DocumentCode :
2069109
Title :
An isolated word recognition system based on DSP and improved dynamic time warping algorithm
Author :
Li, Shicheng ; Ren, Haipeng
Author_Institution :
Dept. of Inf. & Control Eng., Xi´´an Univ. of Technol., Xi´´an, China
Volume :
1
fYear :
2010
fDate :
10-12 Dec. 2010
Firstpage :
136
Lastpage :
139
Abstract :
Dynamic time warping (DTW) algorithm has been widely used in the isolated word recognition system due to its simplicity. But its searching efficiency is low, and it needs large storage space which is inconvenient to be implemented on the digital signal processor(DSP). In this paper, the differential double threshold method is proposed to improve the accuracy of the endpoint detection. The weighted distance searching and vector memory space allocation is proposed to improve the accuracy of the distance calculation and to reduce the storage capacity demand. The matching distance threshold is proposed to stop the matching once the distance of matching is larger than the threshold, thus the redundant matching calculation is cancelled, and the efficiency is improved. The experiments are conducted using the proposed method and 6713DSK board. The results shows that the improved DTW proposed in this paper can obtain a higher recognition rate on the premise of less storage space and faster processing speed compared with the conventional DTW.
Keywords :
digital signal processing chips; speech recognition; 6713DSK board; DSP; DTW; differential double threshold method; digital signal processor; distance calculation; distance searching; dynamic time warping algorithm improvement; endpoint detection; isolated word recognition system; storage capacity demand; vector memory space allocation; Hidden Markov models; DTW; isolated word recognition; matching distance threshold; vector memory space allocation; weighted distance searching;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Progress in Informatics and Computing (PIC), 2010 IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-6788-4
Type :
conf
DOI :
10.1109/PIC.2010.5687421
Filename :
5687421
Link To Document :
بازگشت