[1]周炳良,邓立新,洪民江. 一种新的基于 DTW 的孤立词语音识别算法[J].计算机技术与发展,2018,28(04):119-123.[doi:10.3969/ j. issn.1673-629X.2018.04.025]
　ZHOU Bing-liang,DENG Li-xin,HONG Min-jiang.A Novel Isolated Word Algorithm of Speech Recognition Based on DTW[J].,2018,28(04):119-123.[doi:10.3969/ j. issn.1673-629X.2018.04.025]
点击复制

 一种新的基于 DTW 的孤立词语音识别算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年04期
页码:
119-123
栏目:
智能、算法、系统工程
出版日期:
2018-04-10

文章信息/Info

Title:
A Novel Isolated Word Algorithm of Speech Recognition Based on DTW
文章编号:
1673-629X(2018)04-0119-05
作者:
周炳良; 邓立新; 洪民江
南京邮电大学 通信与信息工程学院,江苏 南京 210003
Author(s):
ZHOU Bing-liang; DENG Li-xin; HONG Min-jiang
 School of Telecommunications &Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)
关键词:
语音识别; 动态时间规整; 部分匹配; 孤立词
Keywords:
speech recognition; DTW; partial match; isolated word
分类号:
TP301.6
DOI:
10.3969/ j. issn.1673-629X.2018.04.025
文献标志码:
A
摘要:
为了提高传统孤立词语音识别系统中 DTW(动态时间规整)算法的识别效率,提出了一种新的基于 DTW 的孤立词语音识别算法。 该算法针对语音识别阶段的方法进行改进：首先对输入的测试语音信号进行预处理,包括预加重、分帧加窗和端点检测,然后提取预处理语音信号的特征参数矢量,并通过截取测试语音特征矢量起始部分长度与库模板矢量进行最优路径匹配(最优时间规整),匹配后只保留失真度较小的部分库模板矢量继续进行下一轮最优路径匹配,如此反复截取测试语音特征矢量的起始不同部分进行最优路径匹配与参考模板保留,直至参考模板保留唯一。 实验结果表明,与传统 DTW 算法相比,该算法在保证识别精度不变的前提下,能大幅减少孤立词语音识别系统的计算开销,有效提高孤立词语音识别系统的识别效率。
Abstract:
In order to improve the recognition efficiency of dynamic time warping (DTW) algorithm in traditional isolated word recognition system,we propose a new isolated word speech recognition algorithm based on DTW. It has made improvements on the contents of speech recognition phase. Firstly,the input speech signal is preprocessed,including pre-emphasis,frame-by-frame and endpoint detection,and then the feature vector of preprocessed speech signal is extracted. The initial parts of speech feature vector are intercepted and respectively matched with all model vectors properly,then only several model vectors with less distortion can be left to continue next optimal path matching,repeated the optimal path matching and model vectors retaining until it is unique. The experiments show that compared with the ordinary DTW,the proposed algorithm can dramatically reduce the computational cost and improve the efficiency for the isolated word recognition system on the premise of ensuring its recognition accuracy.

相似文献/References:

[1]宋鑫坤 陈万米 朱明 桂春胜 程硕远 陈海波.基于正则表达式的语音识别控制策略研究[J].计算机技术与发展,2010,(02):106.
　SONG Xin-kun,CHEN Wan-mi,ZHU Ming,et al.Study on Speech Recognition Control Strategy Based on Regular Expression[J].,2010,(04):106.
[2]石现峰 张学智 张峰.基于HTK的语音识别系统设计[J].计算机技术与发展,2006,(10):37.
　SHI Xian-feng,ZHANG Xue-zhi,ZHANG Feng.Design of Speech Recognition System Based on HTK[J].,2006,(04):37.
[3]朱宇 宋艳.嵌入式语音识别系统特征参数提取研究[J].计算机技术与发展,2011,(07):246.
　ZHU Yu,SONG Yan.Research of Characteristic Parameters Extraction Based on Embedded Speech Recognition System[J].,2011,(04):246.
[4]林鸣霄.基于SpeechSDK的语音识别技术在三维仿真中的应用[J].计算机技术与发展,2011,(11):160.
　LIN Ming-xiao.Application of Speech Recognition Technology in 3D Simulation Based on Speech SDK[J].,2011,(04):160.
[5]李克粉,王直.改进的小波阈值去噪在语音识别中的应用[J].计算机技术与发展,2013,(05):231.
　LI Ke-fen,WANG Zhi.Application of Improved Wavelet Threshold Denoising in Speech Recognition[J].,2013,(04):231.
[6]胡亚洲,王新民,曹江涛.基于改进DTW的机器人语音指令识别系统研究[J].计算机技术与发展,2013,(07):70.
　HU Ya-zhou[],WANG Xin-min[],CAO Jiang-tao[].Study of Voice Command Recognition System for Robot Based on Improved DTW[J].,2013,(04):70.
[7]王亚飞,杨庚,李百惠.基于内距离形状上下文的跌倒检测方法[J].计算机技术与发展,2014,24(03):58.
　WANG Ya-fei,YANG Geng,LI Bai-hui.Fall Detection Approach Based on Inner-distance Shape Context[J].,2014,24(04):58.
[8]成谢锋,刘伟. 基于Android平台的心音识别系统的研究[J].计算机技术与发展,2015,25(02):152.
　CHENG Xie-feng,LIU Wei. Research on Heart Sound Identification System Based on Android Platform[J].,2015,25(04):152.
[9]王海洋,郭星. 基于语音识别的智慧旅游系统研究[J].计算机技术与发展,2015,25(05):143.
　WANG Hai-yang,GUO Xing. Study on Smart Tourism System Based on Voice Recognition[J].,2015,25(04):143.
[10]孙科学[] [],洪櫆[],章康宁[],等. 一种联合检测门禁系统的设计与实现[J].计算机技术与发展,2016,26(01):155.
　SUN Ke-xue[][],HONG Kui[],ZHANG Kang-ning[],et al. Design and Implementation of Joint Detection Access Control System[J].,2016,26(04):155.

更新日期/Last Update: 2018-06-07