Authors:
NatalijaV. Chmelarova (Kudriavtseva),Vyacheslav A. Tykhonov,Valerij M. Bezruk,Pavel Chmelar,Lubos Rejfek,DOI NO:
https://doi.org/10.26782/jmcms.spl.4/2019.11.00018Keywords:
Composite Vector Stochastic Processes Autoregressive Models,Power Spectrum Density,Speaker Verification,Abstract
This paper deals with the speaker verification system similar to a fingerprint or an eye scanner. For these purpose a long-term words’ model and its spectral characteristics were used. The speaker verification method uses the word’s sound parametric spectrum factorization in composite vector stochastic process representation based on the multiplicative autoregressive model. The developed method enables to receive the words’ features with stable characteristics for the same speaker and differ for different speakers. During the training phase speaker's etalon frequencies has to be estimated for a pronounced word repeated several times. In the verification phase a speaker pronouncing the same word, word's frequencies are estimated and compared with the etalon frequencies database to find the best match or his deny. The results presented in the paper showed the high correct identification probability.Refference:
I. Chen Y. and Tang Z. M. (2013) ‘The speaker recognition of noisy short
utterance. ICISBDE, pp. 666–671
II. Das R. K., and Mahadeva Prasanna S. R. (2016) Exploring different
attributes of source information for speaker verification with limited test
data, J. Acoust. Soc. Am., Vol. 1, pp. 184–190
III. Dişken G., Tüfekçi Z., and Saribulut L. (2017) A review on feature extraction
for speaker recognition under degraded conditions’, IETE Tech. Rev.,
2017, Vol 3,
pp. 321–332
IV. Guo J., Yeung G., Muralidharan D., Arsikere H., Afshan A., Alwan A.
(2016) Speaker Verification Using Short Utterances with DNN-Based
Estimation of Subglottal Acoustic Features, Proc. Interspeech 2016, 2219-
2222.
V. Hansen J. H. L., and Hasan T. (2015) Speaker recognition by machines and
humans: a tutorial review, IEEE Signal Process. Mag., Vol. 6, pp. 74–99
VI. Jayanna H., and Prasanna S. M. (2009) Analysis, feature extraction, modeling
and testing techniques for speaker recognition, IETE Tech. Rev. Vol 3, pp.
181–190
VII. KinnunenT., and LiH. (2010) An overview of text-independent speaker
recognition: from features to supervectors, Speech Commun., Vol. 1, pp. 12–
40
VIII. Kudriavtseva N. V. (2014) Factorization of processes parametric spectra on
the base of multiplicative linear prediction polymodels,
RADIOELEKTRONIKA 2014 24th International Conference, pp.1-4
IX. Kudriavtseva N. V. and Fil I. O. (2012) Factorization of Rhythmograms
Parametric Spectra on the Base of Multiplicative Linear Prediction Models,
IEEE East-West Design & Test Symposium (EWDTS’2012), Kharkiv,
Ukraine, pp. 538-540
X. Li L., Wang D., Zhang C., and Zheng T. F. (2016) Improving short utterance
speaker recognition by modeling speech unit classes, IEEE Trans. Audio
Speech Lang. Process., Vol. 6, pp. 1129–1139
XI. LiZ.Y., ZhangW.Q. and LiuJ. (2015) Multi-resolution time frequency feature
and complementary combination for short utterance speaker
recognition, Multimedia Tools Appl., Vol. 3,pp. 937–953
XII. Poddar A., Sahidullah Md., and Saha G. (2018) Speaker Verification with
Short Utterances: A Review of Challenges, Trends and Opportunities, IET
Biometrics. 7 (2): 91–101.
XIII. Sahidullah M., and Saha G. (2012) Design, analysis and experimental
evaluation of block based transformation in MFCC computation for speaker
recognition’, Speech Commun., Vol. 4, pp. 543–565
XIV. Sahidullah Md., and Kinnunen T. (2016) Local spectral variability features
for speaker verification”. Digital Signal Processing, pp. 1–11
XV. SoldiG., BozonnetS., AlegreF., Beaugeant, Ch., and Evans N.(2014) Shortduration
speaker modelling with phone adaptive training., Proc. Odyssey
XVI. Tykhonov V.A., and Fil I. O. (2011) Statistical modelling of composite
vectorial stochastic processes,Radiotekhnika Journal, #165, KhNURE, pp.
173-176
XVII. Tykhonov V.A.,Kudriavtseva N. V., and Fil I. O. (2011b) Mathematical
models of combining vectorial stochastic processes, Eastern-European
Journal of Foremost Technologies, pp. 17-20