.png){kind=icon}
返回
Learning Self-Informed Feature Contribution for Deep Learning-Based Acoustic Modeling
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2018.2858923.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we introduce a new feature engineering approach for deep learning-based acoustic modeling, which utilizes input feature contributions. For this purpose, we propose an auxiliary deep neural network (DNN) called a feature contribution network (FCN) whose output layer is composed of sigmoid-based contribution gates. In our framework, the FCN tries to learn element-level discriminative contributions of input features and an acoustic model network (AMN) is trained by gated features generated by element-wise multiplication between contribution gate outputs and input features. In addition, we also propose a regularization method for the FCN, which helps the FCN to activate the minimum number of the gates. The proposed methods were evaluated on the TED-LIUM release 1 corpus. We applied the proposed methods to DNN- and long short-term memory-based AMNs. Experimental results results showed that AMNs with the FCNs consistently improved recognition performance compared with AMN-only frameworks.
Keyword:
Acoustic modeling
deep learning
feature contribution network
speech recognition
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
暂无机构信息
引用论文
分享收藏Microtubule Stabilization Reduces Scarring and Causes Axon Regeneration After Spinal Cord Injury.png)
Science
OAAI
ScienceIF0
OAAI分享收藏
查看更多内容