研究人员推出MoDiCoL，一个旨在提高自动语音识别（ASR）系统鲁棒性的新数据集。与现有数据集孤立地考虑口音或噪声等因素不同，MoDiCoL允许对语言内容、说话人特征和声学环境进行受控分析，包括它们的共现。该数据集配有持续学习课程，以模拟真实世界的增量更新，并研究ASR模型在不断变化的情况下如何获取、迁移和遗忘鲁棒性。 AI
影响 该数据集旨在通过解决分布偏移来弥合ASR在基准测试和实际应用之间的性能差距。
排序理由 该集群包含一篇学术论文，详细介绍了用于ASR研究的新数据集和方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.14459v1 Announce Type: cross Abstract: Modern Automatic Speech Recognition (ASR) systems have made remarkable progress on standard benchmarks, yet performance gaps have emerged under real-world distribution shifts, caused by recording conditions, accents, speech impair…
Modern Automatic Speech Recognition (ASR) systems have made remarkable progress on standard benchmarks, yet performance gaps have emerged under real-world distribution shifts, caused by recording conditions, accents, speech impairments, and noise. Existing datasets and benchmarks…