Speaker Identification using Frequency Dsitribution in the Transform Domain

被引：0
作者：
Kekre, H. B. [1 ]
Kulkarni, Vaishali [2 ]
机构：
[1] NMIMS Univ, MPSTME, Comp Dept, Bombay, Maharashtra, India
[2] NMIMS Univ, MPSTME, Elect & Telecommun, Bombay, Maharashtra, India
来源：
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS | 2012年 / 3卷 / 02期
关键词：
Speaker Identification; DFT; DCT; DST; Hartley; Haar; Walsh; Kekre's Transform;
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
In this paper, we propose Speaker Identification using the frequency distribution of various transforms like DFT (Discrete Fourier Transform), DCT (Discrete Cosine Transform), DST (Discrete Sine Transform), Hartley, Walsh, Haar and Kekre transforms. The speech signal spoken by a particular speaker is converted into frequency domain by applying the different transform techniques. The distribution in the transform domain is utilized to extract the feature vectors in the training and the matching phases. The results obtained by using all the seven transform techniques have been analyzed and compared. It can be seen that DFT, DCT, DST and Hartley transform give comparatively similar results (Above 96%). The results obtained by using Haar and Kekre transform are very poor. The best results are obtained by using DFT (97.19% for a feature vector of size 40).
引用
收藏
页码：73 / 78
页数：6
相关论文
共 28 条
  • [11] Kekre H., 2011, INT J COMPUTER SCI E, V3
  • [12] Kekre H B, 2010, TECHNOPATH J SCI ENG, V02
  • [13] Kekre H B, IJACSA INT J ADV COM
  • [14] Kekre H B, 2010, THINKQUEST 2010 INT
  • [15] Khan S., 2008, INT J COMPUTER SCI E, V2
  • [16] Kinnunen Tomi, ISCLP2004
  • [17] Matsui T., 1992, ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech and Signal Processing (Cat. No.92CH3103-9), P157, DOI 10.1109/ICASSP.1992.226096
  • [18] Molau S, 2001, INT CONF ACOUST SPEE, P73, DOI 10.1109/ICASSP.2001.940770
  • [19] Myers L., 2004, EXPLORATION VOICE BI
  • [20] Rabiner L., 2009, FUNDAMENTAL SPEECH R
123