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.

Registration link - https://forms.gle/85rvE9CAyL8UtXHr5

Challenge Timeline

• Registration opens - 27 May 2023

• Dataset (train+dev) sharing - 27 May 2023

• Baselines release - 28 May 2023

• Dataset (test) sharing- 28 June 2023

• Challenge Submission opens - 30 June 2023

• Paper submission deadline -   03 July 2023  10 July 2023

• Final challenge submission deadline -  5 July 2023 10 July 2023

• Challenge acceptance results - 07 July 2023 12 July 2023

• Paper revision deadline -   10 July 2023  17 July 2023

• Note: Anywhere on Earth (AoE) time is used for deadlines