arXiv 2502.039452025-02-06cs.CL

Afrispeech-Dialog：面向医疗及其他领域的非洲口音英语自发对话基准数据集

Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond

Intron（英创公司）；BioRAMP（BioRAMP机构）；Brown University（布朗大学）；Indian Institute of Information Technology Allahabad（阿拉哈巴德印度信息技术学院）；University of Minnesota-Twin Cities（明尼苏达大学双城分校）；University of Glasgow（格拉斯哥大学）；University of Florida（佛罗里达大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Georgia Institute of Technology（佐治亚理工学院）

Mardhiyah Sanni, Tassallah Abdullahi, Devendra D. Kayande, Emmanuel Ayodele, Naome A. Etori, Michael S. Mollel, Moshood Yekini, Chibuzor Okocha, Lukman E. Ismai… 展开作者

Mardhiyah Sanni, Tassallah Abdullahi, Devendra D. Kayande, Emmanuel Ayodele, Naome A. Etori, Michael S. Mollel, Moshood Yekini, Chibuzor Okocha, Lukman E. Ismaila, Folafunmi Omofoye, Boluwatife A. Adewale, Tobi Olatunji

备注：: 19 pages, 5 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该工作提出 Afrispeech-Dialog 基准数据集，通过 50 段非洲口音英语对话评估 ASR 和说话人分离系统，发现口音导致性能下降超 10%，并揭示 ASR 错误对医疗摘要的影响，呼吁构建更具包容性的低资源语音数据集。

摘要：

语音技术正在改变从医疗保健到呼叫中心和机器人等各个领域的交互方式，但其在非洲口音对话上的表现仍未得到充分探索。我们引入了 Afrispeech-Dialog，这是一个包含 50 段模拟医疗和非医疗非洲口音英语对话的基准数据集，旨在评估自动语音识别（ASR）及相关技术。我们评估了最先进（SOTA）的说话人分离和 ASR 系统在长格式、带口音语音上的表现，将其与母语口音进行对比，发现性能下降超过 10%。此外，我们探索了大型语言模型（LLM）的医疗对话摘要能力，以展示 ASR 错误对下游医疗摘要的影响，为全球南方语音技术面临的挑战和机遇提供了见解。我们的工作强调了需要更具包容性的数据集，以推动低资源环境下对话式人工智能的发展。

英文摘要：

Speech technologies are transforming interactions across various sectors, from healthcare to call centers and robots, yet their performance on African-accented conversations remains underexplored. We introduce Afrispeech-Dialog, a benchmark dataset of 50 simulated medical and non-medical African-accented English conversations, designed to evaluate automatic speech recognition (ASR) and related technologies. We assess state-of-the-art (SOTA) speaker diarization and ASR systems on long-form, accented speech, comparing their performance with native accents and discover a 10%+ performance degradation. Additionally, we explore medical conversation summarization capabilities of large language models (LLMs) to demonstrate the impact of ASR errors on downstream medical summaries, providing insights into the challenges and opportunities for speech technologies in the Global South. Our work highlights the need for more inclusive datasets to advance conversational AI in low-resource settings.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。