Title :
An improved method for feature extraction of Mandarin pronunciation
Author_Institution :
Sch. of Inf. & Electron. Eng., Zhejiang Univ. of Sci. & Technol., Hangzhou, China
Abstract :
Mandarin features extraction plays a very important role in the Mandarin recognition. It still has a long way to go before it reaches the level of success. In this paper, the Mandarin features are explored. The standard of Mandarin pronunciation is divided into six levels. The Mandarin pronunciation is divided into consonant, vowel and tone. And the feature parameters of pronunciation are surveyed. The experimental results show that the features have good recognition ability and robust performances.
Keywords :
feature extraction; natural language processing; speech recognition; Mandarin features extraction; Mandarin pronunciation; Mandarin recognition; feature extraction; recognition ability; robust performances; Feature extraction; Frequency domain analysis; Humans; Psychoacoustic models; Psychology; Signal sampling; Speech analysis; Speech processing; Speech recognition; Testing; component; consonant; mandarin feature; tone; vowel;
Conference_Titel :
Computational Intelligence and Industrial Applications, 2009. PACIIA 2009. Asia-Pacific Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-4606-3
DOI :
10.1109/PACIIA.2009.5406639