With the emergence of automatic speech recognition (ASR) models, converting the spoken form text (from ASR) to the written form is in urgent need. This inverse text normalization (ITN) problem attracts the attention of researchers from various fields. Recently, several works show that data-driven ITN methods can output high-quality written form text. Due to the scarcity of labeled spoken-written datasets, the studies on non-English data-driven ITN are quite limited. In this work, we propose a language-agnostic data-driven ITN framework to fill this gap. Specifically, we leverage the data augmentation in conjunction with neural machine translated data for low resource languages. Moreover, we design an evaluation method for language agnostic ITN model when only English data is available. Our empirical evaluation shows this language agnostic modeling approach is effective for low resource languages while preserving the performance for high resource languages.
翻译:随着自动语音识别(ASR)模式的出现,迫切需要将口头文字(从ASR)转换成书面形式。反正文本正常化(ITN)问题吸引了各领域研究人员的注意。最近,一些工作显示,数据驱动的ITN方法可以输出高质量的书面形式文本。由于标签的口写数据集稀缺,关于非英语数据驱动的ITN的研究非常有限。在这项工作中,我们提议了一个语言不可知数据驱动的ITN框架来填补这一空白。具体地说,我们利用数据增强与神经机翻译数据相结合,用于低资源语言。此外,我们设计了一种评价方法,在只有英语数据的情况下,对语言具有不可知的ITN模型模式进行语言评估。我们的经验评估显示,这种语言的不可知模型方法对低资源语言有效,同时保持高资源语言的性能。