东篱科研大数据发现系统（DRDS）

位置：成果数据库 > 期刊 > 期刊详情页

A forced alignment approach to detect Chinese repetitive stuttering

ISSN号：0217-9776
期刊名称：《声学学报：英文版》
时间：0
分类：TP319[自动化与计算机技术—计算机软件与理论;自动化与计算机技术—计算机科学与技术] TP335.4[自动化与计算机技术—计算机系统结构;自动化与计算机技术—计算机科学与技术]
作者机构：[1]Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences Beijing 100190, [2]Prof. Lin's Speech Training Center Beijing 102600
相关基金：supported by the National Natural Science Foundation of China（10925419,90920302, 61072124,11074275,11161140319,91120001,61271426）; the Strategic Priority Research Program of the Chinese Academy of Sciences（XDA06030100,XDA06030500）; the National 863 Program（2012AA012503）; the CAS Priority Deployment Project（KGZD-EW-103-2）

作者： ZHANG Junbo[1], YAN Qian[2], GAO Xinglong[1], PAN Puping[1], FENG Yongqiang[1], XING Lili[2], LIN Chunlan[2], PAN Jielin[1]

关键词：检测结果, 中国, 对齐, 解码网络, 惩罚因子, 水平检测, 算法, 多跨度

中文摘要：

<正>A forced alignment based algorithms to detect Chinese repetitive stuttering is studied. According to the features of repetitions in Chinese stuttered speech,improvement solutions are provided based on the previous research findings.First,a multi-span looping forced alignment decoding networks is designed to detect multi-syllable repetitions in Chinese stuttered speech.Second,branch penalty factor is added in the networks to adjust decoding trend using recursive search in order to reduce the error from the complexity of the decoding networks. Finally,we re-judge the detected stutters by calculating confidence to improve the reliability of the detection result.The experimental results show that compared to previous algorithm,the proposed algorithm can improve system performance significantly,about 18%average detection error rate relatively.

英文摘要：

A forced alignment based algorithms to detect Chinese repetitive stuttering is studied. According to the features of repetitions in Chinese stuttered speech,improvement solutions are provided based on the previous research findings.First,a multi-span looping forced alignment decoding networks is designed to detect multi-syllable repetitions in Chinese stuttered speech.Second,branch penalty factor is added in the networks to adjust decoding trend using recursive search in order to reduce the error from the complexity of the decoding networks. Finally,we re-judge the detected stutters by calculating confidence to improve the reliability of the detection result.The experimental results show that compared to previous algorithm,the proposed algorithm can improve system performance significantly,about 18%average detection error rate relatively.