# CN-CVS: A Mandarin Audio-Visual Dataset for Large Vocabulary Continuous Visual to Speech Synthesis

> Research article (ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023) · cited 22× · AI/ML

**Wikidata**: [openalex:W4375869161](https://www.wikidata.org/wiki/openalex:W4375869161)  
**Source**: https://4ort.xyz/entity/cn-cvs-a-mandarin-audio-visual-dataset-for-large-vocabulary-continuous-visual-to-speech-synthesis