Significance of Frequency Band Selection of MFCC for Text-Independent Speaker Identification

被引：1
|
作者：
Dhonde, S. B. [1 ]
Jagade, S. M. [2 ]
机构：
[1] All India Shri Shivaji Mem Soc Inst Informat Tech, Dept Elect Engn, Pune 411001, Maharashtra, India
[2] TPCT COE, Dept Elect & Telecommun Engn, Osmanabad 413501, India
来源：
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON DATA ENGINEERING AND COMMUNICATION TECHNOLOGY, ICDECT 2016, VOL 2 | 2017年 / 469卷
关键词：
Speaker recognition; Feature extraction; Mel scale; Vector quantization; MULTITAPER MFCC; FEATURES; VERIFICATION; WAVELET; RECOGNITION; TRANSFORMS;
D O I：
10.1007/978-981-10-1678-3_21
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents significance of Mel-frequency Cepstral Coefficients (MFCC) Frequency band selection for text-independent speaker identification. Recent studies have been focused on speaker specific information that may extends beyond telephonic passband. The selection of the frequency band is an important factor to effectively capture the speaker specific information present in the speech signal for speaker recognition. This paper focuses on development of a speaker identification system based on MFCC features which are modeled using vector quantization. Here, the frequency band is varied up to 7.75 kHz. Speaker identification experiments evaluated on TIMIT database consisting of 630 speaker shows that the average recognition rate achieved is 97.37 % in frequency band 0-4.85 kHz for 20 MFCC filters.
引用
收藏
页码：217 / 224
页数：8
相关论文
共 50 条
  • [41] Wavelet entropy and neural network for text-independent speaker identification
    Daqrouq, Khaled
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2011, 24 (05) : 796 - 802
  • [42] Robust text-independent speaker identification over telephone channels
    Murthy, HA
    Beaufays, F
    Heck, LP
    Weintraub, M
    [J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1999, 7 (05): : 554 - 568
  • [43] Text-independent speaker identification based on spectral weighting functions
    Ma, JY
    Gao, W
    [J]. AUDIO- AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, 1997, 1206 : 267 - 272
  • [44] HCRF-UBM approach for text-independent speaker identification
    Hong, Wei-Tyng
    [J]. COMPUTERS & MATHEMATICS WITH APPLICATIONS, 2012, 64 (05) : 1120 - 1127
  • [45] A two-level classifier for text-independent speaker identification
    Hadjitodorov, S
    Boyanov, B
    Dalakchieva, N
    [J]. SPEECH COMMUNICATION, 1997, 21 (03) : 209 - 217
  • [46] I-vector Based Text-Independent Speaker Identification
    Liu, Tingting
    Kang, Kai
    Guan, Shengxiao
    [J]. 2014 11TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2014, : 5420 - 5425
  • [47] A robust wavelet-based text-independent speaker identification
    Phung Trung Nghia
    Pham Viet Binh
    Nguyen Huu Thai
    Nguyen Thanh Ha
    Kumsawat, Prayoth
    [J]. ICCIMA 2007: INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND MULTIMEDIA APPLICATIONS, VOL II, PROCEEDINGS, 2007, : 219 - 223
  • [48] Text-Independent Speaker Identification Using the Histogram Transform Model
    Ma, Zhanyu
    Yu, Hong
    Tan, Zheng-Hua
    Guo, Jun
    [J]. IEEE ACCESS, 2016, 4 : 9733 - 9739
  • [49] Text-independent speaker identification utilizing likelihood normalization technique
    Markov, KP
    Nakagawa, S
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1997, E80D (05) : 585 - 593
  • [50] Robust text-independent speaker identification using bispectrum slice
    Özkurt, TE
    Akgül, T
    [J]. PROCEEDINGS OF THE IEEE 12TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, 2004, : 418 - 421
12345