Zero-Shot Cross-lingual Aphasia Detection using Automatic Speech Recognition
This work addresses the challenge of scarce aphasic speech data for non-English languages, offering a potential tool to automate detection in medical settings, though it is incremental as it builds on existing cross-lingual approaches.
The paper tackled the problem of detecting aphasia in low-resource languages like Greek and French by developing an end-to-end pipeline using pre-trained Automatic Speech Recognition models, achieving results comparable to previous methods that relied on manually extracted transcripts.
Aphasia is a common speech and language disorder, typically caused by a brain injury or a stroke, that affects millions of people worldwide. Detecting and assessing Aphasia in patients is a difficult, time-consuming process, and numerous attempts to automate it have been made, the most successful using machine learning models trained on aphasic speech data. Like in many medical applications, aphasic speech data is scarce and the problem is exacerbated in so-called "low resource" languages, which are, for this task, most languages excluding English. We attempt to leverage available data in English and achieve zero-shot aphasia detection in low-resource languages such as Greek and French, by using language-agnostic linguistic features. Current cross-lingual aphasia detection approaches rely on manually extracted transcripts. We propose an end-to-end pipeline using pre-trained Automatic Speech Recognition (ASR) models that share cross-lingual speech representations and are fine-tuned for our desired low-resource languages. To further boost our ASR model's performance, we also combine it with a language model. We show that our ASR-based end-to-end pipeline offers comparable results to previous setups using human-annotated transcripts.