Knowledge Commons of Institute of Automation,CAS
Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin | |
Dong, Linhao1,2; Zhou, Shiyu1,2; Chen, Wei1; Xu, Bo1 | |
2018-09 | |
会议名称 | Nineteenth Annual Conference of the International Speech Communication Association (INTERSPEECH) |
页码 | 816-820 |
会议日期 | 2018-09 |
会议地点 | Hyderabad, India |
出版者 | IEEE Xplore |
摘要 | End-to-end models have been showing superiority in Automatic Speech Recognition (ASR). At the same time, the capacity of streaming recognition has become a growing requirement for end-to-end models. Following these trends, an encoder-decoder recurrent neural network called Recurrent Neural Aligner (RNA) has been freshly proposed and shown its competitiveness on two English ASR tasks. However, it is not clear if RNA can be further improved and applied to other spoken language. In this work, we explore the applicability of RNA in Mandarin Chinese and present four effective extensions: In the encoder, we redesign the temporal down-sampling and introduce a powerful convolutional structure. In the decoder, we utilize a regularizer to smooth the output distribution and conduct joint training with a language model. On two Mandarin Chinese conversational telephone speech recognition (MTS) datasets, our Extended-RNA obtains promising performance. Particularly, it achieves 27.7% character error rate (CER), which is superior to current state-of-the-art result on the popular HKUST task. |
关键词 | speech recognition recurrent neural aligner mandarin end-to-end |
学科门类 | 工学 |
收录类别 | EI |
资助项目 | Beijing Science and Technology Program[Z171100002217015] ; Beijing Science and Technology Program[Z171100002217015] |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39275 |
专题 | 复杂系统认知与决策实验室_听觉模型与认知计算 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, China 2.University of Chinese Academy of Sciences, China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Dong, Linhao,Zhou, Shiyu,Chen, Wei,et al. Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin[C]:IEEE Xplore,2018:816-820. |
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 | ||
Extending Recurrent (321KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论