Work

CoSTA: Cognitive-State-Conditioned TTS Data Augmentation Using ASR Transcripts for Alzheimer's Disease Detection

Year: 2026

Type: preprint

Abstract: Speech-based Alzheimer's Disease (AD) detection is constrained by scarce pathological speech data. To address this, we propose CoSTA, a Text-to-Speech (TTS)-based data augmentation framework. Specifically, we first develop two Cognitive-State-Conditioned (CS-Cond) TTS models by adapting CosyVoice2 and F5-TTS to synthesize speech with distinct AD and Healthy Control characteristics. Furthermore, by constructing a transcript pool comprising Manual Transcripts (MT) and 36 Automatic Speech Recognition (ASR) transcripts, we investigate the impact of text sources on TTS-based augmentation. We also perform augmentation-factor analysis and test-time augmentation. Experiments on the ADReSS dataset show that CS-Cond TTS significantly improves synthetic speech utility, and ASR-driven augmentation frequently outperforms MT-driven augmentation. Finally, CoSTA yields a 4.16% gain over the baseline, achieving an audio-only accuracy of 85.83% on the ADReSS test set and outperforming prior methods.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2606.06170

Authors: Liu, Yin-Long, Li, Yuanchao, Wang, Yiming, Li, Yue, Feng, Rui, Chen, Jiaxin, Liu, Shaobo, He, Liu, Chen, Yuang, Yuan, Jiahong, Ling, Zhen-Hua

Institutions: University of Science and Technology of China, University of Edinburgh

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: green

Funders: University of Science and Technology of China, National Social Science Fund of China

Award: G2828938620

OpenAlex ID: W7163644971

Cites:

Cited by:

Related to: