Feature Extraction based on DBN-SVM for Tone Recognition


Hao Chao, Cheng Song, Bao-yun Lu, Yong-li Liu, Journal of Information Processing Systems Vol. 15, No. 1, pp. 91-99, Feb. 2019  

10.3745/JIPS.04.0101
Keywords: Deep Belief Networks, Deep Learning, Feature Fusion, Support Vector Machine, Tone Feature Extraction
Fulltext:

Abstract

An innovative tone modeling framework based on deep neural networks in tone recognition was proposed in this paper. In the framework, both the prosodic features and the articulatory features were firstly extracted as the raw input data. Then, a 5-layer-deep deep belief network was presented to obtain high-level tone features. Finally, support vector machine was trained to recognize tones. The 863-data corpus had been applied in experiments, and the results show that the proposed method helped improve the recognition accuracy significantly for all tone patterns. Meanwhile, the average tone recognition rate reached 83.03%, which is 8.61% higher than that of the original method.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.




Cite this article
[APA Style]
Chao, H., Song, C., Lu, B., & Liu, Y. (2019). Feature Extraction based on DBN-SVM for Tone Recognition. Journal of Information Processing Systems, 15(1), 91-99. DOI: 10.3745/JIPS.04.0101.

[IEEE Style]
H. Chao, C. Song, B. Lu, Y. Liu, "Feature Extraction based on DBN-SVM for Tone Recognition," Journal of Information Processing Systems, vol. 15, no. 1, pp. 91-99, 2019. DOI: 10.3745/JIPS.04.0101.

[ACM Style]
Hao Chao, Cheng Song, Bao-yun Lu, and Yong-li Liu. 2019. Feature Extraction based on DBN-SVM for Tone Recognition. Journal of Information Processing Systems, 15, 1, (2019), 91-99. DOI: 10.3745/JIPS.04.0101.