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 2309.09413cs.SDeess.AS
收藏

软提示是语音识别中良好的零样本学习器吗?

Are Soft Prompts Good Zero-shot Learners for Speech Recognition?

Alibaba Group(阿里巴巴集团);Alibaba-NTU Singapore Joint Research Institute(阿里巴巴-新加坡南洋理工大学联合研究院);Nanyang Technological University(南洋理工大学)

Dianwen Ng, Chong Zhang, Ruixi Zhang, Yukun Ma, Fabian Ritter-Gutierrez, Trung Hieu Nguyen, Chongjia Ni, Shengkui Zhao, Eng Siong Chng, Bin Ma

AI总结:

本文探究软提示在语音识别中的零样本学习能力,揭示其内容细化与噪声增强作用,并提出噪声提示修改方法以提升对分布外噪声的适应性。

摘要:

大型自监督预训练语音模型在下游任务中需要计算成本高昂的微调。软提示调优通过利用最少的软提示引导,提供了一种简单的参数高效替代方案,在保持竞争性能的同时增强了可移植性。然而,许多人并不理解这是如何以及为何实现的。在本研究中,我们旨在通过探究软提示在自动语音识别(ASR)中的作用来加深对这一新兴方法的理解。我们的发现强调了它们作为零样本学习器在提升ASR性能方面的作用,但也使其容易受到恶意修改的影响。软提示有助于泛化,但并非推理所必需。我们还识别出软提示的两个主要作用:内容细化和噪声信息增强,这增强了对背景噪声的鲁棒性。此外,我们提出了一种对噪声提示的有效修改,以表明它们能够在适应分布外噪声环境方面进行零样本学习。

英文摘要:

Large self-supervised pre-trained speech models require computationally expensive fine-tuning for downstream tasks. Soft prompt tuning offers a simple parameter-efficient alternative by utilizing minimal soft prompt guidance, enhancing portability while also maintaining competitive performance. However, not many people understand how and why this is so. In this study, we aim to deepen our understanding of this emerging method by investigating the role of soft prompts in automatic speech recognition (ASR). Our findings highlight their role as zero-shot learners in improving ASR performance but also make them vulnerable to malicious modifications. Soft prompts aid generalization but are not obligatory for inference. We also identify two primary roles of soft prompts: content refinement and noise information enhancement, which enhances robustness against background noise. Additionally, we propose an effective modification on noise prompts to show that they are capable of zero-shot learning on adapting to out-of-distribution noise environments.

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。

↑