StreamTN：面向对话系统中流式TTS的低延迟中文文本规范化模型
StreamTN: A Low-Latency Streaming Chinese Text Normalization Model for Streaming TTS in Dialogue Systems
- Northwestern Polytechnical University（西北工业大学）
- Shenzhen Pimei Technology Co., Ltd.（深圳皮米科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
StreamTN是一种基于Qwen3-0.6B的双轨流式中文文本规范化模型，通过任务微调实现低延迟、高准确率，并引入新基准评估，适用于对话系统TTS。
AI中文摘要：
文本到语音（TTS）是以大型语言模型（LLM）为中心的语音对话系统（SDS）中提供语音响应的关键模块。为确保TTS合成的准确性，LLM生成的响应必须通过文本规范化（TN）模块转换为TTS可读格式，这在实时SDS场景中对低延迟提出了严格要求。现有的TN解决方案主要基于规则，依赖人工工程，且对未见模式泛化能力差。尽管LLM本身可以通过提示工程执行TN，但它面临关键限制：由于非流式处理导致的高首令牌延迟、幻觉风险，以及当核心LLM模块仅针对TN进行微调时智能或推理能力下降。为解决这些挑战，我们提出了StreamTN，一种基于LLM的轻量级中文流式TN模型。StreamTN基于Qwen3-0.6B构建，采用双轨流式框架，其中输入令牌和输出令牌在两条并行轨道上处理，无需复杂提示即可实现低延迟实时推理。此外，任务特定的微调相比基于规则的系统和大规模通用LLM，带来了更优的TN性能和更少的幻觉。我们还引入了一个涵盖多种文本场景的TN基准，为语音对话系统中的语音生成提供了全面的评估标准。实验证明了StreamTN在准确性和推理延迟方面的有效性。
英文摘要：
Text-to-Speech (TTS) is an essential module that provides spoken responses in a spoken dialogue system (SDS) centered on a large language model (LLM). To ensure accurate TTS synthesis, responses generated by an LLM must be converted into TTS-readable formats via a Text Normalization (TN) module, imposing strict low-latency requirements in real-time SDS scenarios. Existing TN solutions are largely rule-based, rely on manual engineering, and generalize poorly to unseen patterns. Although an LLM itself can perform TN through prompt engineering, it faces key limitations: high first-token latency due to non-streaming processing, hallucination risks, and degraded intelligence or reasoning when the core LLM module is fine-tuned solely for TN. To address these challenges, we propose StreamTN, a lightweight LLM-based Chinese streaming TN model. Built on Qwen3-0.6B, StreamTN employs a dual-track streaming framework in which input tokens and output tokens are processed on two parallel tracks, enabling low-latency real-time inference without complex prompting. Moreover, task-specific fine-tuning yields superior TN performance and fewer hallucinations than rule-based systems and general-purpose LLMs. We also introduce a TN benchmark that spans diverse text scenarios, providing a comprehensive evaluation standard for speech generation in spoken dialogue systems. Experiments demonstrate the effectiveness of StreamTN in accuracy and inference latency.
