The Extraction of Differential MFCC Based on EMD

Yun Yun Chu; Wei Hua Xiong; Wei Wei Shi; Yu Liu

doi:10.4028/www.scientific.net/AMM.313-314.1167

Paper Titles

Calculation Model of Exergy Cost Based on Thermoeconomics Structure Theory and Thermoeconomics Accounting Mode
p.1148

Application of Differential Transform Method to Buckling Problems at Pined-Pined Boundary Conditions
p.1155

Design of Precision Breeding System for Pigs Based on DDE
p.1159

The Design of a Data Acquisition System for Wave Energy Conversion Efficiency Measurement System Based on the Serial Communication
p.1163

The Extraction of Differential MFCC Based on EMD
p.1167

The Precision Breeding System of Pig Based on RFID
p.1171

A Study on GDOP for Vector-Based Tracking Loop GPS/INS Receiver
p.1175

The Design of Elevator Monitoring Terminal Based on the GPRS
p.1180

Delay-Dependent Stability Criteria for Time-Delayed Systems
p.1184

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 313-314The Extraction of Differential MFCC Based on EMD

The Extraction of Differential MFCC Based on EMD

Abstract:

Feature extraction is the key to the object recognition. How to obtain effective, reliable characteristic parameters from the limited measured data is a question of great importance in feature extraction. This paper presents a method based on Empirical Mode Decomposition (EMD) for the extraction of Mel Frequency Cepstrum Coefficients (MFCCs) and its first order difference from original speech signals that contain four kinds of emotions such as anger, happiness, surprise and natural for emotion recognition. And the experiments compare the recognition rate of MFCC, differential MFCC (Both of them are extracted based on EMD) or their combination through using Support Vector Machine (SVM) to recognize speakers' emotional speech identity. It proves that the combination of MFCC and its first order difference has a highest recognition rate.

You might also be interested in these eBooks

Machinery Electronics and Control Engineering II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 313-314)

Pages:

1167-1170

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.313-314.1167

Citation:

Cite this paper

Online since:

March 2013

Authors:

Yun Yun Chu, Wei Hua Xiong, Wei Wei Shi, Yu Liu

Keywords:

Empirical Mode Decomposition (EMD), Feature Extraction, First Order Difference, Mel Frequency Cepstrum Coefficients (MFCCs)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] M.A. Hossan, S. Memon and M.A. Gregory, in: A Novel Approach for MFCC Feature Extraction, Progress in 4th International Conference on Signal Processing and Communication Systems (2010)．

DOI: 10.1109/icspcs.2010.5709752

Google Scholar

[2] L. Zhao: Speech Signal Processing (in Chinese), China Machine Press, Beijing (2003).

Google Scholar

[3] Y. Shao, B. Liu, and Z. Li: Speaker Recognition System Based on MFCC and Weighted Vector Quantization, Computer Engineering and Applications (in Chinese) (2002), pp.127-128.

Google Scholar

[4] Binbin Tu and Fengqin YU: Speech Emotion Recognition Based on Improved MFCC with EMD. Computer Engineering and Applications (in Chinese) (2012), pp.119-122.

Google Scholar

[5] Z. Bian, X. Zhang, et al, in: Pattern Recognition (in Chinese). Tsinghua University Press, Beijing (2000).

Google Scholar

[6] Junqin Wu and Junjun Yu, in: An Improved Arithmetic of MFCC in Speech Recognition System. Progress in International Conference on Electronics, Communications and Control (2011).

DOI: 10.1109/icecc.2011.6066676

Google Scholar

[7] Gan Lu, Long Zhou and Xinge You, in: An improved EMD analysis method for GPR images, Process in International Conference on Computational and Information Sciences (2011).

DOI: 10.1109/iccis.2011.77

Google Scholar