研究人员调查了 wav2vec 2.0 和 Whisper 等语音模型如何表示非裔美国人英语 (AAE) 中的辅音簇简化 (CCR)。研究发现，这两种模型都能准确地区分 CCR 的简化形式和规范形式。重要的是，模型保留了对底层声音的线索，这表明 CCR 被编码为一种结构化的音系变异，而不是简单的删除。 AI
影响 这项研究为人工智能模型如何处理语言变异提供了见解，有可能改进针对不同方言的自动语音识别 (ASR) 系统。
排序理由 该集群包含一篇详细介绍语音模型研究结果的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.23948v1 Announce Type: new Abstract: Self-supervised and supervised speech models are increasingly used to investigate which linguistic information their internal representations encode, and at what level of abstraction they encode it. One underexplored phenomenon is c…
Self-supervised and supervised speech models are increasingly used to investigate which linguistic information their internal representations encode, and at what level of abstraction they encode it. One underexplored phenomenon is consonant cluster reduction (CCR) in African Amer…