# JDI-T: Jointly Trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment

> Research article (Interspeech 2020, 2020) · cited 32× · AI/ML

**Wikidata**: [openalex:W3096442195](https://www.wikidata.org/wiki/openalex:W3096442195)  
**Source**: https://4ort.xyz/entity/jdi-t-jointly-trained-duration-informed-transformer-for-text-to-speech-without-explicit-alignment