Metraipolis › archive › dc_ccbe3f03e7f6
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents — arXiv:2608.08638
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08638
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:50:50.790Z
- SHA-256 of the archived text
84d97b66fbdb3c62cee8fef2bc3697578ee26abd67f53749d665c66d9a006428- Stable URL of this page
https://metraipolis.com/documento/dc_ccbe3f03e7f6
How to cite
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents — arXiv:2608.08638 — arXiv (en), https://arxiv.org/abs/2608.08638 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccbe3f03e7f6 (Metraipolis archive dc_ccbe3f03e7f6, sha256 84d97b66fbdb3c62cee8fef2bc3697578ee26abd67f53749d665c66d9a006428)
BibTeX
@misc{dcccbe3f03e7f6,
title = {CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents — arXiv:2608.08638},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08638},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccbe3f03e7f6; sha256 84d97b66fbdb3c62cee8fef2bc3697578ee26abd67f53749d665c66d9a006428},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08638. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools. All TTS systems require faithful linguistic rendering, consistent speaker identity, and low-latency response. Yet compact streaming systems must preserve sufficient acoustic detail in a predictable low-rate latent sequence, while iterative diffusion sampling and classifier-free guidance multiply inference cost at every autoregressive step. To strike a balance between high-fidelity synthesis and low-latency inference, we present CuteTTS, a compact continuous-autoregressive TTS system. It combines semantically aligned causal VAE latents with patch-level autoregression, explicit speaker conditioning, and a bidirectional flow-matching head. We further introduce guidance-step distillation, which absorbs classifier-free guidance and multiple solver steps into a single interval-conditioned student. Evaluations on LibriSpeech and Seed-TTS-Eval demonstrate competitive intelligibility and speaker similarity in zero-shot voice cloning, while distillation lowers first-audio latency by 23.3% and real-time factor by 40.8% relative to the base model with comparable objective and subjective quality. These results provide a practical path toward continuous-autoregressive TTS that reconciles high-fidelity generation with the latency demands of real-time interaction. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.08638 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:49:41.991Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).