Zero-Shot Parkinson's Disease Detection from Speech: Comparing Large Audio and Language Models
For researchers developing cross-lingual PD detection systems, this work highlights the importance of input modality choice, but findings are incremental and dataset-specific.
This study compares zero-shot Parkinson's disease detection using handcrafted acoustic features with LLMs versus raw audio waveforms with audio models across four languages. Results show that handcrafted features provide more stable performance in low-resource languages (e.g., Bengali), while audio input yields dataset-dependent gains.
Large audio and language models have recently demonstrated zero-shot reasoning capabilities across various domains. However, it remains unclear how the form of audio input, whether handcrafted acoustic features extracted from speech or the raw audio waveform itself, affects performance for Parkinson's disease (PD) detection across different languages. In this study, we systematically compare two input modalities for zero-shot PD detection: (i) handcrafted acoustic features extracted from speech recordings analyzed by a general-purpose LLM, and (ii) direct waveform input analyzed by audio-capable models. Experiments on PD speech datasets in four languages show that performance varies across input modalities, speech tasks, and languages. Handcrafted acoustic features provide more stable performance in a low-resource language (e.g., Bengali), whereas audio input yields dataset-dependent gains. These findings highlight the impact of input modality on zero-shot PD detection from speech.