Title :
A Mixed Parameter Method Based on MFCC and Fractal Dimension for Speech Recognition
Author :
Yao, Minghai ; Hu, Jing ; Gu, Qinlong
Author_Institution :
Coll. of Inf. Eng., Zhejiang Univ. of Technol., Hangzhou
Abstract :
We propose a speech recognition approach with mixed parameter in this paper, which combines the traditional MFCC and fractal feature as the feature parameter. MFCC has higher spectrum resolution at low frequency segment, while it cannot represent speech nonlinearity. Fractal dimension is used to quantitatively describe the chaos nonlinearity in speech air flow. Experimental results demonstrate this method is promising in improving speech recognition performance.
Keywords :
cepstral analysis; chaos; fractals; speech recognition; chaos nonlinearity; fractal dimension; fractal feature; mel-frequency cepstral coefficients; mixed parameter method; speech air flow; speech nonlinearity; speech recognition; Cepstral analysis; Chaos; Character recognition; Educational institutions; Fractals; Interpolation; Mel frequency cepstral coefficient; Power measurement; Speech recognition; Topology; Fractal Dimension; MFCC; Speech Recognition;
Conference_Titel :
Information Acquisition, 2006 IEEE International Conference on
Conference_Location :
Shandong
Print_ISBN :
1-4244-0528-9
Electronic_ISBN :
1-4244-0529-7
DOI :
10.1109/ICIA.2006.305906
