超越统一模型：面向服务的低延迟、上下文感知音素转换方案在实时TTS中的实现

摘要

轻量级实时文本转语音系统对于信息无障碍至关重要。然而最高效的TTS模型通常依赖轻量级音素转换器，这些转换器难以应对上下文相关的挑战。相比之下，具有更深层语言理解能力的先进音素转换器往往需要高昂的计算成本，从而无法实现实时性能。本文研究了G2P辅助TTS系统中音素转换质量与推理速度之间的权衡，提出了一种弥合这一差距的实用框架。我们针对上下文感知音素转换提出轻量化策略，并构建面向服务的TTS架构，将这些模块作为独立服务运行。该设计将重度的上下文感知组件与核心TTS引擎解耦，有效突破延迟瓶颈，使高质量音素转换模型能够实现实时应用。实验结果表明，所提出的系统在保持实时响应能力的同时，显著提升了发音准确性与语言规范性，特别适用于离线及终端设备的TTS应用场景。

English

Lightweight, real-time text-to-speech systems are crucial for accessibility. However, the most efficient TTS models often rely on lightweight phonemizers that struggle with context-dependent challenges. In contrast, more advanced phonemizers with a deeper linguistic understanding typically incur high computational costs, which prevents real-time performance. This paper examines the trade-off between phonemization quality and inference speed in G2P-aided TTS systems, introducing a practical framework to bridge this gap. We propose lightweight strategies for context-aware phonemization and a service-oriented TTS architecture that executes these modules as independent services. This design decouples heavy context-aware components from the core TTS engine, effectively breaking the latency barrier and enabling real-time use of high-quality phonemization models. Experimental results confirm that the proposed system improves pronunciation soundness and linguistic accuracy while maintaining real-time responsiveness, making it well-suited for offline and end-device TTS applications.

超越统一模型：面向服务的低延迟、上下文感知音素转换方案在实时TTS中的实现

Beyond Unified Models: A Service-Oriented Approach to Low Latency, Context Aware Phonemization for Real Time TTS

摘要

Support