Abstract
Recognizing the person from a sample of their voice print or speech samples is known as Speaker recognition. It is an emerging technology, in recent years machine learning (ML) based classification schemes have been observed as one kind of alternate solution for speaker recognition. In this paper adaptive boosting (AdaBoost) combined with a powerful ML classifier (Random Forest) is proposed to handle multi-class imbalanced speaker data classification. Based on weights AdaBoost integrates several sub-classifiers and constructs a robust classifier. A new strong and more accurate technique is proposed by employing Random Forests as the initial stage classifier and AdaBoost as the subsequent stage classifiers, to decide the class that the speaker sample belongs to. Three dissimilar datasets are utilized to estimate the robustness of the proposed hybrid AdaBoost technique. The classification results of the hybrid RF-AdaBoost are evaluated against other state-of-the-art algorithms (kNN, SVM, RF, kNN- AdaBoost, and SVM- AdaBoost), experimental results convey the proposed algorithm improves accuracy as well as stability for the imbalanced speaker data. The f1_score for RF-AdaBoost is 92%, as well as it produces minimum root mean squared value. The stability of the hybrid algorithm is evaluated using Matthews correlation coefficient (MCC), g-means metric value, and variance, it shows RF- AdaBoost outperforms the other state-of-the-art algorithms in all the aspects of speaker recognition.
Similar content being viewed by others
References
Jain A K, Ross A and Prabhakar S 2004 An introduction to biometric recognition. IEEE Trans. Circuits Syst. Video Technol. 14(1): 4–20. https://doi.org/10.1109/TCSVT.2003.818349
Billeb S, Rathgeb C, Reininger H, Kasper K and Busch C 2015 Biometric template protection for speaker recognition based on universal background models. IET Biometrics 4(2): 116–126
Cochran W T, Cooley J W, Favin D L, Helms H D, Kaenel R A, Lang W W, Maling G C, Nelson D E, Rader C M and Welch P D 1967 What is the fast fourier transform. Proceedings of the IEEE 55(10): 1664–1674
Ramachandran R P, Farrell K R, Ramachandran R and Mammone R J 2002 Speaker recognition-general classifier approaches and data fusion methods. Pattern Recognition 35(12): 2801–2821
Kinnunen T and Li H 2010 An overview of text independent speaker recognition: from features to super vectors. Speech Communications 52(1): 12–40
Amrani Yassine Al, Lazaar Mohamed and Kadiri Kamal Eddine El 2018 Random Forest and Support Vector Machine based Hybrid Approach to Sentiment Analysis. Procedia Computer Science 127: 511–520
Singh N, Khan R A and Shree R 2012 Applications of speaker recognition. Procedia Engineering 38: 3122–3126
Reynolds D A 2002 An Overview of Automatic Speaker Recognition Technology. IEEE International Conference on Acoustics, Speech, and Signal Processing IV: 4072–4075
Prabhakar S, Pankanti S and Jain A K 2003 Biometric recognition: security and privacy concerns. IEEE Security & Privacy 1(2): 33–42. https://doi.org/10.1109/MSECP.2003.1193209
Molau S, Pitz M, Schluter R and Ney H 2001. Computing mel-frequency cepstral coefficients on the power spectrum. IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221). 1: 73–76. https://doi.org/10.1109/ICASSP.2001.940770
Davis S and Mermelstein P 1980 Comparison of Parametric Representations for Mono syllabic Word Recognition in Continuously Spoken Sentences. IEEE Transactions on Acoustics, Speech, and Signal Processing 28(4): 357–366. https://doi.org/10.1109/TASSP.1980.1163420
Kabal P and Ramachandran R P 1986 The computation of line spectral frequencies using chebyshev polynomials. IEEE Transactions on Acoustics, Speech, and Signal Processing 34(6): 1419–1426
Hermansky H 1990 Perceptual linear predictive (PLP) analysis of speech. Journal of the Acoustical Society of America 87(4): 1738–1752
Yujin Y, Peihua Z and Qun Z 2010 Research of speaker recognition based on combination of LPCC and MFCC. IEEE International Conference on Intelligent Computing and Intelligent Systems 3: 765–767. https://doi.org/10.1109/ICICISYS.2010.5658337
Ai O C, Hariharan M, Yaacob S and Chee L S 2012 Classification of speech dysfluencies with MFCC and LPCC features. Expert Systems with Applications 39(2): 2157–2165
Shahin I and Botros N 1998. Speaker identification using dynamic time warping with stress compensation technique. Proceedings IEEE Southeastcon '98 'Engineering for a New Era. 65–68
Singh S and Rajan E 2011 Vector quantization approach for speaker recognition using MFCC and inverted MFCC. International Journal of Computer Applications 17(1): 1–7
Martinez J, Perez H, Escamilla E and Suzuki M M 2012. Speaker recognition using mel frequency cepstral coefficients (MFCC) and vector quantization (VQ) techniques. In: CONIELECOMP 2012, 22nd International Conference on Electrical Communications and Computers. 248–251
Forsyth M E, Sutherland A M, Elliott J A and Jack M A 1993 HMM speaker verification with sparse training data on telephone quality speech. Speech Communication 13(3–4): 411–416
Lee K F and Hon H W 1988. Large-vocabulary speaker-independent continuous speech recognition using HMM. ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing 1:123–126. https://doi.org/10.1109/ICASSP.1988.196527
Reynolds D A, Quatieri T F and Dunn R B 2000 Speaker Verification using Adapted GaussianMixture Models. Digital Signal Processing 10(1–3): 19–41
Ali T, Spreeuwers L, Veldhuis R and Meuwly D 2014 Biometric evidence evaluation: an empirical assessment of the effect of different training data. IET Biometrics 3(4): 335–346
Shah H N M, Rashid M Z A, Abdollah M F, Kamarudin M N, Lin C K and Kamis Z 2014 Biometric voice recognition in security system. Indian J. Sci. Technol. 7: 104–112
Srinivas Vasamsetti and Santhirani Ch . 2020 Optimization-Based Support Vector Neural network for Speaker Recognition. The Computer Journal. 63(1): 151–167
Hourri S and Kharroubi J 2019 A novel scoring method based on distance calculation for similarity measurement in text independent speaker verification. Procedia Computer Science 148: 256–265
Schapire R E 1990 The Strength of Weak Learnability. Machine Learning 5: 197–227
Breiman Leo. 2003. Manual on setting up, using, and understanding random forests. v3.1. 2003
Freund Y and Schapire R E 1997 A decision theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Science 55(1): 119–139
Schwenk H 1999. Using Boosting To Improve A Hybrid HMM/Neural Network Speech Recognizer. In: 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258). 2:1009–1012
Fine S, Navratil J and Gopinath R A 2001. A hybrid GMM/SVM approach to speaker identification. In: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221). 1: 417–420. https://doi.org/10.1109/ICASSP.2001.940856
Thongkam J, Xu G and Zhang Y 2008. AdaBoost algorithm with random forests for predicting breast cancer survivability. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence). 3062–3069. https://doi.org/10.1109/IJCNN.2008.4634231
Vogt R, Sridharan S and Mason M 2010 Making confident speaker verification decisions with minimal speech. IEEE transactions on audio, speech, and language processing 18(6): 1182–1192
Amami R, Ben Ayed D and Ellouze N 2013. Adaboost with SVM using GMM super vector for imbalanced phoneme data. 2013 6th International Conference on Human System Interactions (HSI). Sopot 328-333, https://doi.org/10.1109/HSI.2013.6577843
Sahidullah M and Saha G 2013 A novel windowing technique for efficient computation of MFCC for speaker recognition. IEEE Signal Process. Lett. 20(2): 149–152. https://doi.org/10.1109/LSP.2012.2235067
Chakrabotry K A, Talele S and Upadhya S 2014 Voice Recognition Using MFCC Algorithm. International Journal of Innovative Research in Advanced Engineering. 10(1): 158–161
Rao K S and Sarkar S 2014 Robust Speaker Modeling for Speaker Verification in Noisy Environments. Springer Briefs in Electrical and Computer Engineering. https://doi.org/10.1007/978-3-319-07130-5
Gosztolya G 2014. Is AdaBoost Competitive for Phoneme Classification?. In: 2014 IEEE 15th International Symposium on Computational Intelligence and Informatics (CINTI). 61–66
McClanahan R and Leon P L D 2015 Reducing computation in an i-vector speaker recognition system using a tree-structured universal background model. Speech Commun. 66: 36–46
D’Arca E, Robertson N M and Hopgood J R 2016 Robust indoor speaker recognition in a network of audio and video sensors. Signal Process. 129: 137–149
Huang H, Yao S, Zhou R and Yan Y 2016 Robust speaker recognition using library of cross-domain variation compensation transforms. Electronics Letters 52(4): 321–323
Cumani S and Laface P 2017 Non-linear I-vector transformations for PLDA based speaker recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 25(4): 908–919
Khosravani A, Homayounpour M M, Dijana P and Chollet G 2016. A PLDA approach for Language and text independent speaker recognition. The Speaker and Language Recognition Workshop https://doi.org/10.21437/Odyssey.2016-38
Alku P and Saeidi R 2017 The linear predictive modeling of speech from higher-lag autocorrelation coefficients applied to noise-robust speaker recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 25(8): 1606–1617. https://doi.org/10.1109/TASLP.2017.2703165
Xu L, Lee K A, Li H and Yang Z 2018 Generalizing I-vector estimation for rapid speaker recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing 26(4): 749–759
Haixiang Guo, Yijing Li, Yanan Li, Xiao Liu and Jinling Li 2016 BPSO-Adaboost-KNN ensemble learning algorithm for multi-class imbalanced data classification. Engineering Applications of Artificial Intelligence 49: 176–193
Leung Joseph Hang, Kuo Yu-Liang, Weng Ting-Wei and Chin Chiun-Li 2017 Hybrid-Neuro-Fuzzy System and Adaboost-Classifier for Classifying Breast Calcification. Journal of Computers (Taiwan) 28(2): 29–42. https://doi.org/10.3966/199115592017042802003
Ranjan S and Hansen J H L 2018 Curriculum learning based approaches for noise robust speaker recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 26(1): 197–210
Liu Z, Wu Z, Li T, Li J and Shen C 2018 GMM and CNN Hybrid Method for Short Utterance Speaker Recognition. IEEE Transactions on Industrial Informatics 14(7): 3244–3252. https://doi.org/10.1109/TII.2018.2799928
Lu H, Gao H, Ye M, Yan K and Wang X. 2018. A Hybrid Ensemble Algorithm Combining AdaBoost and Genetic Algorithm for Cancer Classification with Gene Expression Data. In: 2018 9th International Conference on Information Technology in Medicine and Education (ITME). 15–19, https://doi.org/10.1109/ITME.2018.00015
Han J H, Bae K M, Hong S K, Park H, Kwak J, Wang H S, Joe D J, Park J H, Jung Y H, Hur S, Yoo C D and Lee K J 2018 Machine learning-based self-powered acoustic sensor for speaker recognition. Nano Energy 53: 658–665
Dhakal P, Damacharla P, Javaid A and Devabhaktuni V 2019 A Near Real-Time Speaker Recognition Architecture for Voice-Based User Interface. Machine Learning and Knowledge Extraction 1(1): 504–520. https://doi.org/10.3390/make1010031
Mokgonyane T B, Sefara T J, Modipa T I, Mogale M M, Manamela M J and Manamela P J 2019. Automatic Speaker Recognition System based on Machine Learning Algorithms. Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA). 141–146, https://doi.org/10.1109/RoboMech.2019.8704837
Peng S, Lv T, Han X, Wu S, Yan C and Zhang H 2019 Remote speaker recognition based on the enhanced LDV-captured speech. Appl. Acoust. 143: 165–170
Gosztolya G and Busa-Fekete R 2019 Calibrating AdaBoost for phoneme classification. Soft Computing 23: 115–128. https://doi.org/10.1007/s00500-018-3577
SamiaAbd El-Moneim, El-Sayed M EL-Rabaie, Nassar M A, Moawad I Dessouky, Nabil A Ismail, Adel S El-Fishawy and Fathi E Abd El-Samie. 2020. Speaker recognition based on preprocessing Approaches. International Journal of Speech Technology., 23: 435–442
Chen S, Shen B, Wang X and Yoo S J 2019 A Strong Machine Learning Classifier and Decision Stumps Based Hybrid AdaBoost Classification Algorithm for Cognitive Radios. Sensors (Basel) 19(23): 5077. https://doi.org/10.3390/s19235077
Ashar A, Bhatti M S and Mushtaq U 2020 Speaker Identification Using a Hybrid CNN-MFCC Approach. International Conference on Emerging Trends in Smart Technologies (ICETST) 2020: 1–4. https://doi.org/10.1109/ICETST49965.2020.9080730
Zvarevashe Kudakwashe and Olugbara Oludayo 2020 Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition. Algorithms 13(3): 70. https://doi.org/10.3390/a13030070
Hamidi M, Satori H, Laaidi N and Satori K 2020. Conception of Speaker Recognition Methods: A Review. 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET). 1–6, https://doi.org/10.1109/IRASET48871.2020.9092118
Anand Sunjyot Singh, Mamodia Ankit Kumar, Acharya Atri, Padam Karanpal Singh and Bhingarkar Sukhada 2018 A Study of Classification Algorithms for Categorizing Website Users using Machine Learning. International Journal of Pure and Applied Mathematics 118(16): 333–348
Meir R and Ratsch G 2003 An introduction to Boosting and Leveraging. Advanced lectures on Machine Learning. https://doi.org/10.1007/3-540-36434-X_4
Li X, Wang L and Sung E 2008 Adaboost with SVM-based component classifiers. Engineering Applications of Artificial Intelligence 21(5): 785–795. https://doi.org/10.1016/j.engappai.2007.07.001
Freund Y 1995 Boosting a weak learning algorithm by majority. Inf. Comput. 121(2): 256–285
Scholkopf B, Sung K K, Burges C, Girosi F, Niyogi P, Poggio T and Vapnik V 1997 Comparing support vector machines with Gaussian kernels to radial basis function classifiers. IEEE Transactions on Signal Processing 45(11): 2758–2765
Sahoo J K and Deepak rishi. 2014 Speaker Recognition Using Support Vector Machines. International Journal of Electrical, Electronics and Data Communication 2(2): 1–4
Dietterich T G 2000 An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Machine Learning. 40(2): 139–157
Breiman L 2001 Random Forests. Machine Learning. 45: 5–32
Meinshausen N 2006 Quantile Regression Forests. J. Machine Learning Research. 7: 983–999
Breima L, Friedman J, Olshen R and Stone C 1984 Classification and regression trees. Wadsworth, Belmont Calif
Leshem G and Ritov Y 2007 Traffic flow prediction using adaboost algorithm with random forests as a weak learner. World Academy of Science, Engineering and Technology 25: 193–198
Feng L 2004. Speaker Recognition, Informatics and Mathematical Modelling, Technical University of Denmark, DTU. English Language Speech Database for Speaker Recognition (ELSDSR)
John S Garofolo, Lori F Lamel, William M Fisher, Jonathan G Fiscus, David S Pallett, Nancy L Dahlgren and Victor Zue. 1993. TIMIT Acoustic-Phonetic Continuous Speech Corpus LDC93S1., Web Download. Philadelphia: Linguistic Data Consortium
Xia Rui, Zong Chengqing and Li Shoushan 2011 Ensemble of feature sets and classification algorithms for sentiment classification. Information Sciences 181(6): 1138–1152
Joshi M V, Kumar V and Agarwal R C 2001. Evaluating Boosting algorithms to classify rare classes: Comparison and improvements. In: Proceedings 2001 IEEE International Conference on Data Mining. 257–264, https://doi.org/10.1109/ICDM.2001.989527
Boughorbel S, Jarray F and Elanbari M 2017. Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric. PLoS One. 12(6): e0177678
Kubat M and Matwin S 2000. Addressing the curse of imbalanced training sets: one-sided selection. In: Proceedings of the 14th International Conference on Machine Learning. 179–186
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Karthikeyan, V., Suja Priyadharsini, S. A strong hybrid AdaBoost classification algorithm for speaker recognition. Sādhanā 46, 138 (2021). https://doi.org/10.1007/s12046-021-01649-6
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12046-021-01649-6