基于层次子空间的声单元发现模型
A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
摘要：
在这项工作中，我们提出了一个层次子空间模型的声学单元发现。在这种方法中，我们框架的任务作为一个低维语音子空间上的学习嵌入，同时指定子空间本身作为一个超子空间上的嵌入。我们训练的超子空间上的一组转录的语言，并将其转移到目标语言。在目标语言中，我们以无监督的方式推断语言和单元嵌入，并且在这样做的过程中，我们同时学习特定于该语言的单元的子空间以及驻留在其上的单元。我们对TIMIT和两种低资源语言进行了实验：Mboshi和Yoruba。结果表明，我们的模型优于主要的声学单元发现技术，无论是在聚类质量和分割精度。
英文摘要：
In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this approach, we frame the task as one of learning embeddings on a low-dimensional phonetic subspace, and simultaneously specify the subspace itself as an embedding on a hyper-subspace. We train the hyper-subspace on a set of transcribed languages and transfer it to the target language. In the target language, we infer both the language and unit embeddings in an unsupervised manner, and in so doing, we simultaneously learn a subspace of units specific to that language and the units that dwell on it. We conduct our experiments on TIMIT and two low-resource languages: Mboshi and Yoruba. Results show that our model outperforms major acoustic unit discovery techniques, both in terms of clustering quality and segmentation accuracy.
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。
