Feature Extraction based on DBN-SVM for Tone Recognition
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
An innovative tone modeling framework based on deep neural networks in tone recognition was proposed inthis paper. In the framework, both the prosodic features and the articulatory features were firstly extracted asthe 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 inexperiments, and the results show that the proposed method helped improve the recognition accuracysignificantly for all tone patterns. Meanwhile, the average tone recognition rate reached 83.03%, which is 8.61%higher than that of the original method.
Abstract
An innovative tone modeling framework based on deep neural networks in tone recognition was proposed inthis paper. In the framework, both the prosodic features and the articulatory features were firstly extracted asthe 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 inexperiments, and the results show that the proposed method helped improve the recognition accuracysignificantly for all tone patterns. Meanwhile, the average tone recognition rate reached 83.03%, which is 8.61%higher than that of the original method.
참고문헌 (11)
- L. W. Cheng, "Improved large vocabulary Mandarin speech recognition by selectively using tone information with a two-stage prosodic model", Proceedings of the 9th Annual Conference of the International Speech Communication Association, pp.1137~1140 (2008)
- H. Wei, "Exploiting prosodic and lexical features for tone modeling in a conditional random field framework", Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.4549~4552 (2008)
- Y. Qian, "A multi-space distribution(MSD)and two-stream tone modeling approach to Mandarin speech recognition", Speech Communication, 51(12), pp.1169~1179 (2009)
- H. Chao, "Improved tone modeling by exploiting articulatory features for Mandarin speech recognition", Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.4741~4744 (2012)
- G. E. Hinton, "Reducing the dimensionality of data with neural networks", Science, 313(5786), pp.504~507 (2006)
- G. Hinton, "Deep neural networks for acoustic modeling in speech recognition : the shared views of four research groups", IEEE Transactions on Signal Processing Magazine, 29(6), pp.82~97 (2012)
- S. K. Kim, "Voice activity detection based on deep belief networks using likelihood ratio", Journal of Central South University, 23(1), pp.145~149 (2016)
- R. Xia, "A multi-task learning framework for emotion recognition using 2D continuous space", IEEE Transactions on Affective Computing, 8(1), pp.3~14 (2017)
- J. Lee, "High-level feature representation using recurrent neural network for speech emotion recognition", Proceedings of the 16th Annual Conference of the International Speech Communication Association, pp.1537~1540 (2015)
- G. E. Hinton, "Training products of experts by minimizing contrastive divergence", Neural Computation, 14(8), pp.1771~1800 (2002)
- "LIBSVM: a library for support vector machines (v.3.23)" (2018)[URL]