arXiv Machine Learning
Jul 24
Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models
arXiv:2607. 21496v1 Announce Type: cross Abstract: Cognitive impairment (CI) is a growing public health concern.
SpeechDx: A Multi-Task Benchmark for Clinical Speech AI
arXiv:2606. 17339v1 Announce Type: new Abstract: Speech offers a uniquely informative window into health by simultaneously engaging neurological, motor, respiratory, and vocal systems.
Related stories
arXiv Computation and Language
Sep 21
Cross-Lingual Parkinson's Disease Severity Assessment Using Pre-trained Speech Embeddings: A Multi-Class Evaluation
The paper evaluates pre‑trained speech embeddings from four state‑of‑the‑art speech foundation models for cross‑lingual Parkinson's disease severity assessment. Experiments span three datasets in zero‑shot and k‑shot settings, showing that these embeddings can transfer meaningfully across languages, though performance varies with dataset characteristics, preprocessing, and adaptation strategy. Misclassifications linked to inter‑speaker variability and atypical speech patterns underscore the need for more robust feature extraction, modeling, and explainability to support reliable clinical insights.
arXiv Machine Learning
Jun 30
RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity
arXiv:2602. 18452v3 Announce Type: replace-cross Abstract: As conversational multimodal AI tools are increasingly adopted to process patient data for health assessment, robust benchmarks are needed to measure progress and expose failure modes under realistic conditions.
arXiv AI
Sep 17
Rethinking How We Evaluate Methodological Progress in Health AI
The study re‑implements 12 AI algorithms for electronic health records within a unified framework and evaluates them on MIMIC‑IV and NWICU datasets. It compares expert‑authored clinically meaningful tasks with randomly generated tasks, finding that pairwise algorithm comparisons transfer well across task families and datasets, yet clinically meaningful tasks show stronger task‑method interactions. The results also reveal that newer algorithms do not consistently outperform older ones, with gradient‑boosted trees remaining highly competitive when combined with modern EHR representations.
arXiv AI
Sep 18
Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification under Federated Domain Generalization with Causality-Inspired Interventions
The paper introduces BTS-CAFE, a federated domain generalization framework for respiratory sound classification that addresses stethoscope-induced shortcuts. It combines causality-inspired device-style interventions, counterfactual metadata augmentation, and gradient alignment to reduce style–content entanglement and promote device-invariant decision boundaries. Experiments on ICBHI and SPRSound datasets show a 3.69‑point improvement in out-of-distribution performance over the baseline and outperform conventional data augmentation and federated learning methods.
arXiv AI
Sep 2
Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment
The paper introduces a framework that aligns self‑supervised respiratory encoders with medical terminology in a shared latent space, enabling zero‑shot respiratory sound classification. By using a medical LLM to generate structured reports from metadata, the method creates dense semantic anchors for contrastive learning, combining a sigmoid‑based contrastive loss with the encoder’s native SSL objective and similarity‑aware negative sampling. On nine tasks across six datasets, the approach achieves a 61.3% mean zero‑shot AUC, outperforming CLAP and Qwen2‑Audio, and reaches the highest linear probing AUC with only 43% of the data used by full‑scale baselines.
arXiv AI
Jul 21
A Benchmark for Early-stage Parkinson's Disease Detection from Speech
arXiv:2605. 14066v2 Announce Type: replace-cross Abstract: Early-stage Parkinson's disease (EarlyPD) detection from speech is clinically meaningful yet underexplored, and published results are hard to compare because studies differ in datasets, languages, tasks, evaluation protocols, and EarlyPD definitions.
arXiv AI
Jun 18
Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech
arXiv:2603. 15988v3 Announce Type: replace-cross Abstract: Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies.
arXiv AI
Jun 16
Unifying Acoustic Features and Text with Multimodal LLMs for Neurodegenerative Screening
arXiv:2606. 14788v1 Announce Type: cross Abstract: Voice-based screening offers a scalable and non-invasive way to assess neurodegenerative diseases such as Alzheimer's disease (AD) and Parkinson's disease (PD), but their staging remains challenging due to the difficulty of integrating heterogeneous data.
arXiv Machine Learning
5d ago
BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio
BreathGRU is a semi‑supervised Bidirectional Gated Recurrent Unit framework designed to segment speech and breath events in respiratory audio. It combines acoustic feature extraction, bidirectional recurrent modeling, pseudo‑label refinement, and duration‑constrained Segmental Viterbi decoding to produce accurate speech‑breath segmentation. In evaluations against existing methods, BreathGRU achieved the highest breath event recall, lowest onset‑localisation error, and highest Mean Match Intersection over Union, outperforming large pretrained VAD models such as Silero.
arXiv AI
Sep 2
Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer's Disease Detection
The study examines how speech preprocessing—such as enhancement, sample selection, and demographic balancing—affects Alzheimer’s disease detection models that use the Pitt Corpus. Experiments reveal that while speech‑enhanced datasets boost in‑domain accuracy, they diminish cross‑dataset robustness and introduce class imbalance and prediction shifts, even when training and testing enhancements are matched. Large audio‑language models show similar sensitivity, indicating that cleaner speech does not guarantee better real‑world performance.
arXiv AI
3d ago
Automatic estimation of verbal fluency index in people with Motor Neuron Disease using ASR alignment and pause modelling
The study introduces an automated system for estimating the Verbal Fluency Index (VFI) in individuals with Motor Neuron Disease (MND) by combining ASR (WhisperX) and VAD (Silero) with precise timestamping. Using a unique MND dataset, the approach outperformed traditional acoustic and self‑supervised embedding methods, achieving high predictive accuracy (R² up to 0.9 for P‑words and 0.8 for S‑words). Clinically inspired features were consistently superior, demonstrating the feasibility of automated VFI estimation for monitoring cognitive impairment in MND.