CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition | |
Dong, Linhao1,2; Xu, Bo2 | |
2020-05 | |
会议日期 | 2020-05 |
会议地点 | 在线会议 |
关键词 | continuous integrate-and-fire end-to-end model soft and monotonic alignment online speech recognition acoustic boundary positioning |
英文摘要 | In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of continuous functions, thus being named as: Continuous Integrate-and-Fire (CIF). Applied to the ASR task, CIF not only shows a concise calculation, but also supports online recognition and acoustic boundary positioning, thus suitable for various ASR scenarios. Several support strategies are also proposed to alleviate the unique problems of CIF-based model. With the joint action of these methods, the CIF-based model shows competitive performance. Notably, it achieves a word error rate (WER) of 2.86% on the test-clean of Librispeech and creates new state-of-the-art result on Mandarin telephone ASR benchmark. |
会议录出版者 | IEEE Xplore |
资助项目 | Beijing Municipal Science and Technology Project[Z181100008918017] |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/39277] |
专题 | 数字内容技术与服务研究中心_听觉模型与认知计算 |
作者单位 | 1.University of Chinese Academy of Sciences, China 2.Institute of Automation, Chinese Academy of Sciences, China |
推荐引用方式 GB/T 7714 | Dong, Linhao,Xu, Bo. CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition[C]. 见:. 在线会议. 2020-05. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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