The rapid development in technology has led to a colossal surge in the use of biometric authentication system. Speaker identification biometric is one of the fields that is under progress and demands more and more precision. The objective of this research is to explore the issue of identifying a speaker from voice regardless of the content. Perceptual Wavelet Packet Transform (PWPT) and Artificial Neural Networks (ANN) approach are discussed in this paper for speaker identification. Perceptual Wavelet Packet Cepstral Coefficients (PWPCC) are used for transforming speech into spectral feature vectors, and the most germane aspects of the speech signal are selected from the energy and variance distribution characteristics. These selected attributes are presented to the Cascaded Feedforward Neural Network (CFNN) and trained with Levenberg-Marquardt Back Propagation (LMBP) algorithm for further classification. The performance of the network is determined by evaluating the Speaker Identification Rate (SIR). For comparison, five different gradient descent training algorithms are considered and it is found that the LMBP produces better performance. The proposed model is evaluated for clean as well as noisy speech at various SNR levels and is found to be competitive, and the experimental results show significant improvement in speaker identification rate compared with other classical methods.
AlmaadeedN., AggounA. and AmiraA., Text-independent speaker identification using vowel formants, Journal of Signal Processing Systems82(3) (2016), 345–356.
2.
NaikM. and Jayant, Speaker Verification: A Tutorial, Communications Magazine, IEEE (1990), pp. 42–48.
3.
DhondeS.B. and JagadeS.M., Significance of Frequency Band Selection of MFCC for Text-Independent Speaker Identification, Singapore, Springer, pp, Pro International Conference on Data Engineering and Communication Technology (2017), 217–224.
4.
SahuP.K., BiswasA., BhowmickA. and ChandraM., Auditory ERB like admissible wavelet packet features for TIMIT phoneme recognition, Engineering Science and Technology, an International Journal17(3) (2014), 145–151.
5.
ChetouaniM., Faundez-ZanuyM., GasB. and ZaraderJ.L., Investigation on LP-residual representations for speaker identification, Pattern Recognition42(3) (2009), 487–494.
6.
AlsterisL.D. and PaliwalK.K., ASR on Speech Reconstructed from Short-time Fourier Phase Spectra, Proc of Int Conference on Spoken Language Processing2004.
7.
HuangH., XuY., ZhouR. and YanY., Feature recovery for noise-robust speaker verification,–IET Journals & Magazines, Electronics Letters51(18) (1461).
8.
LiM., LiuL., CaiW. and LiuW., Generalized I-vector representation with phonetic tokenizations and tandem features for both text independent and text dependent speaker verification, Journal of Signal Processing Systems82(2) (2016), 207–215.
9.
LeiL. and KunS., Speaker recognition using wavelet cepstral coefficient, I-vector, and cosine distance scoring and its application for forensics, Journal of Electrical and Computer Engineering (2016).
10.
ChauhanP.M. and DesaiN.P., Mel Frequency Cepstral Coefficients (MFCC) based speaker identification in noisy environment using wiener filter, Coimbatore, India, Proc IEEE Int Conference on Green Computing Communication and Electrical Engineering (ICGCCEE)2014.
11.
LiW. and BourlardH., Sub-Band Based Log-Energy and its Dynamic Range Stretching for Robust In-Car Speech Recognition, Portland, Oregon, Proc Int Conference Speech Communication Association2012.
12.
DhondeS.B., ChaudhariA. and JagadeS.M., Integration of Mel-frequency Cepstral Coefficients with Log Energy and Temporal Derivatives for Text-Independent Speaker Identification, Singapore, Springer, Volume 1, pp, Proc Int Conference on Data Engineering and Communication Technology: ICDECT 2016791–797.
13.
AlmaadeedN., AggounA. and AmiraA., Speaker identification using multimodal neural networks and wavelet analysis, IET Biometrics, IET Journals & Magazines4(1) (2015), 18–28.
14.
BarbosaF.G. and SilvaW.L.S., Support Vector Machines, Mel-Frequency Cepstral Coefficients and the Discrete Cosine Transform Applied on Voice Based Biometric Authentication, Proc Int Conference SAI Intelligent Systems Conference, London, 2015.
15.
RathorS. and JadonR.S., Text Independent Speaker Recognition Using Wavelet Cepstral Coefficient and Butter Filter, India, pp, Proc Of IEEE Int Conference on Computing Communication and Networking Technologies (ICCCNT) (2017), 1–5DelhiWorth.
16.
KhanchandaniK.B. and HussainM.A., Emotion recognition using multilayer perceptron and generalized feed forward neural network, Journal of Scientific and Industrial Research (JSIR)68(05) (2009), 367–371.
17.
DaqrouqK. and TutunjiT.A., Speaker identification using vowels features through a combined method of formants, wavelets, and neural network classifiers, Applied Soft Computing27 (2015), 231–239.
18.
JensenJ. and TanZ.-H., Minimum mean-square error estimation of mel-frequency cepstral features–a theoretically consistent approach, IEEE/ACM Transactions on Audio, Speech, and Language Processing23(1) (2015), 186–197.
19.
YadavS.S. and BhalkeD.G., Speaker identification system using wavelet transform and VQ modeling technique, International Journal of Computer Applications112(9) (2015), 75–88.
20.
BiswasA., SahuP.K., BhowmickA. and ChandraM., Articulation based admissible wavelet packet feature based on human cochlear frequency response for TIMIT speech recognition, Ain Shams Engineering Journal5(4) (2014), 1189–1198.
21.
PavezE. and SilvaJ.F., Analysis and design of Wavelet-Packet Cepstral coefficients for automatic speech recognition, Speech Communication54(6) (2012), 814–835.
22.
Pradeep KumarP., RaoP., A Study of Frequency-Scale Warping for Speaker Recognition, Proc of National Conference on Communications, NCC 2004, IISc Bangalore, 2004.
23.
BiswasA., SahuP.K., BhowmickA. and ChandraM., Admissible wavelet packet subband-based harmonic energy features for Hindi phoneme recognition, IET Signal Processing9(8) (2015).
24.
SquartiniS., PrincipiE., RotiliR. and PiazzaF., Environmental robust speech and speaker recognition through multi-channel histogram equalization, Neurocomputing78(1) (2012), 111–120.
25.
de JesúsR.J., EdwinL., Meda-CampañaJesús A., PáramoL.A., FranciscoN.J. and JaimeP., Neural network updating via argument Kalman filter for modeling of Takagi-Sugeno fuzzy models, Journal of Intelligent & Fuzzy Systems35(2) (2018), 2585–2596.
26.
Xiao-LiM., Fu-GuiS. and Jen-ChihY., An inequality approach for evaluating decision making units with a fuzzy output, Journal of Intelligent & Fuzzy Systems34(1) (2018), 459–465.
27.
de JesÚsJ., Rubio, SOFMLS: Online self-organizing fuzzy modified least-squares network, IEEE Transactions on Fuzzy Systems17(6) (2009), 1296–1309.
28.
ZhangX.-M. and HanQ.-L., State estimation for static neural networks with time-varying delays based on an improved reciprocally convex inequality, IEEE Transactions on Neural Networks and Learning Systems29(4) (2018), 1376–1381.
29.
de JesúsJ., Rubio, A method with neural networks for the classification of fruits and vegetables, Soft Computing21(23) (2017), 7207–7220.
30.
JiangM., LiangY., FengX., FanX., PeiZ., XueY. and GuanR., Text classification based on deep belief network and softmax regression, Neural Computing and Applications29(1) (2018), 61–70.
31.
MakremB.J., ImenJ. and KaïsO., Study of speaker recognition system based on Feed Forward deep neural networks exploring text-dependent mode, Sciences of Electronics, Technologies of Information and Telecommunications SETIT2016.
32.
MueenF., AhmedA., SanaullahA. and Gaba, Speaker recognition using artificial neural networks, Students Conference IEEE, ISCON ’02, 2002.
33.
Le-QingZ., Insect Sound Recognition Based on MFCC and PNN, Pro International Conference on Multimedia and Signal Processing (CMSP)2011.
34.
JayasreeT., DevarajD. and SukaneshR., Power quality disturbance classification using Hilbert transform and RBF networks, Neurocomputing73(7–9) (2010), 1451–1456.
35.
MaazouziA.-E., AqiliN., RajiM. and HammouchA., A speaker recognition system using power spectrum density and similarity measurements, IEEE Third World Conference on Complex Systems (WCCS), Marrakech, Morocco, 2015.
36.
ShoumyN.J., YaakobS.N., EhkanP., AliMd.S. and KhatunS., Cascade-forward neural network performance study for bloodstain image analysis, IEEE Int Conference Electronic Design (ICED), Thailand, IEEE, 2016.
37.
KuaJ.M.K., ThiruvaranT., AmbikairajahM.N.E. and EppsJ., Investigation of Spectral Centroid Magnitude and Frequency for Speaker Recognition, The Speaker and Language Recognition Workshop, Brno, Czech Republic, 2010.
38.
NawiN.M., KhanA. and RehmanM.Z., CSLM: Levenberg marquardt based back propagation algorithm optimized with cuckoo search, Journal of ICT Research and Applications7(2) (2013).
39.
FuruiS.J., Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology
2005.
40.
CaonD.R.S., AmehrayeA., RazikJ., CholletG., AndreaoR.V. and MokbelC., Experiments on Acoustic Model supervised adaptation and evaluation by K-Fold Cross Validation technique, Proc International Symposium on I/V Communications and Mobile Network, 2010.
41.
RenishaG.P., KarpagavalliK.P. and Krishnaveni, Classification of gender based on voice using support vector machine, International Journal of Advanced Research Trends in Engineering and Technology (IJARTET)3(4) (2016).
42.
LalithaS., AshwiniV., MadhusudhanK.N. and SachinB.S., Person authentication using face and voice modalities, International Journal of Advances in Science Engineering and Technology1(2) (2013).
