Language Agnostic Data-Driven Inverse Text Normalization
This addresses the scarcity of labeled data for non-English languages in speech recognition, though it is incremental as it builds on existing data-driven methods.
The paper tackles the inverse text normalization problem for converting spoken to written text in low-resource languages by proposing a language-agnostic data-driven framework using data augmentation and neural machine translation, showing effectiveness for low-resource languages while maintaining performance for high-resource ones.
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.