Knowledge Commons of Institute of Automation,CAS
An End-to-end Structure with CTC Encoder and OCD Decoder For Speech Recognition | |
Cheng, Yi1,2; Feng, Wang1; Bo, Xu1 | |
2019-09 | |
会议名称 | Proceedings of the Conference of the International Speech Communication Association(INTERSPEECH) |
会议日期 | 2019-9 |
会议地点 | Graz, Austria |
摘要 | Real-time streaming speech recognition is required by most applications for a nice interactive experience. To naturally support online recognition, a common strategy used in recently proposed end-to-end models is to introduce a blank label to the label set and instead output alignments. However, generating the alignment means decoding much longer than the length of the linguistic sequence. Besides, there exist several blank labels between two output units in the alignment, which hinders models from learning the adjacent dependency of units in the target sequence. In this work, we propose an innovative encoder-decoder structure, called ECTC-DOCD, for online speech recognition which directly predicts the linguistic sequence without blank labels. Apart from the encoder and decoder structures, ECTC-DOCD contains an additional shrinking layer to drop the redundant acoustic information. This layer serves as a bridge connecting acoustic representation and linguistic modelling parts. Through experiments, we confirm that ECTC-DOCD can obtain better performance than a strong CTC model in online ASR tasks. We also show that ECTC-DOCD can achieve promising results on both Mandarin and English ASR datasets with first and second pass decoding. |
关键词 | end-to-end, streaming ASR, encoder-decoder, OCD, CTC |
学科门类 | 工学 |
收录类别 | EI |
七大方向——子方向分类 | 语音识别与合成 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44878 |
专题 | 复杂系统认知与决策实验室_听觉模型与认知计算 |
通讯作者 | Cheng, Yi |
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 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Cheng, Yi,Feng, Wang,Bo, Xu. An End-to-end Structure with CTC Encoder and OCD Decoder For Speech Recognition[C],2019. |
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 | ||
Ectc-Docd An End-to-(604KB) | 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