arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2505.02469cs.LGcs.SD
收藏

使用二值神经网络在关键词检测中进行高效的持续学习

Efficient Continual Learning in Keyword Spotting using Binary Neural Networks

Department of Computer and Electrical Engineering, Mid Sweden University(计算机与电气工程系,Mid Sweden大学);Department of Information Technology and Electrical Engineering, ETH Zürich(信息科技与电气工程系,ETH Zürich)

Quynh Nguyen-Phuong Vu, Luciano Sebastian Martinez-Rau, Yuxuan Zhang, Nho-Duc Tran, Bengt Oelmann, Michele Magno, Sebastian Bader

AI总结:

针对资源受限设备中KWS模型静态化无法适应新关键词的问题,提出基于二值神经网络的持续学习框架,评估七种CL技术实现新词无缝集成,在保持高准确率的同时验证了其计算高效性。

摘要:

关键词检测(KWS)是一项基本功能,能够实现与无处不在的智能设备的交互。然而,在资源受限的设备中,KWS模型通常是静态的,因此无法适应新场景,例如添加的关键词。为了克服这个问题,我们提出了一种基于二值神经网络(BNNs)的KWS持续学习(CL)方法。该框架利用了BNNs降低的计算和内存需求,同时结合了能够随时间无缝集成新关键词的技术。本研究在一个16类用例上评估了七种CL技术,报告显示对于单个额外关键词,准确率超过95%,对于四个额外类别,准确率高达86%。研究中还评估了对CL阶段训练样本数量的敏感性,以及计算复杂度方面的差异。这些评估表明,基于批次的算法对CL数据集大小更敏感,并且计算复杂度之间的差异并不显著。这些发现突出了开发一种有效且计算高效的技术以在KWS应用中持续集成新关键词的潜力,该技术与资源受限设备兼容。

英文摘要:

Keyword spotting (KWS) is an essential function that enables interaction with ubiquitous smart devices. However, in resource-limited devices, KWS models are often static and can thus not adapt to new scenarios, such as added keywords. To overcome this problem, we propose a Continual Learning (CL) approach for KWS built on Binary Neural Networks (BNNs). The framework leverages the reduced computation and memory requirements of BNNs while incorporating techniques that enable the seamless integration of new keywords over time. This study evaluates seven CL techniques on a 16-class use case, reporting an accuracy exceeding 95% for a single additional keyword and up to 86% for four additional classes. Sensitivity to the amount of training samples in the CL phase, and differences in computational complexities are being evaluated. These evaluations demonstrate that batch-based algorithms are more sensitive to the CL dataset size, and that differences between the computational complexities are insignificant. These findings highlight the potential of developing an effective and computationally efficient technique for continuously integrating new keywords in KWS applications that is compatible with resource-constrained devices.

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。

↑