Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands

TL;DR

This paper introduces a new Cantonese audio-visual dataset and challenge for in-car speech recognition, addressing the scarcity of resources for low-resource languages in automotive AI applications.

Contribution

It provides a novel Cantonese in-car audio-visual dataset and establishes a new benchmark challenge to promote research in low-resource speech recognition in automotive environments.

Findings

New Cantonese in-car audio-visual dataset released

Benchmark challenge established for low-resource speech recognition

Encourages development of speech recognition models for underrepresented languages

Abstract

With the rise of deep learning and intelligent vehicles, the smart assistant has become an essential in-car component to facilitate driving and provide extra functionalities. In-car smart assistants should be able to process general as well as car-related commands and perform corresponding actions, which eases driving and improves safety. However, in this research field, most datasets are in major languages, such as English and Chinese. There is a huge data scarcity issue for low-resource languages, hindering the development of research and applications for broader communities. Therefore, it is crucial to have more benchmarks to raise awareness and motivate the research in low-resource languages. To mitigate this problem, we collect a new dataset, namely Cantonese In-car Audio-Visual Speech Recognition (CI-AVSR), for in-car speech recognition in the Cantonese language with video and audio data. Together with it, we propose Cantonese Audio-Visual Speech Recognition for In-car Commands as a new challenge for the community to tackle low-resource speech recognition under in-car scenarios.