Rnn-transducer With Language Bias For End-to-end Mandarin-English Code-switching Speech Recognition | |
Shuai Zhang1,2 | |
2021-03-01 | |
会议日期 | 2021-1-24 |
会议地点 | Hong Kong |
英文摘要 | 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. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48817] |
专题 | 模式识别国家重点实验室_智能交互 |
作者单位 | 1.NLPR, Institute of Automation, Chinese Academy of Sciences, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, China |
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]. 见:. Hong Kong. 2021-1-24. |
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