CTC-TTS: 基于大语言模型的双流文本到语音系统与CTC对齐
CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment
AI总结：
CTC-TTS提出了一种基于大语言模型的双流文本到语音系统，采用CTC对齐器和双词交错策略，提升了流式合成和零样本任务的性能。
摘要：
基于大语言模型（LLM）的文本到语音（TTS）系统可以生成自然语音，但大多数系统并非为低延迟双流合成而设计。高质量的双流TTS依赖于准确的文本-语音对齐和精心设计的训练序列，这些序列需要在合成质量和延迟之间取得平衡。先前的工作往往依赖于基于GMM-HMM的强制对齐工具包（例如MFA），这些工具包流程繁琐且不如神经对齐器灵活；固定比例交错文本和语音标记的方法难以捕捉文本-语音对齐的规律性。我们提出了CTC-TTS，它用基于CTC的对齐器替代MFA，并引入了基于双词的交错策略。设计了两种变体：CTC-TTS-L（沿序列长度进行标记拼接）用于更高质量，CTC-TTS-F（沿特征维度进行嵌入堆叠）用于更低延迟。实验表明，CTC-TTS在流式合成和零样本任务上优于固定比例交错和基于MFA的基线。语音样本可在https://ctctts.github.io/上获取。
英文摘要：
Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-streaming synthesis. High-quality dual-streaming TTS depends on accurate text--speech alignment and well-designed training sequences that balance synthesis quality and latency. Prior work often relies on GMM-HMM based forced-alignment toolkits (e.g., MFA), which are pipeline-heavy and less flexible than neural aligners; fixed-ratio interleaving of text and speech tokens struggles to capture text--speech alignment regularities. We propose CTC-TTS, which replaces MFA with a CTC based aligner and introduces a bi-word based interleaving strategy. Two variants are designed: CTC-TTS-L (token concatenation along the sequence length) for higher quality and CTC-TTS-F (embedding stacking along the feature dimension) for lower latency. Experiments show that CTC-TTS outperforms fixed-ratio interleaving and MFA-based baselines on streaming synthesis and zero-shot tasks.
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。
