# Face2Speech: Towards Multi-Speaker Text-to-Speech Synthesis Using an Embedding Vector Predicted from a Face Image

> Research article (Interspeech 2020, 2020) · cited 28× · AI/ML

**Wikidata**: [openalex:W3096806995](https://www.wikidata.org/wiki/openalex:W3096806995)  
**Source**: https://4ort.xyz/entity/face2speech-towards-multi-speaker-text-to-speech-synthesis-using-an-embedding-vector-predicted-from-a-face-image