English(EN) Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning

新的Tacit-TTS系统可实现更快、无文本的语音克隆

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员开发了Tacit-TTS，一种新颖的文本到语音系统，旨在实现高效且无文本的语音克隆。该系统源自IndexTTS2，用掩码非自回归生成方法取代了传统的自回归解码。与前代产品相比，Tacit-TTS在生成较长语音时速度提高了10倍以上，并支持跨语言和非词汇参考，展示了其处理多样化音频输入的能力。 AI

影响这项研究可能带来更高效、更多功能的语音克隆工具，对内容创作和可访问性产生影响。

排序理由该集群包含一篇详细介绍新模型及其技术方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 21 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新模型及其技术方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Jian Chen, You Zhang, Mark Vinton · 2026-10-01 04:00

Tacit-TTS：从自回归解码到掩码预测，实现高效无文本语音克隆

arXiv:2609.38658v1 Announce Type: cross Abstract: TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but their sequential decoding incurs substantial latency. Non-autoregressive alternative…

本文如何被排名

报道来源 [1]

Tacit-TTS：从自回归解码到掩码预测，实现高效无文本语音克隆

相关实体

相关话题