Knowledge Commons of Institute of Automation,CAS
Consecutive decoding for speech-to-text translation | |
Dong QQ(董倩倩)1,2; Mingxuan Wang(王明轩)3; Hao Zhou(周浩)3; Shuang Xu(徐爽)1; Bo Xu(徐波)1,2; Lei Li(李磊)3 | |
2021-02 | |
会议名称 | In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-2021) |
会议日期 | 2021-2 |
会议地点 | Virtual |
摘要 | Speech-to-text translation (ST), which directly translates the source language speech to the target language text, has at- tracted intensive attention recently. However, the combina- tion of speech recognition and machine translation in a single model poses a heavy burden on the direct cross-modal cross- lingual mapping. To reduce the learning difficulty, we pro- pose COnSecutive Transcription and Translation (COSTT), an integral framework for speech-to-text translation. Our method is verified on three mainstream datasets, includ- ing Augmented LibriSpeech English-French dataset, TED English-German dataset, and TED English-Chinese dataset. Experiments show that our proposed COSTT outperforms the previous state-of-the-art methods. Our code and models will be released. |
收录类别 | EI |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 其他 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44967 |
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 | Bo Xu(徐波) |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.ByteDance AI Lab, 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 | Dong QQ,Mingxuan Wang,Hao Zhou,et al. Consecutive decoding for speech-to-text translation[C],2021. |
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 | ||
_AAAI2021__Consecuti(586KB) | 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