Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition
Dong, Linhao1,2; Xu, Shuang1; Xu, Bo1
2018-04
会议名称International Conference on Acoustics, Speech and Signal Processing (ICASSP)
页码5884-5888
会议日期2018-04
会议地点Calgary, Canada
出版者IEEE Xplore
产权排序1
摘要

Recurrent sequence-to-sequence models using encoder-decoder architecture have made great progress in speech recognition task. However, they suffer from the drawback of slow training speed because the internal recurrence limits the training parallelization. In this paper, we present the Speech-Transformer, a no-recurrence sequence-to-sequence model entirely relies on attention mechanisms to learn the positional dependencies, which can be trained faster with more efficiency. We also propose a 2D-Attention mechanism, which can jointly attend to the time and frequency axes of the 2-dimensional speech inputs, thus providing more expressive representations for the Speech-Transformer. Evaluated on the Wall Street Journal (WSJ) speech recognition dataset, our best model achieves competitive word error rate (WER) of 10.9%, while the whole training process only takes 1.2 days on 1 GPU, significantly faster than the published results of recurrent sequence-to-sequence models.

关键词speech recognition sequence-to-sequence attention transformer
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]
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/39274
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,Xu, Shuang,Xu, Bo. Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition[C]:IEEE Xplore,2018:5884-5888.
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
Speech-Transformer_A(640KB)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
[Dong, Linhao]的文章
[Xu, Shuang]的文章
[Xu, Bo]的文章
百度学术
百度学术中相似的文章
[Dong, Linhao]的文章
[Xu, Shuang]的文章
[Xu, Bo]的文章
必应学术
必应学术中相似的文章
[Dong, Linhao]的文章
[Xu, Shuang]的文章
[Xu, Bo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Speech-Transformer_A No-Recurrence Sequence-to-Sequence Model for Speech Recognition.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。