Text Normalization for Indonesian Text-to-Speech (TTS) using Rule-Based Approach: A Dataset and Preliminary Study

Text-to-Speech (TTS) is a technology that is currently widely used for several purposes both for academic/ non-commercial and industry/commercial purposes. In several cases, some researchers on the TTS field adding a text normalization process for normalizing text that will be used for TTS input to enhance the TTS performance itself. In this paper, we present a rule-based approach to make an Indonesian text normalization dataset that has a raw text and a spoken form of it for enhancing Indonesian Text-to-Speech (TTS) performance. We conduct a set of rule-based for normalizing Indonesian text as an input for the TTS system. Using those rule-based, we generated a dataset and correct it manually so that we have a gold standard for text normalization for Indonesian TTS input. Our approach shows a rule-based can give a good performance for normalizing text for Indonesian TTS with 0.0805 of Word Error Rate (WER).