arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.12503eess.AS
收藏

无监督在线持续学习用于自动语音识别

Unsupervised Online Continual Learning for Automatic Speech Recognition

KU Leuven(荷语鲁汶大学)

Steven Vander Eeckt, Hugo Van hamme

AI总结:

本文提出无监督在线持续学习方法,通过自训练实现ASR模型在无标签数据下的持续适应,有效减少灾难性遗忘,提升模型在多领域应用中的性能。

摘要:

将自动语音识别(ASR)模型适应到新领域会导致灾难性遗忘(CF)的出现。本文针对在线持续学习(OCL)这一具有挑战性的场景,即任务以未知边界持续的数据流呈现,提出了扩展OCL到ASR的无监督领域。通过利用自训练(ST)来促进无监督适应,使模型能够在没有标签依赖和不遗忘先前知识的情况下持续适应。通过在两个领域适应实验中比较各种OCL和ST方法,我们发现UOCL相比监督OCL显著减少了遗忘,使UOCL方法能够接近监督OCL的性能水平。我们提出的UOCL扩展进一步提升了UOCL的效果。我们的发现代表了朝着能够利用不同领域无标签数据的持续适应ASR系统迈出的重要一步。

英文摘要:

Adapting Automatic Speech Recognition (ASR) models to new domains leads to Catastrophic Forgetting (CF) of previously learned information. This paper addresses CF in the challenging context of Online Continual Learning (OCL), with tasks presented as a continuous data stream with unknown boundaries. We extend OCL for ASR into the unsupervised realm, by leveraging self-training (ST) to facilitate unsupervised adaptation, enabling models to adapt continually without label dependency and without forgetting previous knowledge. Through comparative analysis of various OCL and ST methods across two domain adaptation experiments, we show that UOCL suffers from significantly less forgetting compared to supervised OCL, allowing UOCL methods to approach the performance levels of supervised OCL. Our proposed UOCL extensions further boosts UOCL's efficacy. Our findings represent a significant step towards continually adaptable ASR systems, capable of leveraging unlabeled data across diverse domains.

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。

↑