mlsanityData to 19 Oct 2026

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

arXiv 2606.06170 ↗First posted 4 Jun 2026eess.AScited by 0

On the map: Speech and audio language models → ASR evaluation, bias and atypical speech

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in ASR evaluation, bias and atypical speech, one of 11 directions in Speech and audio language models. Builds on 19 of its 35 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

19 of 35 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?10 Jan
  2. 2022Data Augmentation for Dementia Detection in Spoken Language26 Jun

Other references · 17

  1. 2022Scalable Diffusion Models with Transformerscited by 6,161
  2. 2022Flow Matching for Generative Modelingcited by 5,905
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,812
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,661
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 4,385
  6. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,762
  7. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 2,135
  8. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,462
  9. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 737
  10. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 483
  11. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 397
  12. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 218
5 more
  1. 2020Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challengecited by 113
  2. 2024Clever Hans Effect Found in Automatic Detection of Alzheimer's Disease through Speechcited by 15
  3. 2024Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labelingcited by 5
  4. 2025Detecting Neurocognitive Disorders through Analyses of Topic Evolution and Cross-modal Consistency in Visual-Stimulated Narrativescited by 3
  5. 2024Leveraging Multimodal Methods and Spontaneous Speech for Alzheimer's Disease Identificationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Manual Transcripts: The Potential of Automated Speech Recognition Errors in Improving Alzheimer's Disease Detection
  2. 2026Impact of automatic speech recognition quality on Alzheimer's disease detection from spontaneous speech: a reproducible benchmark study with lexical modeling and statistical validation
  3. 2021Exploiting Pre-Trained ASR Models for Alzheimer's Disease Recognition Through Spontaneous Speech
  4. 2023Alzheimer Disease Classification through ASR-based Transcriptions: Exploring the Impact of Punctuation and Pauses
  5. 2021Influence of ASR and Language Model on Alzheimer's Disease Detection
  6. 2025MoTAS: MoE-Guided Feature Selection from TTS-Augmented Speech for Enhanced Multimodal Alzheimer's Early Screening
  7. 2026Transcript-Free Lightweight Detection of Alzheimer's Disease from Spontaneous Speech Using Handcrafted MFCC-Dominant Acoustic Biomarkers
  8. 2026Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection