Mohammed A.M. ABDULLAH, Musab T.S. Al-KALTAKCHI, Raid R. O. AL-NIMA

Comparisons of extreme learning machine and backpropagation-based i-vector approach for speaker identification

The extreme learning machine (ELM) is one of the machine learning applications used for regression andclassification systems. In this paper, an extended comparison between an ELM and the backpropagation neural network(BPNN)-based i-vector is given in terms of a closed-set speaker identification task using 120 speakers from the TIMITdatabase. The system is composed of the mel frequency cepstal coefficient (MFCC) and power normalized cepstalcoefficient (PNCC) approaches to form the feature extraction stage, while the cepstral mean variance normalization(CMVN) and feature warping are applied in order to mitigate the linear channel effect. The system is utilized withequal numbers of speakers of both genders with 120 speakers with eight dialects from the TIMIT database. The resultsdemonstrate that the combination of the i-vector with the ELM for different features has the highest speaker identificationaccuracy (SIA) compared with the combination of the BPNN with the i-vector. The results also show that the i-vectorwith ELM approach is faster than the BPNN-based i-vector and it has the highest SIA.

PDF

___

[1] Huang GB, Zhu QY, Siew CK. Extreme learning machine: theory and applications. Neurocomputing 2006; 70 (1-3): 489-501. doi: 10.1016/j.neucom.2005.12.126
[2] Huang G, Huang GB, Song S, You K. Trends in extreme learning machines: a review. Neural Networks 2015; 61: 32-48. doi: 10.1016/j.neunet.2014.10.001
[3] Ding S, Zhao H, Zhang Y, Xu X, Nie R. Extreme learning machine: algorithm, theory and applications. Artificial Intelligence Review 2015; 44 (1): 103-115. doi: 10.1007/s10462-013-9405-z
[4] Albadra MA, Tiuna S. Extreme learning machine: a review. International Journal of Applied Engineering Research 2017: 12 (14): 4610-4623.
[5] Ding S, Xu X, Nie R. Extreme learning machine and its applications. Neural Computing and Applications 2014; 25 (3-4): 549-556. doi: 10.1007/s00521-013-1522-8
[6] Dhanani J, Mehta R, Rana D, Tidke B. Back-Propagated Neural Network on Map Reduce Frameworks: A Survey. New York, NY, USA: Springer, 2019.
[7] Gopi ES. Digital Speech Processing Using MATLAB. New York, NY, USA: Springer, 2014.
[8] Yap KS, Tiong SK, Nagi J , Koh J, Nagi F. Comparison of supervised learning techniques for non-technical loss detection in power utility. International Review on Computers and Software 2012; 7 (2): 1828-6003.
[9] Verma P, Das PK. i-Vectors in speech processing applications: a survey. International Journal of Speech Technology 2015; 18 (4): 529-546. doi: 10.1007/s10772-015-9295-3
[10] Al-Kaltakchi MT, Woo WL, Dlay SS, Chambers JA. Speaker identification evaluation based on the speech biometric and i-vector model using the TIMIT and NTIMIT databases. In: 5th IEEE International Workshop on Biometrics and Forensics; London, UK; 2017. pp. 1-6.
[11] Al-Kaltakchi MT, Woo WL, Dlay SS, Chambers JA. Comparison of i-vector and GMM-UBM approaches to speaker identification with TIMIT and NIST 2008 databases in challenging environments. In: 25th IEEE European Signal Processing Conference; Kos, Greece; 2017. pp. 533-537.
[12] Al-Kaltakchi MT, Woo WL, Dlay SS, Chambers JA. Multi-dimensional i-vector closed set speaker identification based on an extreme learning machine with and without fusion technologies. In: 2017 Intelligent Systems Conference; London, UK; 2017. pp. 1141-1146.
[13] Huang GB, Cambria E, Toh, Widrow B, Xu Z. New trends of learning in computational intelligence. IEEE Computational Intelligence Magazine 2015; 10 (2): 16-17. doi: 10.1109/MCI.2015.2405277
[14] Cambria E, Liu Q, Li K, Leung VCM, Feng L et al. Extreme learning machines. IEEE Intelligent Systems 2013; 28 (6): 30-59. doi: 10.1109/MIS.2013.140
[15] Lan Y, Hu Z, Soh YC, Huang GB. An extreme learning machine approach for speaker recognition. Neural Computing and Applications 2013; 22 (3-4): 417-425. doi: 10.1007/s00521-012-0946-x
[16] Sadjadi SO, Slaney M, Heck L. MSR Identity Toolbox. Seattle, WA, USA: Microsoft, 2013.
[17] Dehak N, Kenny PJ, Dehak R, Dumouchel P, Ouellet P. Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing 2011; 19 (4): 788-798.