CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition
This work addresses the problem of developing in-car smart assistants for Cantonese speakers, but it is incremental as it primarily provides a new dataset for a specific domain.
The authors tackled the data scarcity issue for low-resource languages in in-car command recognition by introducing the CI-AVSR dataset, which includes 4,984 samples (8.3 hours) of Cantonese audio-visual speech and an augmented version 10 times larger, and they demonstrated that leveraging visual signals improves model performance, though recognition on noisy data remains challenging.
With the rise of deep learning and intelligent vehicle, 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, there is a data scarcity issue for low resource languages, hindering the development of research and applications. In this paper, we introduce a new dataset, Cantonese In-car Audio-Visual Speech Recognition (CI-AVSR), for in-car command recognition in the Cantonese language with both video and audio data. It consists of 4,984 samples (8.3 hours) of 200 in-car commands recorded by 30 native Cantonese speakers. Furthermore, we augment our dataset using common in-car background noises to simulate real environments, producing a dataset 10 times larger than the collected one. We provide detailed statistics of both the clean and the augmented versions of our dataset. Moreover, we implement two multimodal baselines to demonstrate the validity of CI-AVSR. Experiment results show that leveraging the visual signal improves the overall performance of the model. Although our best model can achieve a considerable quality on the clean test set, the speech recognition quality on the noisy data is still inferior and remains as an extremely challenging task for real in-car speech recognition systems. The dataset and code will be released at https://github.com/HLTCHKUST/CI-AVSR.