基于流匹配的语音合成模型，提升对齐精度并加速推理。
ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inference
- 用自监督语义对齐器增强文本与语音的时序一致性。
- 通过复用编码器特征，推理速度大幅提升，零性能损失。
- 适合追求高效高质语音合成的开发者和研究者。
尽管基于扩散的非自回归语音合成系统展现出出色的零样本合成能力，但仍面临两大挑战：文本与语音对齐建模困难，以及迭代去噪过程计算开销高。为此，我们提出ARCHI-TTS，其配备专用语义对齐器，确保文本与音频在时序和语义上的一致性。为降低推理计算成本，ARCHI-TTS采用高效的推理策略，复用编码器特征于多个去噪步骤中，显著加速合成且不损失性能。此外，在条件编码器上引入辅助的CTC损失，进一步增强语义理解。实验结果表明，ARCHI-TTS在LibriSpeech-PC测试集上的词错误率（WER）为1.98%，在SeedTTS测试集（英语/中文）上分别为1.47%和1.42%，兼具高推理效率，持续优于近期最先进语音合成系统。
原文摘要 · Abstract (English)
Although diffusion-based, non-autoregressive text-to-speech (TTS) systems have demonstrated impressive zero-shot synthesis capabilities, their efficacy is still hindered by two key challenges: the difficulty of text-speech alignment modeling and the high computational overhead of the iterative denoising process. To address these limitations, we propose ARCHI-TTS that features a dedicated semantic aligner to ensure robust temporal and semantic consistency between text and audio. To overcome high computational inference costs, ARCHI-TTS employs an efficient inference strategy that reuses encoder features across denoising steps, drastically accelerating synthesis without performance degradation. An auxiliary CTC loss applied to the condition encoder further enhances the semantic understanding. Experimental results demonstrate that ARCHI-TTS achieves a WER of 1.98% on LibriSpeech-PC test-clean, and 1.47%/1.42% on SeedTTS test-en/test-zh with a high inference efficiency, consistently outperforming recent state-of-the-art TTS systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。