Model Adaptation for ASR in low-resource Indian Languages

TL;DR

This paper explores adaptation techniques for improving automatic speech recognition in low-resource Indian languages by leveraging similarities among languages and modalities, with experiments on Bengali and Bhojpuri.

Contribution

It investigates the relative importance of acoustic and textual data in low-resource language ASR and proposes adaptation strategies utilizing related languages and shared features.

Findings

Shared linguistic features aid in model adaptation.

Acoustic data can compensate for limited text resources.

Methodology applicable to other low-resource languages.

Abstract

Automatic speech recognition (ASR) performance has improved drastically in recent years, mainly enabled by self-supervised learning (SSL) based acoustic models such as wav2vec2 and large-scale multi-lingual training like Whisper. A huge challenge still exists for low-resource languages where the availability of both audio and text is limited. This is further complicated by the presence of multiple dialects like in Indian languages. However, many Indian languages can be grouped into the same families and share the same script and grammatical structure. This is where a lot of adaptation and fine-tuning techniques can be applied to overcome the low-resource nature of the data by utilising well-resourced similar languages. In such scenarios, it is important to understand the extent to which each modality, like acoustics and text, is important in building a reliable ASR. It could be the case that an abundance of acoustic data in a language reduces the need for large text-only corpora. Or, due to the availability of various pretrained acoustic models, the vice-versa could also be true. In this proposed special session, we encourage the community to explore these ideas with the data in two low-resource Indian languages of Bengali and Bhojpuri. These approaches are not limited to Indian languages, the solutions are potentially applicable to various languages spoken around the world.