AI RESEARCH
Cascade-Free Mandarin Visual Speech Recognition via Semantic-Guided Cross-Representation Alignment
arXiv CS.CV
•
ArXi:2603.21808v1 Announce Type: new Chinese mandarin visual speech recognition (VSR) is a task that has advanced in recent years, yet still lags behind the performance on non-tonal languages such as English. One primary challenge arises from the tonal nature of Mandarin, which limits the effectiveness of conventional sequence-to-sequence modeling approaches. To alleviate this issue, existing Chinese VSR systems commonly incorporate intermediate representations, most notably pinyin, within cascade architectures to enhance recognition accuracy.