arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2506.04397eess.AScs.CLcs.SD

我们能否使用大型语音模型 Parler TTS 重建构音障碍语音?

Can we reconstruct a dysarthric voice with the large speech model Parler TTS?

Centre for Speech Technology Research, University of Edinburgh(爱丁堡大学语音技术研究中心)

Ariadna Sanchez, Simon King

AI总结:

本研究探索使用大型语音模型 Parler TTS 重建构音障碍患者患病前的声音,通过微调模型生成语音,发现模型能生成但难以控制可理解性和保持说话人身份,并提出了改进方向。

摘要:

言语障碍会使患者难以甚至无法进行交流。个性化文本转语音系统作为一种辅助沟通工具具有吸引力。我们尝试使用大型语音模型进行语音重建,生成患者在患病前声音的近似版本。具体而言,我们研究最先进的大型语音模型 Parler TTS 能否在保持说话人身份的同时生成可理解的语音。我们构建了一个数据集,并标注了相关的说话人和可理解性信息,并利用该数据集对模型进行微调。结果表明,该模型确实能够学习从这一具有挑战性的数据分布中生成语音,但在控制可理解性和保持一致的说话人身份方面存在困难。我们提出了未来方向,以提高此类模型在语音重建任务中的可控性。

英文摘要:

Speech disorders can make communication hard or even impossible for those who develop them. Personalised Text-to-Speech is an attractive option as a communication aid. We attempt voice reconstruction using a large speech model, with which we generate an approximation of a dysarthric speaker's voice prior to the onset of their condition. In particular, we investigate whether a state-of-the-art large speech model, Parler TTS, can generate intelligible speech while maintaining speaker identity. We curate a dataset and annotate it with relevant speaker and intelligibility information, and use this to fine-tune the model. Our results show that the model can indeed learn to generate from the distribution of this challenging data, but struggles to control intelligibility and to maintain consistent speaker identity. We propose future directions to improve controllability of this class of model, for the voice reconstruction task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑