Title :
Research on isolated word recognition with DTW-based
Author :
Xu, Lijun ; Ke, Minyi
Author_Institution :
Sch. of Comput. Sci. & Technol., Hubei Univ. of Technol., Wuhan, China
Abstract :
The paper first conducts a study and analysis on DTW algorithm. As the DTW algorithm needs a large number of calculations and has poor anti-interference weakness, the paper proposes improved DTW algorithm with path constraint and improved DTW algorithm to relax the starting and ending point. Experiments show that the improved DTW methods can improve the recognition speed, reduce the noise interference on speech recognition, and improve speech recognition rate.
Keywords :
dynamic programming; speech recognition; ending point relaxation; improved DTW algorithm; isolated word recognition; noise interference reduction; path constraint; recognition speed improvement; speech recognition rate improvement; starting point relaxation; Algorithm design and analysis; Computer science; Educational institutions; Heuristic algorithms; Signal processing algorithms; Speech; Speech recognition; DTW; Endpoint detection; Isolated word; Speech recognition;
Conference_Titel :
Computer Science & Education (ICCSE), 2012 7th International Conference on
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4673-0241-8
DOI :
10.1109/ICCSE.2012.6295044
