arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.06232cs.CLcs.SDeess.AS
收藏

探究自监督语音模型中的语音与音位信息:以送气特征为例的个案研究

Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration

Massachusetts Institute of Technology(麻省理工学院)

Kinan Martin, Jon Gauthier, Canaan Breiss, Roger Levy

AI总结:

该研究以词首塞音送气特征为例,探究自监督语音模型编码的语言信息,发现语音和音位区分表征在模型早期层出现且深层主成分可保留,其成效源于语音数据优化与高维架构,且语音训练的HuBERT可生成对应抽象音系区分的低噪声低维子空间。

摘要:

近年来,无文本自监督语音模型的能力不断提升,但它们所编码的语言信息的本质尚未得到彻底研究。我们评估了这些模型的学习表征与人类做出的基本表征区分的对齐程度,重点关注词首塞音中体现的一组语音(低层)和音位(更抽象)对比。我们发现,语音和音位区分的稳健表征均出现在这些模型架构的早期层中,并且在更深层表征的主成分中得以保留。我们的分析表明,这种成功有两个来源:一部分只能通过模型在语音数据上的优化来解释,另一部分则可归因于这些模型的高维架构。我们的研究结果表明,经语音训练的HuBERT衍生出了一个与抽象音系区分对应的低噪声、低维子空间。

英文摘要:

Textless self-supervised speech models have grown in capabilities in recent years, but the nature of the linguistic information they encode has not yet been thoroughly examined. We evaluate the extent to which these models' learned representations align with basic representational distinctions made by humans, focusing on a set of phonetic (low-level) and phonemic (more abstract) contrasts instantiated in word-initial stops. We find that robust representations of both phonetic and phonemic distinctions emerge in early layers of these models' architectures, and are preserved in the principal components of deeper layer representations. Our analyses suggest two sources for this success: some can only be explained by the optimization of the models on speech data, while some can be attributed to these models' high-dimensional architectures. Our findings show that speech-trained HuBERT derives a low-noise and low-dimensional subspace corresponding to abstract phonological distinctions.

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。

↑