DEEP RECURRENT REGULARIZATION NEURAL NETWORK FOR SPEECH RECOGNITION

檔案

本條目沒有附加檔案。

日期

2015

系所

期刊名稱

2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP)

卷期與頁次

頁 4560–4564

ISSN

1520-6149

ISBN

978-1-4673-6997-8

語言

英文

摘要

This paper presents a deep recurrent regularization neural network (DRRNN) for speech recognition. Our idea is to build a regularization neural network acoustic model by conducting the hybrid Tikhonov and weight-decay regularization which compensates the variations due to the input speech as well as the model parameters in the restricted Boltzmann machine as a pre-training stage for feature learning and structural modeling. In addition, a new backpropagation through time (BPTT) algorithm is developed by extending the truncated minibatch training for recurrent neural network where the minibatch BPTT is not only performed in recurrent layer but also in feedforward layer. The DRRNN acoustic model is accordingly established to capture the temporal correlation in a regularization neural network. Experimental results on the tasks of RM and Aurora4 show the effectiveness and robustness of using DRRNN for speech recognition.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Chien, J.-T., & Lu, T.-W. (2015). DEEP RECURRENT REGULARIZATION NEURAL NETWORK FOR SPEECH RECOGNITION. 2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 4560–4564. https://ir.lib.nycu.edu.tw/handle/11536/135716

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/135716