Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.15066 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909586433245184 |
|---|---|
| author | Zhao, Jinghua Jia, Yuhang Wang, Shiyao Zhou, Jiaming Wang, Hui Qin, Yong |
| author_facet | Zhao, Jinghua Jia, Yuhang Wang, Shiyao Zhou, Jiaming Wang, Hui Qin, Yong |
| contents | Incorporating visual modalities to assist Automatic Speech Recognition (ASR) tasks has led to significant improvements. However, existing Audio-Visual Speech Recognition (AVSR) datasets and methods typically rely solely on lip-reading information or speaking contextual video, neglecting the potential of combining these different valuable visual cues within the speaking context. In this paper, we release a multimodal Chinese AVSR dataset, Chinese-LiPS, comprising 100 hours of speech, video, and corresponding manual transcription, with the visual modality encompassing both lip-reading information and the presentation slides used by the speaker. Based on Chinese-LiPS, we develop a simple yet effective pipeline, LiPS-AVSR, which leverages both lip-reading and presentation slide information as visual modalities for AVSR tasks. Experiments show that lip-reading and presentation slide information improve ASR performance by approximately 8\% and 25\%, respectively, with a combined performance improvement of about 35\%. The dataset is available at https://kiri0824.github.io/Chinese-LiPS/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15066 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides Zhao, Jinghua Jia, Yuhang Wang, Shiyao Zhou, Jiaming Wang, Hui Qin, Yong Multimedia Artificial Intelligence Incorporating visual modalities to assist Automatic Speech Recognition (ASR) tasks has led to significant improvements. However, existing Audio-Visual Speech Recognition (AVSR) datasets and methods typically rely solely on lip-reading information or speaking contextual video, neglecting the potential of combining these different valuable visual cues within the speaking context. In this paper, we release a multimodal Chinese AVSR dataset, Chinese-LiPS, comprising 100 hours of speech, video, and corresponding manual transcription, with the visual modality encompassing both lip-reading information and the presentation slides used by the speaker. Based on Chinese-LiPS, we develop a simple yet effective pipeline, LiPS-AVSR, which leverages both lip-reading and presentation slide information as visual modalities for AVSR tasks. Experiments show that lip-reading and presentation slide information improve ASR performance by approximately 8\% and 25\%, respectively, with a combined performance improvement of about 35\%. The dataset is available at https://kiri0824.github.io/Chinese-LiPS/ |
| title | Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides |
| topic | Multimedia Artificial Intelligence |
| url | https://arxiv.org/abs/2504.15066 |