Ensemble Learning Approach with Application to Chinese Dialect Identification

Yu Guo Xia; Ming Liang Gu

doi:10.4028/www.scientific.net/AMM.333-335.769

Paper Titles

Automatic Transcription of Piano Music Using Audio-Vision Fusion
p.742

An Improved Direct Current Prediction Method for Intra Coding
p.749

Improved Algorithm for Pitch Detection and Harmonic Separation
p.753

Acoustic Events Detection in Dissimilarity Measurement Space
p.764

Ensemble Learning Approach with Application to Chinese Dialect Identification
p.769

Effect of Speaking Rate on Chinese Speech Recognition for Foreign Students
p.775

Design and Realization of the Birdsong Analysis and Identification System
p.779

A Novel Rate Control Algorithm for H.264/AVC Standard
p.783

A Novel Header Bits Estimation Scheme for H.264/AVC Standard
p.787

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 333-335Ensemble Learning Approach with Application to...

Ensemble Learning Approach with Application to Chinese Dialect Identification

Abstract:

In this paper we propose ensemble learning based approach to identify Chinese dialects. This new method firstly uses Gaussian Mixture Models and N-gram language models to produce a set of base learners. Then the two typical ensemble learning approach, Bagging and AdaBoost are conducted to combine the base learner to determine the dialect category. The ANN is selected as weak learner. The experimental results show that the ensemble approach not only enhances the performance of the system greatly, but also reduces the contradiction between the training data and the number of parameters in models.

You might also be interested in these eBooks

Measurement Technology and Engineering Researches in Industry

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 333-335)

Pages:

769-774

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.333-335.769

Citation:

Cite this paper

Online since:

July 2013

Authors:

Yu Guo Xia, Ming Liang Gu

Keywords:

Adaboost, Bagging, Dialect Identification, Ensemble Learning

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] M.A. Zissman. Comparison of four approaches to automatic language identification of telephone speech [J], IEEE Trans. Speech Audio Processing, 4(1): 31～44, (1996).

DOI: 10.1109/tsa.1996.481450

Google Scholar

[2] P. Torres-Carrasquillo,E. Singer,M. Kohler,R. Greene,D. Reynolds, and J. Deller, Jr., Approach to Language Identification using Gaussian Mixture Model and Shifted Delta Cepstral Features[J]. in Proc. Int. Cof. Spoken Language Processing, 89～92, (2002).

DOI: 10.21437/icslp.2002-74

Google Scholar

[3] Mingliang Gu, Zhaoyong Shen. Phonotatics Based Chinese Dialects Identification[J]. Journal of Chinese Information Processing. 20(5): 77～82, 2006. (In Chinese).

Google Scholar

[4] Zhouli Hai, Liang Wang, Bo Yin, and Vidhyasaharan Sethu. Language Identification: A Tutorial[J], IEEE Circuits and Systems Magazine, 82～108, (2011).

DOI: 10.1109/mcas.2011.941081

Google Scholar

[5] L. Breiman. Bagging predictors. Machine Learning, 24(2): 123–140, (1996).

Google Scholar

[6] R. E. Schapire. The Strength of Weak Learn ability. Machine Learning, 5(2): 197～227, (1990).

Google Scholar

[7] Hansen L K and Salamon P. Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(10): 993–1001, (1990).

DOI: 10.1109/34.58871

Google Scholar

[8] R. E. Schapire. The Boosting approach to machine learning: An overview. Nonlinear Estimation and Classification. Springer, Berlin, (2003).

Google Scholar

[9] Zhihua Zhou. Ensemble Methods: Foundations and Algorithms, Boca Raton, FL: Chapman & Hall/CRC, 23～46, (2012).

Google Scholar