TEO-CFCC Characteristic Parameter Extraction Method for Speaker Recognition in Noisy Environments

• Autorzy: Li L. , An D. , Zhao D. , Rong C. , Ma S.

Warianty tytułu

PL

Wyznaczanie parametru charakterystycznego dla filtru TEOCFCC w rozpoznaniu głosu w zaszumionym środowisku

• Języki publikacji: EN

Abstrakty

EN

This paper proposes TEO-CFCC characteristic parameter extraction method. Signal phase matching is applied to eliminate speech noise on the basis of CFCC characteristic parameter, and then Teager energy operator is added to the acquisition of CFCC characteristic parameter. In this way TEO-CFCC characteristic parameter is obtained and the energy of speech becomes one of the characteristic parameters for speaker recognition. Experiment results show that the recognition accuracy can reach to 83.2% in a -5dB SNR of vehicle interior noise environment by using TEO-CFCC characteristic parameter.

PL

W artykule przedstawiono metodę wyznaczania parametrów charakterystycznych filtru TEO-CFCC. Zastosowano tu dopasowywanie fazowe sygnału, dla eliminacji z mowy szumów oraz operator Teagera do wyrugowania parametrów. Badania eksperymentalne pokazuję, że dokładność rozpoznania głosu wynosi 83,2% przy -5dB SNR we wnętrzu pojazdu.

Słowa kluczowe

EN

auditory transform; phase matching; energy operator; speaker recognition

PL

transformacja słuchowa; dopasowanie fazowe; operator Teagera; rozpoznawanie mówcy

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2013
• Tom: R. 89, nr 2a
• Strony: 118--121
• Opis fizyczny: Bibliogr. 11 poz., schem., wykr.

Twórcy

autor

Li L.

• School of Information Science & Engineering, Northeastern University, Shenyang, China

autor

An D.

• School of Information Science & Engineering, Northeastern University, Shenyang, China

autor

Zhao D.

• Department of Neurosurgery, The First Affiliated Hospital of China Medical University,Shenyang, China

autor

Rong C.

• School of Information Science & Engineering, Northeastern University, Shenyang, China

autor

Ma S.

• School of Information Science & Engineering, Northeastern University,Shenyang, China

Bibliografia

• [1] Dulas J. Automatic word's identification algorithm used for digits classification [J]. Przeglad Elektrotechniczny,87(2011), No.11, 230-233.
• [2] Dulas J. Speech signal's automatic segmentation based on the grid with various parameter's method [J]. Przeglad Elektrotechniczny,86(2010), No.1, 229-232.
• [3] Dobrowolski A P,Majda E. Evaluation of the usefulness of selected features of the speech signal for automatic speaker recognition systems [J]. Przeglad Elektrotechniczny, 87(2011) No.10, 193-197.
• [4] Vijayasenan D,Valente F, Bourlard H. Multistream speaker diarization of meetings recordings beyond MFCC and TDOA features. Speech Communication, 54(2012) , No.7, 55-67.
• [5] Wang L,Minami K,Yamamoto K,et al. Speaker Recognition by Combining MFCC and Phase Information in Noisy Conditions. IEICE Transactions on Information and Systems, E93D(2011), No.9, 2397-2406.
• [6] Li Q,Huang Y. An Auditory-Based Feature Extraction Algorithm for Robust Speaker Identification Under Mismatched Conditions. IEEE Transactions on Audio Speech and Language Processing, 19(2011), No.1, 1791-1801.
• [7] Qi L. An auditory-based transfrom for audio signal processin. 2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, United states.Oct18-21, (2009). 181-184.
• [8] Dimitriadis D,Maragos P,Potamianos A. On the Effects of Filterbank Design and Energy Computation on Robust Speech Recognition. IEEE Transactions on Audio Speech and Language Processing, 19(2011), No.4, 1504-1516.
• [9] Tu C-C,Juang C-F. Recurrent type-2 fuzzy neural network using Haar wavelet energy and entropy features for speech detection in noisy environments. Expert Systems With Applications, 39(2012), No.7, 2479-2488.
• [10] Lou Hongwei,Hu Guangrui. Speech Feature Based on Teager Energy Operator and Dyadic Wavelet Transform, Journal of Shanghai Jiaotong University, 37(2009), No.2, 83-85.
• [11] Sun Jincai, Zhu Weijie,Sun Tieyuan. DOA and Waveform Estimation by Using Small-Dimension Array, Journal of Northwestern Rolytechnical University, 21(2003), No.4,512-515.