Zhou, S., Zhou, Y., He, Y., Zhou, X., Wang, J., Deng, W., & Shu, J. (2026). IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 35139-35148. https://doi.org/10.1609/aaai.v40i41.40820