arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.08833eess.AScs.CLcs.SD
收藏

从互信息视角重新审视语音表征的自监督学习

Revisiting Self-supervised Learning of Speech Representation from a Mutual Information Perspective

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);University of Edinburgh, Informatics(爱丁堡大学信息学院)

Alexander H. Liu, Sung-Lin Yeh, James Glass

AI总结:

本文从互信息视角重新审视自监督语音表征学习,提出基于线性探针的监督与无监督度量方法,用于评估表征对目标信息的可获取性,并验证其与下游任务表现的一致性。

摘要:

现有的自监督语音表征学习研究主要集中在开发新的训练方法以及将预训练模型应用于不同任务上。然而,这些模型的质量往往通过不同下游任务的表现来衡量,而表征能够在多大程度上获取所关注信息的问题则研究较少。本文从信息论视角对现有语音自监督方法进行更深入的分析。我们旨在利用互信息开发度量指标,以帮助解决模型设计和选择等实际问题。我们使用线性探针估计目标信息与所学表征之间的互信息,从而从另一个角度揭示语音表征对目标信息的可获取性。此外,我们探索了以自监督方式评估表征的潜力,即在不使用任何标签的情况下估计数据不同部分之间的互信息。最后,我们表明,监督和无监督度量均能在逐层线性探针和语音识别任务上与模型性能表现出一致性。

英文摘要:

Existing studies on self-supervised speech representation learning have focused on developing new training methods and applying pre-trained models for different applications. However, the quality of these models is often measured by the performance of different downstream tasks. How well the representations access the information of interest is less studied. In this work, we take a closer look into existing self-supervised methods of speech from an information-theoretic perspective. We aim to develop metrics using mutual information to help practical problems such as model design and selection. We use linear probes to estimate the mutual information between the target information and learned representations, showing another insight into the accessibility to the target information from speech representations. Further, we explore the potential of evaluating representations in a self-supervised fashion, where we estimate the mutual information between different parts of the data without using any labels. Finally, we show that both supervised and unsupervised measures echo the performance of the models on layer-wise linear probing and speech recognition.

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。

↑