Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition

2025-01-25

AI Summary

This study addresses the critical challenges of speaker dependency and poor cross-etiology generalization in dysarthric speech recognition. We propose the first truly speaker-independent universal dysarthria recognition method, built upon the Whisper large language model and integrating phoneme-level robustness enhancement with cross-etiology transfer learning. Evaluated on the Parkinson’s disease dataset SAP-1005, our method achieves a character error rate (CER) of 6.99% and word error rate (WER) of 10.71%. On the cross-etiology TORGO dataset—encompassing cerebral palsy, amyotrophic lateral sclerosis, and other etiologies—it attains CER=25.08% and WER=39.56%, substantially outperforming existing adaptive approaches. To our knowledge, this is the first work to empirically validate the feasibility and generalizability of speaker-independent dysarthria recognition across multiple neurological etiologies. Our results establish a scalable, clinically deployable foundation for objective, etiology-agnostic assessment of speech disorders.

Technology Category

• Natural Language Processing: Speech
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In this paper, we present a speaker-independent dysarthric speech recognition system, with a focus on evaluating the recently released Speech Accessibility Project (SAP-1005) dataset, which includes speech data from individuals with Parkinson's disease (PD). Despite the growing body of research in dysarthric speech recognition, many existing systems are speaker-dependent and adaptive, limiting their generalizability across different speakers and etiologies. Our primary objective is to develop a robust speaker-independent model capable of accurately recognizing dysarthric speech, irrespective of the speaker. Additionally, as a secondary objective, we aim to test the cross-etiology performance of our model by evaluating it on the TORGO dataset, which contains speech samples from individuals with cerebral palsy (CP) and amyotrophic lateral sclerosis (ALS). By leveraging the Whisper model, our speaker-independent system achieved a CER of 6.99% and a WER of 10.71% on the SAP-1005 dataset. Further, in cross-etiology settings, we achieved a CER of 25.08% and a WER of 39.56% on the TORGO dataset. These results highlight the potential of our approach to generalize across unseen speakers and different etiologies of dysarthria.

Problem

• Speech Recognition
• Dysarthria Identification
• Universal Applicability

Innovation

• Speech Recognition
• Dysarthria Identification
• Multi-Disease Adaptability