PEEC：從脆弱臨床族群蒐集語音資料的受保護實體倫理檢查表

// PEEC: The Protected Entities Ethics Checklist for Collecting Speech Data From Vulnerable Clinical Populations

本研究提出「受保護群體倫理檢核表（PEEC）」，用於從弱勢族群蒐集語音資料，促進公平的自動語音辨識（ASR）系統發展｜PEEC強調參與者保護、同意程序、資料標準及合規性，確保研究程序正義｜該框架提供多元臨床族群的專屬指引，並連結尊重研究實務與臨床語音AI的公平性表現。

// This study introduces the Protected Entities Ethics Checklist (PEEC), a framework for ethical speech data collection from vulnerable populations to support fair ASR system development. PEEC focuses on participant protection, consent, data standards, and compliance to ensure procedural justice in research. The framework provides tailored guidance for diverse clinical populations and emphasizes that ethical data practices are essential for algorithmic fairness. Ultimately, PEEC links respectful research practices with equitable AI performance in clinical speech applications.

Published 2026年5月29日