EUVIMEDEUVIMED entdecken
Crossref

KALL-E: Autoregressive Speech Synthesis with Next-Distribution Prediction

Kangxiang Xia, Xinfa Zhu, Jixun Yao, Wenjie Tian, Wenhao Li, Lei Xie

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (40) · 34016-34024

DOI: 10.1609/aaai.v40i40.40695 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Kangxiang Xia und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce KALL-E, a novel autoregressive (AR) language model for text-to-speech (TTS) synthesis that operates by predicting the next distribution of continuous speech frames. Unlike existing methods, KALL-E directly models the continuous speech distribution conditioned on text, eliminating the need for any diffusion-based components. Specifically, we utilize a Flow-VAE to extract a continuous latent speech representation from waveforms, instead of relying on discrete speech tokens. A single AR Transformer is then trained to predict these continuous speech distributions from text, optimizing a Kullback–Leibler divergence loss as its objective. Experimental results demonstrate that KALL-E achieves superior speech synthesis quality and can even adapt to a target speaker from just a single sample. Importantly, KALL-E provides a more direct and effective approach for utilizing continuous speech representations in TTS.

Zitieren

APA

Xia, K., Zhu, X., Yao, J., Tian, W., Li, W., & Xie, L. (2026). KALL-E: Autoregressive Speech Synthesis with Next-Distribution Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 34016-34024. https://doi.org/10.1609/aaai.v40i40.40695

Vancouver

Xia K, Zhu X, Yao J, Tian W, Li W, Xie L. KALL-E: Autoregressive Speech Synthesis with Next-Distribution Prediction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(40):34016-34024. doi:10.1609/aaai.v40i40.40695

BibTeX
@article{Xia2026,
  author = {Xia, Kangxiang and Zhu, Xinfa and Yao, Jixun and Tian, Wenjie and Li, Wenhao and Xie, Lei},
  title = {KALL-E: Autoregressive Speech Synthesis with Next-Distribution Prediction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {40},
  pages = {34016--34024},
  doi = {10.1609/aaai.v40i40.40695}
}
Kostenlos starten →