arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.07388eess.AScs.LGcs.SDeess.SP
收藏

自监督语音表征学习中的条件独立性

Conditional independence for pretext task selection in Self-supervised speech representation learning

Salah Zaiem, Titouan Parcollet, Slim Essid

摘要:

通过解决借口任务,自监督学习(SSL)利用未标记的数据来提取有用的潜在表示,以取代下游任务中的传统输入特征。一个常见的借口任务包括在从原始信号中导出的伪标签上预训练SSL模型。该技术特别与语音数据相关,其中各种有意义的信号处理特征可以用作伪标签。然而,为语音或其他类型的数据选择伪标签的过程仍然是未开发的,目前依赖于观察最终下游任务的结果。然而,由于大量的计算(因此碳)成本,这种方法在规模上是不可持续的。因此,本文介绍了一个实用的和理论的框架来选择相关的伪标签相对于一个给定的下游任务。更确切地说,我们提出了一个基于条件独立理论的伪标签效用函数估计器,它不需要任何训练。对说话人识别和自动语音识别进行的实验验证了我们的估计器,显示出在下游任务上观察到的性能与我们的方法获得的效用估计之间的显着相关性,促进了自监督语音表示学习的相关伪标签的前景。

英文摘要:

Through solving pretext tasks, self-supervised learning (SSL) leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task. A common pretext task consists in pretraining a SSL model on pseudo-labels derived from the original signal. This technique is particularly relevant for speech data where various meaningful signal processing features may serve as pseudo-labels. However, the process of selecting pseudo-labels, for speech or other types of data, remains mostly unexplored and currently relies on observing the results on the final downstream task. Nevertheless, this methodology is not sustainable at scale due to substantial computational (hence carbon) costs. Thus, this paper introduces a practical and theoretical framework to select relevant pseudo-labels with respect to a given downstream task. More precisely, we propose a functional estimator of the pseudo-label utility grounded in the conditional independence theory, which does not require any training. The experiments conducted on speaker recognition and automatic speech recognition validate our estimator, showing a significant correlation between the performance observed on the downstream task and the utility estimates obtained with our approach, facilitating the prospection of relevant pseudo-labels for self-supervised speech representation learning.

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。

↑