Most Chinese Grapheme-to-Phoneme (G2P) systems employ a three-stage framework that first transforms input sequences into character embeddings, obtains linguistic information using language models, and then predicts the phonemes based on global context about the entire input sequence. However, linguistic knowledge alone is often inadequate. Language models frequently encode overly general structures of a sentence and fail to cover specific cases needed to use phonetic knowledge. Also, a handcrafted post-processing system is needed to address the problems relevant to the tone of the characters. However, the system exhibits inconsistency in the segmentation of word boundaries which consequently degrades the performance of the G2P system. To address these issues, we propose the Reinforcer that provides strong inductive bias for language models by emphasizing the phonological information between neighboring characters to help disambiguate pronunciations. Experimental results show that the Reinforcer boosts the cutting-edge architectures by a large margin. We also combine the Reinforcer with a large-scale pre-trained model and demonstrate the validity of using neighboring context in knowledge transfer scenarios.

翻译：大多数中文形音转换（Grapheme-to-Phoneme, G2P）系统采用三阶段框架：首先将输入序列转换为字符嵌入，利用语言模型获取语言信息，然后基于整个输入序列的全局上下文预测音素。然而，单纯的语言知识往往不足。语言模型通常编码过于通用的句子结构，难以覆盖使用语音知识所需的特定情况。此外，还需要手工设计的后处理系统来解决与字符声调相关的问题。但此类系统在词边界分割上存在不一致性，从而降低了G2P系统的性能。为解决这些问题，我们提出了强化器（Reinforcer），通过强调相邻字符之间的语音信息为语言模型提供强归纳偏置，以帮助消解发音歧义。实验结果表明，强化器大幅提升了前沿架构的性能。我们还将其与大规模预训练模型结合，验证了在知识迁移场景中利用相邻上下文的有效性。