# Audio-Visual Speech Recognition is Worth $32\times 32\times 8$ Voxels

> Research article (2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2021) · cited 31× · AI/ML

**Wikidata**: [openalex:W3199527474](https://www.wikidata.org/wiki/openalex:W3199527474)  
**Source**: https://4ort.xyz/entity/audio-visual-speech-recognition-is-worth-32-times-32-times-8-voxels
