AI-Enhanced Speech-Language Intervention Documentation: Opportunities and Design Goals

Qingxiao Zheng, Abhinav Choudhry, Zihan Liu, Parisa Rabbani, Yuting Hu, Abbie Olszewski, Yun Huang, Jinjun Xiong

Abstract: Speech-Language Pathologists (SLPs) support individuals with communication difficulties, but high caseloads and heavy documentation demands often lead to strain and burnout. This research examines how AI-generated intervention documentation can support SLPs and how their insights can inform future AI-enhanced documentation systems. Through a formative study with 17 SLPs, we used an iterative, human-centered approach to examine how AI-generated documentation aligned with their professional practices. Our findings reveal four key opportunities for using AI in documentation and propose three fluidity-focused design goals—contextual, assessment, and individual—for future systems. These goals aim to balance individualization in special education with high-quality documentation. This study advances understanding of how AI can support SLP workflows and inform the design of documentation tools across educational settings where structured documentation is critical.