生成学习者专属黄金语音的系统化框架，并验证其在自动发音评估中可显著提升多项指标性能。
摘要：
第二语言（L2）学习者可以通过模仿黄金语音来改善发音，尤其是当这些语音与他们各自的语音特征相匹配时。本研究探讨了以下假设：利用零样本文本转语音（ZS-TTS）技术生成的、面向特定学习者的黄金语音，可作为衡量L2学习者发音熟练度的有效指标。基于这一探索，本研究的贡献至少有两方面：1）设计并开发了一个系统化框架，用于评估合成模型生成黄金语音的能力；2）深入考察了在自动发音评估（APA）中使用黄金语音的有效性。在L2-ARCTIC和Speechocean762基准数据集上进行的综合实验表明，相对于若干已有方法，我们提出的建模方法能够在多种评估指标上取得显著的性能提升。据我们所知，本研究首次探索了黄金语音在ZS-TTS和APA两者中的作用，为计算机辅助发音训练（CAPT）提供了一种有前景的机制。
英文摘要：
Second language (L2) learners can improve their pronunciation by imitating golden speech, especially when the speech that aligns with their respective speech characteristics. This study explores the hypothesis that learner-specific golden speech generated with zero-shot text-to-speech (ZS-TTS) techniques can be harnessed as an effective metric for measuring the pronunciation proficiency of L2 learners. Building on this exploration, the contributions of this study are at least two-fold: 1) design and development of a systematic framework for assessing the ability of a synthesis model to generate golden speech, and 2) in-depth investigations of the effectiveness of using golden speech in automatic pronunciation assessment (APA). Comprehensive experiments conducted on the L2-ARCTIC and Speechocean762 benchmark datasets suggest that our proposed modeling can yield significant performance improvements with respect to various assessment metrics in relation to some prior arts. To our knowledge, this study is the first to explore the role of golden speech in both ZS-TTS and APA, offering a promising regime for computer-assisted pronunciation training (CAPT).
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。
