研究人员调查了自监督语音模型是否能准确识别不常见的语音声音，特别是科伊桑语系中发现的舌侧塞音。通过在 G|ui 和 West !Xoon 的数据上微调 Wav2Vec2 和 HuBERT 等模型，他们发现这些模型确实比非舌侧塞音更能有效地识别舌侧塞音。这表明自监督学习使这些模型能够跨越更广泛的人类音素进行泛化，即使是那些在典型训练数据中很少遇到的音素。 AI
影响 证明了自监督模型可以泛化到稀有音素，有可能改善低资源语言的自动语音识别。
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 →
完整方法见我们的编辑标准。
arXiv:2606.11542v1 Announce Type: cross Abstract: Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized representations. However, their training data are heavily skewed toward high-resource…
Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized representations. However, their training data are heavily skewed toward high-resource languages with little data from low-resource lang…