Speaker Recognition for Hindi Speech Signal using MFCC-GMM Approach

被引：32
|
作者：
Maurya, Ankur [1 ]
Kumar, Divya [1 ]
Agarwal, R. K. [2 ]
机构：
[1] Motilal Nehru Natl Inst Technol Allahabad, Allahabad 211004, Uttar Pradesh, India
[2] Natl Inst Technol Kurukshetra, Kurukshetra 136119, Haryana, India
来源：
6TH INTERNATIONAL CONFERENCE ON SMART COMPUTING AND COMMUNICATIONS | 2018年 / 125卷
关键词：
Identification rate (IR); MFCC-GMM; MFCC-VQ; VERIFICATION; IDENTIFICATION;
D O I：
10.1016/j.procs.2017.12.112
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
Speaker recognition for different languages is still a big challenge for researchers. The accuracy of identification rate (IR) is great issue, if the utterance of speech sample is less. This paper aims to implement speaker recognition for Hindi speech samples using Mel frequency cepestral coffiecient vector quantization (MFCC-VQ) and Mel frequency cepestral cofficient-Gaussian mixture model (MFCC-GMM) for text dependent and text independent phrases. The accuracy of text independent recognition by MFCC-VQ and MFCC-GMM for Hindi speech sample is 77.64% and 86.27% respectively. However, the accuracy has increased significantly for text dependent recognition. The accuracy of Hindi speech samples are 85.49 % and 94.12 % using MFCC-VQ and MFCC-GMM approach. We have tested 15 speakers consisting 10 male and 5 female speakers. The total number of trails for each speaker is 17. (C) 2018 The Authors. Published by Elsevier B.V.
引用
收藏
页码：880 / 887
页数：8
相关论文
共 50 条
  • [1] MFCC-GMM based accent recognition system for Telugu speech signals
    Mannepalli K.
    Sastry P.N.
    Suman M.
    International Journal of Speech Technology, 2016, 19 (1) : 87 - 93
  • [2] Speaker recognition using mfcc and hybrid model of VQ and GMM
    Desai, Dhruv
    Joshi, Maulin
    1600, Springer Verlag (235): : 53 - 63
  • [3] Speaker recognition using MFCC and hybrid model of VQ and GMM
    1600, Springer Verlag (235):
  • [4] Gender Identification of a Speaker Using MFCC and GMM
    Yucesoy, Ergun
    Nabiyev, Vasif V.
    2013 8TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONICS ENGINEERING (ELECO), 2013, : 626 - 629
  • [5] Design of an Automatic Speaker Recognition System Based on Adapted MFCC and GMM Methods for Arabic Speech
    Tazi, El Bachir
    Benabbou, Abderrahim
    Harti, Mostafa
    INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2010, 10 (01): : 45 - 50
  • [6] A MFCC based Hindi Speech Recognition Technique using HTK Toolkit
    Tripathy, Shweta
    Baranwal, Neha
    Nandi, G. C.
    2013 IEEE SECOND INTERNATIONAL CONFERENCE ON IMAGE INFORMATION PROCESSING (ICIIP), 2013, : 539 - 544
  • [7] Automatic Speech Recognition of Isolated Words in Hindi Language using MFCC
    Patil, U. G.
    Shirbahadurkar, S. D.
    Paithane, A. N.
    2016 INTERNATIONAL CONFERENCE ON COMPUTING, ANALYTICS AND SECURITY TRENDS (CAST), 2016, : 433 - 438
  • [8] On the importance of components of the MFCC in speech and speaker recognition
    Zhen, B.
    Wu, X.
    Liu, Z.
    Chi, H.
    Beijing Daxue Xuebao Ziran Kexue Ban/Acta Scientiarum uaturalium Universitatis Pekinensis, 2001, 37 (03): : 371 - 378
  • [9] Speech/speaker recognition using a HMM/GMM hybrid model
    Rodriguez, E
    Ruiz, B
    Garcia-Crespo, A
    Garcia, F
    AUDIO- AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, 1997, 1206 : 227 - 234
  • [10] Speaker Recognition Improvement for Degraded Human Voice using Modified-MFCC with GMM
    Moondra, Amit
    Chahal, Dr Poonam
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2023, 14 (06) : 246 - 252
12345