研究人员推出dots.tts，一个拥有20亿参数、在连续潜在空间中运行的文本到语音模型。该模型包含多项创新，包括用于结构化语音表示的AudioVAE、用于提高一致性的全历史条件以及用于增强鲁棒性的自纠正后训练。Dots.tts在Seed-TTS-Eval等基准测试中取得了最先进的成果，并通过MeanFlow蒸馏实现了高效、低延迟的生成。 AI
影响 在多语言TTS基准测试中设定了新的SOTA，可能提高AI应用中的语音克隆和情感表达能力。
排序理由 该集群包含一份技术报告，详细介绍了一个具有性能基准的新文本到语音模型。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.07080v1 Announce Type: cross Abstract: We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are …
We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are threefold. First, we train an AudioVAE with multip…
A 2B-parameter continuous autoregressive text-to-speech model trained on a multilingual corpus achieves state-of-the-art performance on multiple benchmarks while enabling efficient low-latency speech generation through specialized distillation techniques.