论文标题
基于规则引导的平晶变压器的端到端中国文本归一化模型
An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer
论文作者
论文摘要
文本归一化定义为将非标准单词转换为口语单词的过程，对于文本到语音系统中合成语音的清晰度至关重要。基于规则的方法而不考虑上下文无法消除歧义，而基于序列到序列神经网络的方法却遭受了意外和无法解释的错误问题。最近提出的混合系统将基于规则的模型和神经模型视为两个级联的子模型，其中有限的相互作用能力使神经网络模型无法完全利用规则中包含的专家知识。受平面变压器（FLAT）的启发，我们提出了一个端到端的中文文本归一化模型，该模型接受汉字直接输入，并将规则中包含的专家知识集成到神经网络中，两者都为文本归一任务的拟议模型提供了出色的性能。我们还发布了第一个公开访问的LargesCale数据集，以实现中文文本归一化。我们提出的模型在此数据集上取得了出色的结果。
Text normalization, defined as a procedure transforming non standard words to spoken-form words, is crucial to the intelligibility of synthesized speech in text-to-speech system. Rule-based methods without considering context can not eliminate ambiguation, whereas sequence-to-sequence neural network based methods suffer from the unexpected and uninterpretable errors problem. Recently proposed hybrid system treats rule-based model and neural model as two cascaded sub-modules, where limited interaction capability makes neural network model cannot fully utilize expert knowledge contained in the rules. Inspired by Flat-LAttice Transformer (FLAT), we propose an end-to-end Chinese text normalization model, which accepts Chinese characters as direct input and integrates expert knowledge contained in rules into the neural network, both contribute to the superior performance of proposed model for the text normalization task. We also release a first publicly accessible largescale dataset for Chinese text normalization. Our proposed model has achieved excellent results on this dataset.
