CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Multilingual Recurrent Neural Networks with Residual Learning for Low-Resource Speech Recognition
Shiyu Zhou1,2; Yuanyuan Zhao1,2; Shuang Xu1; Bo Xu1
2017
Conference NameInterspeech
Source PublicationInterspeech
Conference Date2017
Conference PlaceStockholm
AbstractThe shared-hidden-layer multilingual deep neural network (SHL-MDNN), in which the hidden layers of feed-forward deep neural network (DNN) are shared across multiple languages while the softmax layers are language dependent, has been shown to be effective on acoustic modeling of multilingual low-resource speech recognition. In this paper, we propose that the shared-hidden-layer with Long Short-Term Memory (LSTM) recurrent neural networks can achieve further performance improvement considering LSTM has outperformed DNN as the acoustic model of automatic speech recognition (ASR). Moreover, we reveal that shared-hidden-layer multilingual LSTM (SHL-MLSTM) with residual learning can yield additional moderate but consistent gain from multilingual tasks given the fact that residual learning can allievate the degradation problem of deep LSTMs. Experimental results demonstrate that SHL-MLSTM can relatively reduce word error rate (WER) by 2.1-6.8\% over SHL-MDNN trained using six languages and 2.6-7.3\% over monolingual LSTM trained using the language specific data on CALLHOME datasets. Additional WER reduction, about relatively 2\% over SHL-MLSTM, can be obtained through residual learning on CALLHOME datasets, which demonstrates residual learning is useful for SHL-MLSTM on multilingual low-resource ASR.
KeywordLstm Multilingual Speech Recognition Low-resource Residual Learning Shared-hidden-layer
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15421
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Corresponding AuthorShiyu Zhou
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Shiyu Zhou,Yuanyuan Zhao,Shuang Xu,et al. Multilingual Recurrent Neural Networks with Residual Learning for Low-Resource Speech Recognition[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
Multilingual Recurre(269KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shiyu Zhou]'s Articles
[Yuanyuan Zhao]'s Articles
[Shuang Xu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shiyu Zhou]'s Articles
[Yuanyuan Zhao]'s Articles
[Shuang Xu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shiyu Zhou]'s Articles
[Yuanyuan Zhao]'s Articles
[Shuang Xu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multilingual Recurrent Neural Networks with Residual Learning for Low-Resource Speech Recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.