The dynamic time warping(DTW) technology based on the dynamic programming can solve the problem that the characteristic parameters of speech signal are of different lengths in each other.Matching the pattern character and speech character with dynamic time warping enables the researchers to compare the distortions between them so as to obtain the criterion for identification.According to the experimental results
the algorithm after improvement performs better in single speech recognition.
关键词
Keywords
references
胡光锐.语音处理与识别[M].上海:上海科学技术文献出版社,1994.
王黎明.语音信号亮度补偿技术研究[J].测试技术学报,2004(1):83-85.W ANG L IM ING.T HE STUDY OF LIGH TNESS EQUA LIZ ING FOR THE SPEECH S IGNA L[J].JOURNA L OF T EST AND M EASUREM EN T T ECHNO-LOGY,2004(1):83-85.(IN CH INESE).
[美]拉宾纳L R,谢弗著R W,朱雪龙译.语音信号数字处理[M].北京:科学出版社,1983.
易克初.语音信号处理[M].北京:国防工业出版社,2000.
付中华,赵容椿.用窗口法在小存储器中实现DTW算法[J].西北工业大学学报,2002,20(4):540-543.FU ZHONGHUA,ZHAO R ONGCHUN.O N IM P LEM EN TING DYNAM IC TIM E-W ARP ING IN SM A LL RAM[J].N ORTHW EST U N IVERS ITYCO LLEGE JOURNA L,2002,20(4):540-543.(IN CH INESE).
杨大利.语音识别中一种新的特征参数选择方法[J].清华大学学报,2003,43(1):79-82.Y ANG D A LI.F EATURE SE LECTION M ETHOD BASED ON ORTHOGONA L EXPERIM EN TS FOR SPEECH RECOGN ITION[J].T S INGHUAU N IVERS ITY JOURNA L,2003,43(1):79-82.(IN CH INESE).