CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Towards End-to-End Speech Recognition for Chinese Mandarin using Long Short-Term Memory Recurrent Neural Networks
Jie Li; Heng Zhang; Xinyuan Cai; Bo Xu
2016-09
Conference NameInterspeech2015
Source PublicationInterspeech 2015
Conference Date2016.9.6-2016.9.10
Conference PlaceDersen,German
AbstractEnd-to-end speech recognition systems have been successfully designed for English. Taking into account the distinctive characteristics between Chinese Mandarin and English, it is worthy to do some additional work to transfer these approaches to Chinese. In this paper, we attempt to build a Chinese speech recognition system using end-to-end learning method. The system is based on a combination of deep Long Short-Term Memory Projected (LSTMP) network architecture and the Connectionist Temporal Classification objective function (CTC). The Chinese characters (the number is about 6,000) are used as the output labels directly. To integrate language model information during decoding, the CTC Beam Search method is adopted and optimized to make it more effective and more efficient. We present the first-pass decoding results which are obtained by decoding from scratch using CTC-trained network and language model. Although these results are not as good as the performance of DNN-HMMs hybrid system, they indicate that it is feasible to choose Chinese characters as the output alphabet in the end-toend speech recognition system.
KeywordLong Short-term Memory End-to-end Connectionist Temporal Classification Speech Recognition
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12486
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Corresponding AuthorBo Xu
AffiliationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Jie Li,Heng Zhang,Xinyuan Cai,et al. Towards End-to-End Speech Recognition for Chinese Mandarin using Long Short-Term Memory Recurrent Neural Networks[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
i15_3615.pdf(531KB)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
[Jie Li]'s Articles
[Heng Zhang]'s Articles
[Xinyuan Cai]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jie Li]'s Articles
[Heng Zhang]'s Articles
[Xinyuan Cai]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jie Li]'s Articles
[Heng Zhang]'s Articles
[Xinyuan Cai]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: i15_3615.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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