Consecutive decoding for speech-to-text translation | |
Dong QQ(董倩倩) | |
2021-02 | |
会议日期 | 2021-2 |
会议地点 | Virtual |
英文摘要 | 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. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44967] ![]() |
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 | Institute of Automation,Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Dong QQ. Consecutive decoding for speech-to-text translation[C]. 见:. Virtual. 2021-2. |
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