Speaker recognition based on the combination of GMM and SVDD

• Autorzy: Zhou Y. , Zhang X. , Wang J. , Gong Y. , Zhou Y.

Warianty tytułu

PL

Rozpoznawanie głosu bazujące na kombinacji systemów GMM i SVDD

• Języki publikacji: EN

Abstrakty

EN

Scare-level combination of subsystems can yield significant performance gains over individual subsystems in speaker recognition. A novel speaker verification method based on support vector data description (SVDD) is proposed to remedy the defect of Gaussian mixture model (GMM) to same extent, and then using the theory of multiple classifier systems (MCS),a new speaker recognition system based on the combination of GMM and SVDD is proposed. Experiments on TlMIT speech database show that the GMM-SVDD model fully utilizes the complementarities of GMM and SVDD to improve the performance obviously in speaker verification, closed-set speaker identification and speaker recognition.

PL

Zaproponowano nowa metodę rozpoznawania głosu bazującą na systemie SVDD jako alternatywę dla modelu GMM. Następnie wykorzystując teorię wielokrotnego systemu klasyfikacji MCS zaproponowano wykorzystanie połączenia systemów GMM i SVDD. Eksperymenty potwierdziły że nowy model GMM-SVOO umożliwia ulepszonę rozpoznawanie głosu.

Słowa kluczowe

EN

Gaussian mixture model; support vector data description; speaker recognition; multiple classifier systems

PL

rozpoznawanie głosu; systemy SVDD I GMM

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2011
• Tom: R. 87, nr 3
• Strony: 329--332
• Opis fizyczny: Bibliogr. 8 poz., rys., tab.

Twórcy

autor

Zhou Y.

autor

Zhang X.

autor

Wang J.

autor

Gong Y.

autor

Zhou Y.

• Instiute of Communications Engineering, PLA Univ. of Sci. & Tech,

Bibliografia

• [1] Reynold D. A., Quatieri T. F., Dunn R. B., „Speaker verification using adapter Gaussian mixture models”, Digital Signal Processing, 10(1-3). Pp. 19-41, 2000.
• [2] Tax D.M.J., Duin R.P.W., "Support vector data description", Machine Learning, 54(1), pp45-66, 2004.
• [3] Huenupan, F., Yoma N.B, Molina C. and Garreton C., "Confidence based multiple classifier fusion in speaker verification", Pattern Recognition Letters, 29(7), pp957-966, 2008.
• [4] L. Ferrer, Kemal Sonmez, and E. Shriberg, "An anticorrelation kernel for improved system combination in speaker verification", In Proceedings of the Speaker and Language Recognition Workshop, Odyssey 2008, Stellenbosch, South Africa, January 2008b.
• [5] Shou-Chun Yin, Rose, R., Kenny, P., "Adaptive score normalization for progressive model adaptation in text independent speaker verification", IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, pp4857-4860, 2008.
• [6] Banerjee A., Burlina P., Dieh C., "A support vector method for anomaly detection in hyperspectral imagery", IEEE Transactions on Geoscience and Remote Sensing, 44(8), pp2282-91,2006.
• [7] Yuhuan Zhou, Xiongwei Zhang, Jinming Wang, Yong Gong, "Research on SVDD Applied in Speaker Verification", International Journal of Digital Content Technology and its Applications, 4(5), pp 89-95, 2010.
• [8] Sturim D., Reynold D A., "Speaker Adaptive Cohort Selection for T-norm in Text-Independent Speaker Verification", IEEE International Conference on Acoustics, Speech, and Signal Processing, Philadelphia, 2005.