发表机构
Shenzhen Loop Area Institute; The Chinese University of Hong Kong, Shenzhen（深圳河套学院; 香港中文大学（深圳））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究探讨流匹配TTS中通过循环组织Transformer深度的方法，比较七种权重共享布局，发现共享顺序和位置影响合成质量，需根据采样预算选择布局。
AI 中文摘要
我们研究了如何在流匹配文本到语音中通过循环来组织Transformer深度，改变权重共享的数量、顺序和位置。在共同的训练目标和采样器下，七种布局在每次网络评估中执行18次块调用。在Seed-TTS和LibriSpeech-PC上，SEQUENCE将九个块中的每一个连续应用两次，在32步采样时保持了具有竞争力的可懂度、说话人相似性和预测语音质量，同时参数比未共享基线减少47.1%。将六个块循环三次进一步减小了模型大小，但相对于将九个块循环两次，32步词错误率有所提高。在匹配的参数数量和执行深度下，共享顺序和共享位置产生了不同的质量权衡。这些比较依赖于采样预算：Prefix和Suffix在32步时具有相似的词错误率，但在两个数据集上四步时，Suffix分别差3.44和5.97个百分点。只有Middle在两个数据集的32步和四步平均词错误率上排名第一或第二。这些结果表明，循环计算的组织影响合成质量，并且应根据采样预算和感兴趣的质量维度来选择共享布局。
英文摘要
We study how to organize Transformer depth through recurrence in flow-matching text-to-speech, varying the amount, order, and place?ment of weight reuse. Seven layouts perform 18 block calls per network evaluation under a common training objective and sam?pler. On Seed-TTS and LibriSpeech-PC, SEQUENCE applies each of nine blocks twice consecutively, retaining competitive intelligibil?ity, speaker similarity, and predicted speech quality at 32 sampling steps with 47.1% fewer parameters than the unshared baseline. Cy?cling six blocks three times further reduces model size but raises 32-step word error rates relative to cycling nine blocks twice. At matched parameter counts and executed depth, reuse order and shar?ing position produce different quality trade-offs. These comparisons depend on sampling budget: Prefix and Suffix have similar 32-step word error rates, but Suffix is worse by 3.44 and 5.97 percentage points at four steps on the two datasets, respectively. Only Middle ranks first or second in mean word error rate at 32 and four steps on both datasets. These results show that the organization of recurrent computation affects synthesis quality, and that reuse layouts should be selected for both the sampling budget and the quality dimensions of interest.
