Summary of Visper: Multilingual Audio-visual Speech Recognition, by Sanath Narayan et al.
ViSpeR: Multilingual Audio-Visual Speech Recognition
by Sanath Narayan, Yasser Abdelaziz Dahou Djilali, Ankit Singh, Eustache Le Bihan, Hakim Hacid
First submitted to arxiv on: 27 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed study explores Audio-Visual Speech Recognition (AVSR) for five prominent languages: Chinese, Spanish, English, Arabic, and French. The researchers have compiled large datasets for each language except English and employed supervised learning models. Their model, ViSpeR, is trained in a multilingual setting, achieving competitive performance on newly established benchmarks for each language. To facilitate further research, the datasets and models are released to the community. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Audio-Visual Speech Recognition (AVSR) helps machines recognize speech from videos. This study looks at AVSR for five languages: Chinese, Spanish, English, Arabic, and French. The researchers made big datasets for each language, except English, and used those to train computer models. They tested their model, called ViSpeR, on new benchmarks for each language. Now, they’re sharing the data and code with others so more research can be done. |
Keywords
* Artificial intelligence * Supervised
