# VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

> Research article (INTERSPEECH 2023, 2023) · cited 43× · AI/ML

**Wikidata**: [openalex:W4385823163](https://www.wikidata.org/wiki/openalex:W4385823163)  
**Source**: https://4ort.xyz/entity/vits2-improving-quality-and-efficiency-of-single-stage-text-to-speech-with-adversarial-learning-and-architecture-design