kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университетkaz29-133Research ArticleФИЗИКО-МАТЕМАТИЧЕСКИЕ И ТЕХНИЧЕСКИЕ НАУКИPHYSICAL, MATHEMATICAL AND TECHNICAL SCIENCESСИСТЕМАТИЧЕСКИЙ ОБЗОР И АНАЛИЗ ОСОБЕННОСТЕЙ ИДЕНТИФИКАЦИИ ПО ГОЛОСУSYSTEMATIC REVIEW AND ANALYSIS OF THE PECULIARITIES OF IDENTIFICATION BY VOICEМамырбаевО. Ж.MamyrbayevO.

PhD

КыдырбековаА. С.KydyrbekovaA. S.АхмедияроваА. Т.AkhmediyarovaА.

РhD, ГНС

ТұрдалыұлыМ.TurdalyulyM.

докторант, НС

МекебаевН. О.MekebayevN.

докторант, НС

Институт информационных и вычислительных технологий КН МОН РККазахстан201907112021162120133Copyright © Мамырбаев О.Ж., Кыдырбекова А.С., Ахмедиярова А.Т., Тұрдалыұлы М., Мекебаев Н.О., 20212021Мамырбаев О.Ж., Кыдырбекова А.С., Ахмедиярова А.Т., Тұрдалыұлы М., Мекебаев Н.О.Mamyrbayev O., Kydyrbekova A.S., Akhmediyarova А., Turdalyuly M., Mekebayev N.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/133

Идентификация по голосу - это процесс идентификации говорящего по данному высказыванию путем сравнения голосовой биометрии высказывания с теми моделями высказывания, которые были сохранены заранее. Технологии идентификации по голосу получили новое направление благодаря достижениям в области искусственного интеллекта и широко используются в различных областях. Извлечение признаков является одним из наиболее важных аспектов идентификации по голосу, который существенно влияет на процесс и производительность идентификации. Этот систематический обзор проводится для выявления, сравнения и анализа различных подходов, методов и алгоритмов извлечения признаков для идентификации по голосу, чтобы предоставить справочную информацию о подходах извлечения признаков для приложений идентификации по голосу и будущих исследований. В ходе исследования были рассмотрены модели: основанные на шаблонах, основанные на векторном квантовании, динамическом переносе времени, модель гистограмм, стохастические модели, модели гауссовой смеси и скрытая Марковская модель, основанные на Mel-частотных кепстральных коэффициентах, генеративное или векторное квантование, дискриминационные модели (обычно с использованием методов машинного обучения, таких как SVM и ANN). Это исследование показало, что текущая тенденция исследования идентификации заключается в разработке надежной универсальной структуры идентификации по голосу для решения важных проблем идентификации по голосу, таких как адаптивность, сложность, многоязычное распознавание и устойчивость к шуму. Результаты, представленные в этом исследовании, основаны на прошлых публикациях, цитатах и количестве реализаций, причем цитаты являются наиболее актуальными. Эта статья также представляет общий процесс идентификации по голосу.

Voice identification is the process of identifying a speaker by a given utterance by comparing voice biometrics of a utterance with those utterance models that were saved in advance. Voice identification technologies have gained a new direction due to advances in artificial intelligence and are widely used in various fields. Character extraction is one of the most important aspects of voice identification, which significantly affects the identification process and performance. This systematic review is conducted to identify, compare and analyze various approaches, methods and algorithms for extracting features for voice identification, to provide background information on character retrieval approaches for voice identification applications and future research. The study examined models: based on patterns, based on vector quantization, dynamic time transfer, histogram model, stochastic models, Gaussian mixture models and hidden Markov model, based on Mel-frequency cepstral coefficients, generative or vector quantization, discriminatory models (usually using machine learning methods such as SVM and ANN).This study showed that the current trend of identification research is to develop a robust, universal voice identification structure for solving important voice identification problems, such as adaptability, complexity, multilingual recognition, and resistance to noise. The results presented in this study are based on past publications, quotations and the number of implementations, the quotes being the most relevant. This article also presents the general process of voice identification.

биометриябиометрическая аутентификацияголосовая аутентификацияречевые технологииголосовая биометрияидентификация по голосураспознавание по голосуbiometricsbiometric authenticationvoice authenticationspeech technologyvoice biometricsIdentification by voicevoice recognitionReferencesA. Jain L.Hang and S. Pankanti. “Can multi-biom etrics im prove perform ance,” Proceedings of Auto ID, 59-64, 1999.A. Jain L.Hang and S. Pankanti. “Can multi-biom etrics im prove perform ance,” Proceedings of Auto ID, 59-64, 1999.Dutta, M., Patgiri, C., Sarma, M., & Sarma, K. K. (2015). Closed-set text-independent speaker identification system using multiple ANN classifiers. In Proceedings o f the 3rd international conference on frontiers o f intelligent computing: Theory and applications (FICTA) 2014 (pp. 377-385).Dutta, M., Patgiri, C., Sarma, M., & Sarma, K. K. (2015). Closed-set text-independent speaker identification system using multiple ANN classifiers. In Proceedings o f the 3rd international conference on frontiers o f intelligent computing: Theory and applications (FICTA) 2014 (pp. 377-385).Islam, M. R., & Rahman, M. F. (2009). Im provem ent o f text dependent speaker identification system using neuro-genetic hybrid algorithm in office environmental conditions. International Journal o f Com puter Science Issues, 1, 42-48.Islam, M. R., & Rahman, M. F. (2009). Im provem ent o f text dependent speaker identification system using neuro-genetic hybrid algorithm in office environmental conditions. International Journal o f Com puter Science Issues, 1, 42-48.Kekre, H. B., Athawale, A., & Desai, M. (2011). Speaker identification using row mean vector of spectrogram. In Proceedings o f the international conference and workshop on emerging trends in technology (pp. 171-174).Kekre, H. B., Athawale, A., & Desai, M. (2011). Speaker identification using row mean vector of spectrogram. In Proceedings o f the international conference and workshop on emerging trends in technology (pp. 171-174).Boujelbene, S. Z., M ezghanni, D. B. A., & Ellouze, N. (2009). Robust text independent speaker identification using hybrid GM M -SVM System. International Journal of Digital Content Technology and its Applications, 3, 103-110.Boujelbene, S. Z., M ezghanni, D. B. A., & Ellouze, N. (2009). Robust text independent speaker identification using hybrid GM M -SVM System. International Journal of Digital Content Technology and its Applications, 3, 103-110.Revathi, A., & Venkataramani, Y (2009). Text independent com posite speaker identification / verification using multiple features. In 2009 W RI W orld congress on com puter science and inform ation engineering: 7 (pp. 257-261).Revathi, A., & Venkataramani, Y (2009). Text independent com posite speaker identification / verification using multiple features. In 2009 W RI W orld congress on com puter science and inform ation engineering: 7 (pp. 257-261).Verma, G. K. (2011). M ulti-feature fusion for closed set text independent speaker identification. In International conference on inform ation intelligence, systems, technology and m anagem ent (pp. 170-179).Verma, G. K. (2011). M ulti-feature fusion for closed set text independent speaker identification. In International conference on inform ation intelligence, systems, technology and m anagem ent (pp. 170-179).Richardson, F., Reynolds, D., & Dehak, N. (2015a). Deep neural network approaches to speaker and language recognition. IEEE Signal Processing Letters, 22, 1671-1675.Richardson, F., Reynolds, D., & Dehak, N. (2015a). Deep neural network approaches to speaker and language recognition. IEEE Signal Processing Letters, 22, 1671-1675.Farrell, K. R., M ammone, R. J., & Assaleh, K. T. (1994). Speaker recognition using neural net­ works and conventional classifiers. IEEE Transactions on speech and audio processing, 2, 194­-205.Farrell, K. R., M ammone, R. J., & Assaleh, K. T. (1994). Speaker recognition using neural net­ works and conventional classifiers. IEEE Transactions on speech and audio processing, 2, 194­-205.Hong Kong, China: IEEE. Larcher, A., Lee, K. A., Ma, B., & Li, H. (2014). Text-dependent speak­ er verification: Classifiers, databases and RSR2015. Speech communication, 60, 56-77.Hong Kong, China: IEEE. Larcher, A., Lee, K. A., Ma, B., & Li, H. (2014). Text-dependent speak­ er verification: Classifiers, databases and RSR2015. Speech communication, 60, 56-77.Lippmann, R. P. (1989). Review o f neural networks for speech recognition. Neural computation, 1, 1-38.Lippmann, R. P. (1989). Review o f neural networks for speech recognition. Neural computation, 1, 1-38.Sidorov, M., Schmitt, A., Zablotskiy, S., & M inker, W. (2013). Survey o f automated speaker identification methods. In 2013 9th international conference on intelligent environm ents (IE) (pp. 236-239).Sidorov, M., Schmitt, A., Zablotskiy, S., & M inker, W. (2013). Survey o f automated speaker identification methods. In 2013 9th international conference on intelligent environm ents (IE) (pp. 236-239).Disken, G., Tufeksi, Z., Saribulut, L., & Cevik, U. (2017). A review on feature extraction for speaker recognition under degraded conditions. IETE Technical Review, 34, 321-332.Disken, G., Tufeksi, Z., Saribulut, L., & Cevik, U. (2017). A review on feature extraction for speaker recognition under degraded conditions. IETE Technical Review, 34, 321-332.Rao, K. S., & Sarkar, S. (2014a). Robust speaker verification: A review. In Robust speaker recognition in noisy environm ents (pp. 13-27).Rao, K. S., & Sarkar, S. (2014a). Robust speaker verification: A review. In Robust speaker recognition in noisy environm ents (pp. 13-27).Chavan, M., & Chougule, S. (2012). Speaker features and recognition techniques: A review. Inter­national Journal of Computational Engineering Research, 2, 720-728.Chavan, M., & Chougule, S. (2012). Speaker features and recognition techniques: A review. Inter­national Journal of Computational Engineering Research, 2, 720-728.S. S. Tirumala et al. / Expert Systems With Applications 90 (2017) 250-271.S. S. Tirumala et al. / Expert Systems With Applications 90 (2017) 250-271.Nagaraja, B. G., & Jayanna, H. S. (2012). M ultilingual speaker identification with the constraint of limited data using multitaper MFCC. In International conference on security in com puter networks and distributed systems (pp. 127-134).Nagaraja, B. G., & Jayanna, H. S. (2012). M ultilingual speaker identification with the constraint of limited data using multitaper MFCC. In International conference on security in com puter networks and distributed systems (pp. 127-134).Lawson, A., Vabishchevich, P., Huggins, M., Ardis, P., Battles, B., & Stauffer, A. (2011). Survey and evaluation of acoustic features for speaker recognition. In Acoustics, speech and signal processing (ICASSP), 2011 ieee international conference on (pp. 5444-5447).Lawson, A., Vabishchevich, P., Huggins, M., Ardis, P., Battles, B., & Stauffer, A. (2011). Survey and evaluation of acoustic features for speaker recognition. In Acoustics, speech and signal processing (ICASSP), 2011 ieee international conference on (pp. 5444-5447).Daoudi, K., Jourani, R., Andre, O. R. e. g., & Aboutajdine, D. (2011). In Speaker identification using discriminative learning of large margin GMM: 6 (pp. 300-307).Daoudi, K., Jourani, R., Andre, O. R. e. g., & Aboutajdine, D. (2011). In Speaker identification using discriminative learning of large margin GMM: 6 (pp. 300-307).Shih, P.-Y., Lin, P.-C., Wang, J.-F., & Lin, Y.-N. (2011). Robust several-speaker speech recognition with highly dependable online speaker adaptation and identification. Journal of network and computer applications, 34, 1459-1467.Shih, P.-Y., Lin, P.-C., Wang, J.-F., & Lin, Y.-N. (2011). Robust several-speaker speech recognition with highly dependable online speaker adaptation and identification. Journal of network and computer applications, 34, 1459-1467.Jiang, S., Frigui, H., & Calhoun, A. W. (2015). Speaker identification in medical simulation data using fisher vector representation. In 2015 IEEE 14th international conference on machine learning and applications (iCM LA) (pp. 197-201).Jiang, S., Frigui, H., & Calhoun, A. W. (2015). Speaker identification in medical simulation data using fisher vector representation. In 2015 IEEE 14th international conference on machine learning and applications (iCM LA) (pp. 197-201).Anguera, X., Bozonnet, S., Evans, N., Fredouille, C., Friedland, G., & Vinyals, O. (2012). Speaker diarization: A review of recent research. IEEE Transactions on Audio, Speech, and Language Processing, 20, 356-370 6.Anguera, X., Bozonnet, S., Evans, N., Fredouille, C., Friedland, G., & Vinyals, O. (2012). Speaker diarization: A review of recent research. IEEE Transactions on Audio, Speech, and Language Processing, 20, 356-370 6.Poignant, J., Besacier, L., & Quenot, G. (2015). Unsupervised speaker identification in TV broad­ cast based on written names. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 23, 57-68.Poignant, J., Besacier, L., & Quenot, G. (2015). Unsupervised speaker identification in TV broad­ cast based on written names. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 23, 57-68.Jin, Q., Toth, A. R., Schultz, T., & Black, A. W. (2009). Speaker deidentification via voice transformation (pp. 529-533).Jin, Q., Toth, A. R., Schultz, T., & Black, A. W. (2009). Speaker deidentification via voice transformation (pp. 529-533).Justin, T., Struc, V., Dobrisek, S., Vesnicer, B., Ipsic, I., & Mihelic, F. (2015). In Speaker de-identification using diphone recognition and speech synthesis: 4 (pp. 1-7).Justin, T., Struc, V., Dobrisek, S., Vesnicer, B., Ipsic, I., & Mihelic, F. (2015). In Speaker de-identification using diphone recognition and speech synthesis: 4 (pp. 1-7).Pobar, M., & Ipsic, I. (2014). Online speaker de-identification using voice transformation. In 2014 37th International convention on inform ation and communication technology, electronics and microelectronics (mipro) (pp. 1264-1267).Pobar, M., & Ipsic, I. (2014). Online speaker de-identification using voice transformation. In 2014 37th International convention on inform ation and communication technology, electronics and microelectronics (mipro) (pp. 1264-1267).Haigh, J. A., & Mason, J. S. (1993). Robust voice activity detection using cepstral features. In 1993 IEEE Region 10 conference on proceedings. computer, communication, control and power engineering (TEN CO N ’93): 3 (pp. 321-324).Haigh, J. A., & Mason, J. S. (1993). Robust voice activity detection using cepstral features. In 1993 IEEE Region 10 conference on proceedings. computer, communication, control and power engineering (TEN CO N ’93): 3 (pp. 321-324).Ramir. J., Segura, J. E. C., Ben, I. T. C., De La Torre, A., & Rubio, A. (2004). Efficient voice activity detection algorithm susing long-term speech information. Speech Communication, 42, 271-287.Ramir. J., Segura, J. E. C., Ben, I. T. C., De La Torre, A., & Rubio, A. (2004). Efficient voice activity detection algorithm susing long-term speech information. Speech Communication, 42, 271-287.Beigi, H. (2011). Speaker Modeling. In Fundam entals of speaker recognition (pp. 525-541).Beigi, H. (2011). Speaker Modeling. In Fundam entals of speaker recognition (pp. 525-541).Ganchev, T. (2011). Contemporary methods for speech parameterization. pp. 233-236.Ganchev, T. (2011). Contemporary methods for speech parameterization. pp. 233-236.Kawakami, Y , Wang, L., Kai, A., & Nakagawa, S. (2014). Speaker identification by com bining various vocal tract and vocal source features. In International conference on text, speech, and dialogue (pp. 382-389).Kawakami, Y , Wang, L., Kai, A., & Nakagawa, S. (2014). Speaker identification by com bining various vocal tract and vocal source features. In International conference on text, speech, and dialogue (pp. 382-389).Kawakami, Y , Wang, L., & Nakagawa, S. (2013). Speaker identification using pseudo pitch synchronized phase information in noisy environments. In 2013 Asia-Pacific on signal and inform a­ tion processing association annual summit and conference (APSIPA) (pp. 1-4).Kawakami, Y , Wang, L., & Nakagawa, S. (2013). Speaker identification using pseudo pitch synchronized phase information in noisy environments. In 2013 Asia-Pacific on signal and inform a­ tion processing association annual summit and conference (APSIPA) (pp. 1-4).Tanprasert, C., & Achariyakulporn, V. (2000). Comparative study of GMM, DTW, and ANN on Thai speaker identification system. Sixth international conference on spoken language processing, ICSLP 2000 / INTERSPEECH 2000.Tanprasert, C., & Achariyakulporn, V. (2000). Comparative study of GMM, DTW, and ANN on Thai speaker identification system. Sixth international conference on spoken language processing, ICSLP 2000 / INTERSPEECH 2000.Luengo, I., Navas, E., Sainz, I. N. A., Saratxaga, I., Sanchez, J., & Odriozola, I. (2008). Text independent speaker identification in multilingual environments. In Proceedings o f the international conference on language resources and evaluation, LREC 2008.Luengo, I., Navas, E., Sainz, I. N. A., Saratxaga, I., Sanchez, J., & Odriozola, I. (2008). Text independent speaker identification in multilingual environments. In Proceedings o f the international conference on language resources and evaluation, LREC 2008.Sarma, M., & Sarma, K. K. (2013a). Speaker identification model for Assam ese language using a neural framework. In The 2013 international joint conference on neural networks (IJCNN) (pp. 1-7).Sarma, M., & Sarma, K. K. (2013a). Speaker identification model for Assam ese language using a neural framework. In The 2013 international joint conference on neural networks (IJCNN) (pp. 1-7).Jawarkar, N. P., Holambe, R. S., & Basu, T. K. (2012). Text-independent speaker identification in emotional environments: A classifier fusion approach. In Frontiers in Com puter Education (pp. 569-576).Jawarkar, N. P., Holambe, R. S., & Basu, T. K. (2012). Text-independent speaker identification in emotional environments: A classifier fusion approach. In Frontiers in Com puter Education (pp. 569-576).Jawarkar, N. P., Holambe, R. S., & Basu, T. K. (2015). Effect of nonlinear compression function on the performance of the speaker identification system under noisy conditions. In Proceedings of the 2nd International Conference on Perception and Machine Intelligence (pp. 137-144).Jawarkar, N. P., Holambe, R. S., & Basu, T. K. (2015). Effect of nonlinear compression function on the performance of the speaker identification system under noisy conditions. In Proceedings of the 2nd International Conference on Perception and Machine Intelligence (pp. 137-144).Nagaraja, B. G., & Jayanna, H. S. (2012). Multilingual speaker identification with the constraint of limited data using m ultitaper MFCC. In International conference on security in com puter networks and distributed systems (pp. 127-134).Nagaraja, B. G., & Jayanna, H. S. (2012). Multilingual speaker identification with the constraint of limited data using m ultitaper MFCC. In International conference on security in com puter networks and distributed systems (pp. 127-134).Wang, L., Zhang, Z., & Kai, A. (2013). Hands-free speaker identification based on spectral subtraction using a multi-channel least mean square approach. In 2013 IEEE international conference on acoustics, speech and signal processing (pp. 7224-7228Wang, L., Zhang, Z., & Kai, A. (2013). Hands-free speaker identification based on spectral subtraction using a multi-channel least mean square approach. In 2013 IEEE international conference on acoustics, speech and signal processing (pp. 7224-7228Busso, C., Hernanz, S., Chu, C.-W., Kwon, S.-i., Lee, S., & Georgiou, P. G. (2005). Smart room: Participant and speaker localization and identification. IEEE International Conference on A coustics, Speech, and Signal Processing: 2. IEEE. Campbell, J. P. (1997). Speaker recognition: A tuto­rial. Proceedings of the IEEE, 85, 1437-1462 6.Busso, C., Hernanz, S., Chu, C.-W., Kwon, S.-i., Lee, S., & Georgiou, P. G. (2005). Smart room: Participant and speaker localization and identification. IEEE International Conference on A coustics, Speech, and Signal Processing: 2. IEEE. Campbell, J. P. (1997). Speaker recognition: A tuto­rial. Proceedings of the IEEE, 85, 1437-1462 6.Sahidullah, M., Chakroborty, S., & Saha, G. (2011). Improving perform ance of speaker identi­fication system using com plementary information fusion. In Proceedings of 17th international conference on advanced com puting and com munications (pp. 182-187).Sahidullah, M., Chakroborty, S., & Saha, G. (2011). Improving perform ance of speaker identi­fication system using com plementary information fusion. In Proceedings of 17th international conference on advanced com puting and com munications (pp. 182-187).Ahmed, M. Y , Kenkeremath, S., & Stankovic, J. (2015). Socialsense: A collaborative mobile platform for speaker and mood identification. In Wireless sensor networks: 8965 (pp. 68-83).Ahmed, M. Y , Kenkeremath, S., & Stankovic, J. (2015). Socialsense: A collaborative mobile platform for speaker and mood identification. In Wireless sensor networks: 8965 (pp. 68-83).Farhood, Z., & Abdulghafour, M. (2010). Investigation on model selection criteria for speak­er identification. In 2010 International symposium in information technology (ITSim): 2 -6 (pp. 537-541).Farhood, Z., & Abdulghafour, M. (2010). Investigation on model selection criteria for speak­er identification. In 2010 International symposium in information technology (ITSim): 2 -6 (pp. 537-541).

The authors declare that there are no conflicts of interest present.