Knowledge Commons of Institute of Automation,CAS
Rnn-transducer With Language Bias For End-to-end Mandarin-English Code-switching Speech Recognition | |
Shuai Zhang1,2![]() | |
2021-03-01 | |
会议名称 | International Symposium on Chinese Spoken Language Processing (ISCSLP) |
会议日期 | 2021-1-24 |
会议地点 | Hong Kong |
摘要 | Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition task. However, previous work use an additional language identification (LID) model as an auxiliary module, which increases computation cost. In this work, we propose an improved recurrent neural network transducer (RNN-T) model with language bias to alleviate the problem. We use the language identities to bias the model to predict the CS points. This promotes the model to learn the language identity information directly from transcriptions, and no additional LID model is needed. We evaluate the approach on a Mandarin-English CS corpus SEAME. Compared to our RNN-T baseline, the RNN-T with language bias can achieve 16.2% and 12.9% relative mixed error reduction on two test sets, respectively. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48817 |
专题 | 多模态人工智能系统全国重点实验室_智能交互 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, China 2.NLPR, Institute of Automation, Chinese Academy of Sciences, China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Shuai Zhang. Rnn-transducer With Language Bias For End-to-end Mandarin-English Code-switching Speech Recognition[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 | ||
Rnn-transducer_With_(1191KB) | 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 |
[Shuai Zhang]的文章 |
百度学术 |
百度学术中相似的文章 |
[Shuai Zhang]的文章 |
必应学术 |
必应学术中相似的文章 |
[Shuai Zhang]的文章 |
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