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
会议名称Interspeech2015
会议录名称Interspeech 2015
会议日期2016.9.6-2016.9.10
会议地点Dersen,German
摘要End-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.
关键词Long Short-term Memory End-to-end Connectionist Temporal Classification Speech Recognition
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12486
专题数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者Bo Xu
作者单位Institute of Automation, Chinese Academy of Sciences
推荐引用方式
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
i15_3615.pdf(531KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Jie Li]的文章
[Heng Zhang]的文章
[Xinyuan Cai]的文章
百度学术
百度学术中相似的文章
[Jie Li]的文章
[Heng Zhang]的文章
[Xinyuan Cai]的文章
必应学术
必应学术中相似的文章
[Jie Li]的文章
[Heng Zhang]的文章
[Xinyuan Cai]的文章
相关权益政策
暂无数据
收藏/分享
文件名: i15_3615.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。