Motor, Cognitive, or Corpus? What Survives Cross-Lingual Transfer in Speech-Based Parkinsons Disease Detection

• URL: http://arxiv.org/abs/2608.13425v1
• Date: Thu, 13 Aug 2026 16:15:32 GMT
• Title: Motor, Cognitive, or Corpus? What Survives Cross-Lingual Transfer in Speech-Based Parkinsons Disease Detection
• Abstract summary: Self-supervised learning (SSL) speech representations achieve strong performance for Parkinson's disease detection within individual corpora.<n>It remains unclear whether these models capture disease-related characteristics or exploit dataset-specific confounds.<n>These results highlight critical limitations that must be addressed before speech-based pathology recognition models can be reliably deployed in clinical settings.
• Score: 0.37867904346306974
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-supervised learning (SSL) speech representations achieve strong performance for Parkinson's disease (PD) detection within individual corpora. However, it remains unclear whether these models capture disease-related characteristics or exploit dataset-specific confounds, particularly since most SSL backbones are pretrained exclusively on healthy speech. To investigate this question, we perform a layer-wise analysis of nine SSL speech backbones using a low-capacity logistic regression probe across three languages. We structure the evaluation as multiple scenarios that progressively introduce distribution shifts in participant identity, recording conditions, language, and pathology. Our results reveal two key findings. First, layer selection is highly corpus-dependent: the optimal representation layer is determined primarily by the source dataset rather than by the SSL architecture itself. Second, the transferred discriminative signal lacks pathological specificity: classifiers trained to detect PD assign similarly high probabilities to both PD and dementia speech in the target corpus. These results highlight critical limitations that must be addressed before speech-based pathology recognition models can be reliably deployed in clinical settings.

Related papers

• A Benchmark for Early-stage Parkinson's Disease Detection from Speech [6.032182703186787]
  Early-stage Parkinson's disease (EarlyPD) detection from speech is clinically meaningful yet underexplored.<n>We propose the first benchmark for speech-based EarlyPD detection, with a speaker-independent split for fair and replicable cross-method evaluation.
  arXiv  Detail & Related papers  (2026-05-13T19:43:01Z)
• Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease [72.0406069194794]
  Speech representations often encode language-dependent structure that can confound dysarthria detection.<n>We propose a representation-level language shift that aligns source-language self-supervised speech representations with the target-language distribution.<n>We evaluate the approach on oral DDK recordings from Parkinson's disease speech datasets in Czech, German, and Spanish.
  arXiv  Detail & Related papers  (2026-03-23T17:23:39Z)
• Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech [69.86604856129883]
  Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies.<n>We propose a three-stage framework that leverages unlabeled dysarthric speech and large-scale typical speech datasets to scale training.
  arXiv  Detail & Related papers  (2026-03-16T23:00:07Z)
• Does Language Matter for Early Detection of Parkinson's Disease from Speech? [9.968776083852813]
  Using speech samples as a biomarker is a promising avenue for detecting and monitoring the progression of Parkinson's disease (PD)<n>To assess the role of language in PD detection, we tested pretrained models with varying data types and pretraining objectives.
  arXiv  Detail & Related papers  (2025-07-14T19:23:09Z)
• Evaluating the Effectiveness of Pre-Trained Audio Embeddings for Classification of Parkinson's Disease Speech Data [0.7673339435080445]
  Speech impairments are prevalent biomarkers for Parkinson's Disease (PD)<n>Deep acoustic features have shown promise for PD classification, but their effectiveness often varies due to speaker differences.<n>This study investigates the effectiveness of three pre-trained audio embeddings for PD classification.
  arXiv  Detail & Related papers  (2025-06-02T09:32:54Z)
• Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from Speech [8.852211803870016]
  This work aims to tackle the Parkinson's disease (PD) detection problem from the speech signal in a bilingual setting by proposing an ad-hoc dual-head deep neural architecture for type-based binary classification.<n>One head is specialized for diadochokinetic patterns. The other head looks for natural speech patterns present in continuous spoken utterances.
  arXiv  Detail & Related papers  (2025-03-13T12:23:11Z)
• Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition [71.87998918300806]
  This paper explores approaches to integrate domain fine-tuned SSL pre-trained models and their features into TDNN and Conformer ASR systems. TDNN systems constructed by integrating domain-adapted HuBERT, wav2vec2-conformer or multi-lingual XLSR models consistently outperform standalone fine-tuned SSL pre-trained models. Consistent improvements in Alzheimer's Disease detection accuracy are also obtained using the DementiaBank Pitt elderly speech recognition outputs.
  arXiv  Detail & Related papers  (2024-07-03T08:33:39Z)
• Neural Sign Actors: A diffusion model for 3D sign language production from text [51.81647203840081]
  Sign Languages (SL) serve as the primary mode of communication for the Deaf and Hard of Hearing communities. This work makes an important step towards realistic neural sign avatars, bridging the communication gap between Deaf and hearing communities.
  arXiv  Detail & Related papers  (2023-12-05T12:04:34Z)
• Decoding speech perception from non-invasive brain recordings [48.46819575538446]
  We introduce a model trained with contrastive-learning to decode self-supervised representations of perceived speech from non-invasive recordings. Our model can identify, from 3 seconds of MEG signals, the corresponding speech segment with up to 41% accuracy out of more than 1,000 distinct possibilities.
  arXiv  Detail & Related papers  (2022-08-25T10:01:43Z)
• Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition [55.25565305101314]
  Articulatory features are invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition systems. This paper presents a cross-domain and cross-lingual A2A inversion approach that utilizes the parallel audio and ultrasound tongue imaging (UTI) data of the 24-hour TaL corpus in A2A model pre-training. Experiments conducted on three tasks suggested incorporating the generated articulatory features consistently outperformed the baseline TDNN and Conformer ASR systems.
  arXiv  Detail & Related papers  (2022-06-15T07:20:28Z)
• Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts [56.72488923420374]
  Pre-trained language models (LMs) have shown great potential for cross-lingual transfer in low-resource settings. We show the few-shot cross-lingual transfer property of LMs for named recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke.
  arXiv  Detail & Related papers  (2022-04-10T21:46:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.