New framework aims to decolonize automated speech recognition systems

This paper introduces a framework for developing more culturally competent automated speech recognition (ASR) systems. It argues that current ASR failures with low-resource and Indigenous languages are not just technical issues but reflect colonial linguistic policies. The authors propose a taxonomy of "Three Harms" (Misrecognition, Misalignment, Mistrust) and a seven-layer model for linguistic diversity. They advocate for a participatory design approach where affected communities are integral to the development and governance of ASR technologies. AI

IMPACT This research could lead to more equitable access to AI-powered voice interfaces for underrepresented linguistic communities.

RANK_REASON Academic paper proposing a new framework for ASR development. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• Indigenous
• Linguistic Diversity
• Three Harms (3M) taxonomy

• paper
• policy

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →