Virtual Adversarial Training and Data Augmentation for Acoustic Event Detection with Gated Recurrent Neural Networks

被引：9

作者：

Zoehrer, Matthias ^{[1
]}

Pernkopf, Franz ^{[1
]}

机构：

[1] Graz Univ Technol, Signal Proc & Speech Commun Lab, Intelligent Syst Grp, Graz, Austria

来源：

18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION | 2017年

基金：

奥地利科学基金会;

关键词：

Acoustic event detection; gated recurrent networks; data augmentation; virtual adversarial training;

D O I：

10.21437//nterspeech.2017-1238

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we use gated recurrent neural networks (GRNNs) for efficiently detecting environmental events of the IEEE Detection and Classification of Acoustic Scenes and Events challenge (DCASE2016). For this acoustic event detection task data is limited. Therefore, we propose data augmentation such as on-the fly shuffling and virtual adversarial training for regularization of the GRNNs. Both improve the performance using GRNNs. We obtain a segment-based error rate of 0.59 and an F-score of 58.6%.

引用

页码：493 / 497

页数：5