Title :
Mandarin isolated words recognition method based on pitch contour
Author :
Chunming Wei ; Yingchun Yang
Author_Institution :
Dept. of Comput. Sci. & Technol., Zhejiang Univ., Hangzhou, China
fDate :
Oct. 30 2012-Nov. 1 2012
Abstract :
In this paper, we attempt to use pitch contour in Mandarin isolated words recognition by matching candidate pitch contour with a set of templates. To apply it in speaker-independent speech recognition, we propose a remedy algorithm to weaken speaker information in pitch contour. Speaker-dependent and - independent speech recognition experiments are carried out to evaluate performance of pitch contour and MFCC. Score fusion of MFCC and revised pitch contour are implemented. Experimental results demonstrate that pitch contour performs comparably with MFCC in speaker-dependent speech recognition. Through score fusion, the revised pitch contour helps in improving performance in speaker-independent speech recognition.
Keywords :
cepstral analysis; natural language processing; pattern matching; speech recognition; MFCC score fusion; Mandarin isolated word recognition method; candidate pitch contour matching; pitch contour; pitch contour performance evaluation; remedy algorithm; speaker information; speaker-independent speech recognition experiments; Databases; Hidden Markov models; Mel frequency cepstral coefficient; Speech; Speech processing; Speech recognition; Mandarin isolated words recognition; Pitch contour; Remedy algorithm; Template based approach;
Conference_Titel :
Cloud Computing and Intelligent Systems (CCIS), 2012 IEEE 2nd International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4673-1855-6
DOI :
10.1109/CCIS.2012.6664385