Knowledge Commons of Institute of Automation,CAS
CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition | |
Jiangyan Yi; Zhengqi Wen; Jianhua Tao; Hao Ni; Bin Liu | |
发表期刊 | JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY |
2018 | |
卷号 | 90期号:7页码:985-997 |
摘要 | This paper proposes a novel regularized adaptation method to improve the performance of multi-accent Mandarin speech recognition task. The acoustic model is based on long short term memory recurrent neural network trained with a connectionist temporal classification loss function (LSTM-RNN-CTC). In general, directly adjusting the network parameters with a small adaptation set may lead to over-fitting. In order to avoid this problem, a regularization term is added to the original training criterion. It forces the conditional probability distribution estimated from the adapted model to be close to the accent independent model. Meanwhile, only the accent-specific output layer needs to be fine-tuned using this adaptation method. Experiments are conducted on RASC863 and CASIA regional accented speech corpus. The results show that the proposed method obtains obvious improvement when compared with LSTM-RNN-CTC baseline model. It also outperforms other adaptation methods. |
关键词 | multi-accent, Mandarin speech recognition,LSTM-RNN-CTC, model adaptation, CTC regularization |
WOS研究方向 | 中文 ; 英语 ; 德语 ; 法语 ; 日语 ; 俄语 ; 其他 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40661 |
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.中国科学院大学; 2.中国科学院兰州文献情报中心 |
推荐引用方式 GB/T 7714 | Jiangyan Yi,Zhengqi Wen,Jianhua Tao,et al. CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition[J]. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY,2018,90(7):985-997. |
APA | Jiangyan Yi,Zhengqi Wen,Jianhua Tao,Hao Ni,&Bin Liu.(2018).CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition.JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY,90(7),985-997. |
MLA | Jiangyan Yi,et al."CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition".JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 90.7(2018):985-997. |
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 | ||
1期刊-CTC Regularized (1416KB) | 期刊论文 | 作者接受稿 | 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