arXiv：cs.AI· Al Varrel Putra Kusuma, Fernando Bello, Joshua Brown·· 20 小时前
AphaVoice：面向失语症患者模拟的文本转语音模型
AphaVoice: Text-to-Speech Model for Aphasia Patient Simulation
AI 导读
研究提出 AphaVoice，一个专为合成高度逼真失语症语音设计的 TTS 框架，用于弥补当前 AI 研究几乎只聚焦语音处理、语音生成探索不足的空白。与 SOTA TTS 系统相比，AphaVoice 在时间指标上更优，能更好捕捉不流畅这一临床特征，并保持说话人身份一致。
正文
Abstract:While language therapy is the primary treatment for post-stroke aphasia, limited clinical resources often restrict patient access to proper care. Addressing this gap requires reliable training simulations for medical professionals. However, current AI efforts focus almost exclusively on speech processing, leaving speech generation largely unexplored. This study introduces AphaVoice, a novel text-to-speech (TTS) framework explicitly engineered to synthesize highly realistic aphasic speech. Evaluated against state-of-the-art TTS systems, AphaVoice demonstrates a superior ability to capture the clinical feature of dysfluency, outperforming existing models in temporal metrics while consistently maintaining speaker identity. By leveraging latent space shifting, the model also supports multi-speaker generation without sacrificing phonetic realism. Ultimately, AphaVoice provides a scalable, high-fidelity tool for medical training and clinical simulation related to aphasia.
| Comments: | Accepted at IEEE Spoken Language Technology (SLT) 2026 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14479 [cs.CL] |
| (or arXiv:2610.14479v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14479 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Al Varrel Putra Kusuma [view email]
[v1]
Sat, 10 Oct 2026 02:22:51 UTC (765 KB)
来源：arXiv：cs.AI · arxiv.org