2 papers
cs.CV2023
BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation
Liyan Kang, Luyang Huang, Ningxin Peng +6
We present a large-scale video subtitle translation dataset, BigVideo, to facilitate the study of multi-modality machine translation. Compared with the widely used How2 and VaTeX d…
eess.AS2023
Visual Information Matters for ASR Error Correction
Vanya Bannihatti Kumar, Shanbo Cheng, Ningxin Peng +1
Aiming to improve the Automatic Speech Recognition (ASR) outputs with a post-processing step, ASR error correction (EC) techniques have been widely developed due to their efficienc…