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 1706.03256cs.LG
收藏

基于渐进神经网络的情绪识别迁移学习

Progressive Neural Networks for Transfer Learning in Emotion Recognition

University of Michigan at Ann Arbor(密歇根大学安娜堡分校);IBM T. J. Watson Research Center(IBM托马斯·J·沃森研究中心)

John Gideon, Soheil Khorram, Zakaria Aldeneh, Dimitrios Dimitriadis, Emily Mower Provost

摘要:

许多非语言学任务是密切相关的,因此在一个领域中学习的表征可以用于另一个领域。在本文中,我们研究了知识如何可以转移之间的三个非语言任务:扬声器,情绪,性别识别。此外,我们将这个问题扩展到跨数据集任务,询问如何将一个情感数据集中捕获的知识转移到另一个数据集中。我们专注于渐进式神经网络,并将这些网络与传统的预训练和微调的深度学习方法进行比较。渐进式神经网络提供了一种传递知识的方法,并避免了在不同任务上预训练神经网络时存在的遗忘效应。我们的实验表明:(1)情感识别可以受益于使用最初为不同的语言任务学习的表示,以及(2)迁移学习可以有效地利用附加的数据集来提高情感识别系统的性能。

英文摘要:

Many paralinguistic tasks are closely related and thus representations learned in one domain can be leveraged for another. In this paper, we investigate how knowledge can be transferred between three paralinguistic tasks: speaker, emotion, and gender recognition. Further, we extend this problem to cross-dataset tasks, asking how knowledge captured in one emotion dataset can be transferred to another. We focus on progressive neural networks and compare these networks to the conventional deep learning method of pre-training and fine-tuning. Progressive neural networks provide a way to transfer knowledge and avoid the forgetting effect present when pre-training neural networks on different tasks. Our experiments demonstrate that: (1) emotion recognition can benefit from using representations originally learned for different paralinguistic tasks and (2) transfer learning can effectively leverage additional datasets to improve the performance of emotion recognition systems.

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。

↑