研究人员开发了 JaiTTS-v1.0，一个泰语语音克隆文本到语音模型，取得了最先进的成果，在短时语音生成方面，其词错误率（CER）为1.94%，超越了人类真实数据。该模型改编自VoxCPM，可以直接处理数字和泰英混合语，无需显式文本规范化。在人类评估中，JaiTTS-v1.0在绝大多数配对比较中优于商业旗舰模型。另外，另一项研究专注于科学语音的跨语言语音克隆，评估了基于OmniVoice的模型，并使用数据增强来提高可懂度，同时保持阿拉伯语、中文和法语之间的说话人相似性。 AI
影响 泰语语音克隆和跨语言语音合成的进步可以实现更自然、更易于访问的通信工具。
排序理由 该集群包含两篇arXiv论文，详细介绍了新的语音合成和语音克隆模型。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2604.27607v1 Announce Type: new Abstract: We present JaiTTS-v1.0, a state-of-the-art Thai voice cloning text-to-speech model built through continual training on a large Thai-centric speech corpus. The model architecture is adapted from VoxCPM, a tokenizer-free autoregressiv…
We present JaiTTS-v1.0, a state-of-the-art Thai voice cloning text-to-speech model built through continual training on a large Thai-centric speech corpus. The model architecture is adapted from VoxCPM, a tokenizer-free autoregressive TTS model. JaiTTS-v1.0 directly processes nume…
arXiv:2604.26136v1 Announce Type: cross Abstract: Preserving a speaker's voice identity while generating speech in a different language remains a fundamental challenge in spoken language technology, particularly in specialized domains such as scientific communication. In this pap…
Preserving a speaker's voice identity while generating speech in a different language remains a fundamental challenge in spoken language technology, particularly in specialized domains such as scientific communication. In this paper, we address this challenge through our system s…