특징 강화 방법의 앙상블을 이용한 화자 식별
Speaker Identification Using an Ensemble of Feature Enhancement Methods
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we propose an approach which constructs classifier ensembles of various channel compensation and feature enhancement methods. CMN and CMVN are used as channel compensation methods. PCA, kernel PCA, greedy kernel PCA, and kernel multimodal discriminant analysis are used as feature enhancement methods. The proposed ensemble system is constructed with the combination of 15 classifiers which include three channel compensation methods (including ‘without compensation’) and five feature enhancement methods (including ‘without enhancement’). Experimental results show that the proposed ensemble system gives highest average speaker identification rate in various environments (channels, noises, and sessions).
Abstract
In this paper, we propose an approach which constructs classifier ensembles of various channel compensation and feature enhancement methods. CMN and CMVN are used as channel compensation methods. PCA, kernel PCA, greedy kernel PCA, and kernel multimodal discriminant analysis are used as feature enhancement methods. The proposed ensemble system is constructed with the combination of 15 classifiers which include three channel compensation methods (including ‘without compensation’) and five feature enhancement methods (including ‘without enhancement’). Experimental results show that the proposed ensemble system gives highest average speaker identification rate in various environments (channels, noises, and sessions).
참고문헌 (11)
- 김민석, "Greedy Kernel PCA를 이용한 화자식별", 말소리, 1(66), pp.105~116 (2008), 대한음성학회
- Duda, R. O, "Pattern Classification" (2001), John Wiley & Sons
- "FaNT – Filtering and Noise Adding Tool" (2011)[URL]
- Kim, M-S, "Kernel Multimodal Discriminant Analysis for Speaker Verification", Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, pp.4498~4501 (2010)
- Liu, F, "Efficient Cepstral Normalization for Robust Speech Recognition", Proceedings of ARPA Speech Natural Language Workshop, pp.69~74 (1993)
- Polikar, R, "Ensemble based Systems in Decision Making", Circuits and Systems Magazine, 6(3), pp.21~45 (2006)
- Reynolds, D. A, "Speaker Verification Using Adapted Gaussian Mixture Models", Digital Signal Processing, 10, pp.19~41 (2000)
- Reynolds, D. A, "Robust text-independent speaker identification using Gaussian mixture speaker models", IEEE Transactions on Speech Audio Processing, 3(1), pp.72~83 (1995)
- Scholkopf, B, "Kernel Principal Component Analysis", Proceedings of International Conference on Artificial Neural Networks, pp.583~588 (1997)
- Shawe-Taylor, J, "Kernel Methods for Pattern Analysis" (2004), Cambridge University Press
- Viikki, O, "Cepstral Domain Segmental Feature Vector Normalization for Noise Robust Speech Recognition", Speech Communication, 25(1), pp.133~147 (1998)