Browse > Article

On the Use of Various Resolution Filterbanks for Speaker Identification  

Lee, Bong-Jin (Yonsei university)
Kang, Hong-Goo (Yonsei university)
Youn, Dae-Hee (Yonsei university)
Abstract
In this paper, we utilize generalized warped filterbanks to improve the performance of speaker recognition systems. At first, the performance of speaker identification systems is analyzed by varying the type of warped filterbanks. Based on the results that the error pattern of recognition system is different depending on the type of filterbank used, we combine the likelihood values of the statistical models that consist of the features extracting from multiple warped filterbanks. Simulation results with TIMIT and NTIMIT database verify that the proposed system shows relative improvement of identification rate by 31.47% and 15.14% comparing it to the conventional system.
Keywords
Automatic speaker identification; Filterbank; Gaussian mixture model; TIMIT; Various resolution; Warped filter;
Citations & Related Records
연도 인용수 순위
  • Reference
1 C. S. Liu, W. J. Wang, M. T Lin, H. C. Wang, 'Study of Line Spectrum Pair Frequencies for Speaker Recognition,' Proc. Int. Conf. Acoust. Speech and Audio Processing, 277-280, 1990
2 D. A. Reynolds, 'Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models,' IEEE Trans. On Acoust. Speech and Audio Processing, 3 (1) 1995
3 M. V. Erp, et al., 'An Overview and Comparison of Voting Methods for Pattern Recognition,' in Proc. International Workshop on Frontiers in Handwriting Recognition, 195-200, 2002
4 J. H. Nealand, A. B. Bradley, M. Lech, 'Discriminative Feature Extraction Applied to Speaker Identification,' in Proc. ICSP'02, 484-487, 2002
5 Chiyomi Miyajima, et al., 'A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction,' Speech Communication, 35, 203-218, 2001   DOI   ScienceOn
6 L. Besacier, J. F. Bonastre, 'Subband architecture for automatic speaker recognition,' Signal Processing, 80, 1245-1259, 2000   DOI   ScienceOn
7 G. Gravier, C. Mokbel, G. Chollet, 'Model Dependent Spectral Representations for Speaker Recognition,' in Proc. Eurospeech'97, 5, 2299-2302, 1997
8 S. Hayakawa and F. Itakura, 'Text-dependent Speaker Recognition Using The Information in The Higher Frequency Band,' In Proc. Int. Conf. Acoust. Speech and Audio Processing, 1, 137-140, 1994
9 D. A. Reynolds, 'Experimental Evaluation of Features for Robust Speaker Identification,' IEEE Trans. on Speech and Audio Processing, 2 (4) 639-643, 1994   DOI   ScienceOn