Applications of Artificial Intelligence for Cross-Language Intelligibility Assessment of Dysarthric Speech

Purpose: Speech intelligibility is a critical outcome in the assessment and management of dysarthria, yet most research and clinical practices have focused on American English, limiting their applicability across languages. This commentary introduces a conceptual framework leveraging artificial intelligence (AI) to advance cross-language intelligibility assessment of dysarthric speech. Method: We propose a two-tiered conceptual framework consisting of a universal speech model that encodes dysarthric speech into acoustic–phonetic representations, followed by a language-specific intelligibility assessment model that interprets these representations within the phonological or prosodic structures of the target language. We further identify barriers to cross-language intelligibility assessment of dysarthric speech, including data scarcity, annotation complexity, and limited linguistic insights into dysarthric speech, and outline potential AI-driven solutions to overcome these challenges. Results: We present a specific instantiation of the proposed framework with Spanish dysarthric speech, demonstrating its practical implementation. This example highlights the framework's potential to deliver reliable measures of speech intelligibility across languages. Conclusions: Cross-language intelligibility assessment of dysarthric speech requires approaches that address both language-universal dysarthric manifestations and language-specific factors to ensure accurate and clinically meaning evaluation across languages. Recent advances in AI provide the foundational tools to support this integration, shaping future directions toward cross-langauge intelligibility assessment frameworks that are efficient, scalable, and applicable across diverse languages.