Speaker Identification and Verification Using Convolutional Neural Network CNN
Article Sidebar
Main Article Content
Abstract
Speaker identification and verification are important fields contributing to smart IoT, phone banking, remote login services, E-learning, and other applications. In this work, the speaker identification and verification processes have been experimentally proven to have mutual enhancement effects if they are merged together in a proper manner. Speaker identification and verification work cooperatively so that the verifier will enhance the identifier model. The first step is to identify the speaker using context – independent speech signal, and the identifier model (ID) is trained using a classification model. The model’s outputs are then used to control the verification process as a next step. When the verification result is positive, the first process outcome is approved with high confidence. Otherwise, the negative verification will force the ID process to re-configure itself. The loop continues until both verification and ID agree on the speaker. A multiple Gaussian mixture GMM was used to efficiently model each person’s speech features (MFCC) for using expectation maximization (EM). On the other hand, the conducted experiments showed that the one-dimensional convolutional neural network (1D-CNN) proved its superiority over other models for speaker identification. A novel approach was proposed, proving that little data can be expanded with split-add-noise and train-on-the-fly procedures. In many speaker identification approaches, the specific context was used as a keyword or a password to simplify the processing, requiring big data to achieve high accuracy. It is noteworthy that a small amount of data was enough to efficiently train the proposed model, with a verification error of around 3%, i.e., an accuracy of 97%. Meanwhile, 95% and 96% identification accuracy was achieved using two different datasets. Additionally, the suggested algorithm did not imply using any keyword or password because it is a context-independent approach.
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
THIS IS AN OPEN ACCESS ARTICLE UNDER THE CC BY LICENSE http://creativecommons.org/licenses/by/4.0/
References
Xue Y. Multi-Label Training for Text-Independent Speaker Identification. arXiv preprint arXiv 2022 Nov 14.
Mohammadi M, Mohammadi HRS. Weighted X-Vectors for Robust Text-Independent Speaker Verification with Multiple Enrollment Utterances. Circuits, Systems, and Signal Processing 2022; 41(5):2825-2844.
Nagakrishnan R, Revathi A. Generic Speech-Based Person Authentication System with Genuine and Spoofed Utterances: Different Feature Sets and Models. Multimedia Tools and Applications 2022; 1:1-30.
Gaurav, Bhardwaj S, Agarwal R. An Efficient Speaker Identification Framework Based on Mask R-CNN Classifier Parameter Optimized Using Hosted Cuckoo Optimization (HCO). Journal of Ambient Intelligence and Humanized Computing 2022; 5:1-3.
Shareef SRS, Al-Irhayim YFM. Comparison Between Features Extraction Techniques for Impairments Arabic Speech. Al-Rafidain Engineering Journal 2022; 27(2):190-197.
Monir M et al. Cancelable Speaker Identification Based on Cepstral Coefficients and Comb Filters. International Journal of Speech Technology 2022; 25(2):471-492.
Karthikeyan V. Adaptive Boosted Random Forest-Support Vector Machine Based Classification Scheme for Speaker Identification. Applied Soft Computing 2022; 131:109826.
Hamsa S et al. Speaker Identification from Emotional and Noisy Speech Using Learned Voice Segregation and Speech VGG. Expert Systems with Applications 2023; 224:119871.
AL-Shakarchy ND, Obayes HK, Abdullah ZN. Person Identification Based on Voice Biometric Using Deep Neural Network. International Journal of Information Technology 2023; 15(2):789-795.
Jahangir R et al. Text-Independent Speaker Identification Through Feature Fusion and Deep Neural Network. IEEE Access 2020; 8:32187-32202.
Shafik A et al. Speaker Identification Based on Radon Transform and CNNs in the Presence of Different Types of Interference for Robotic Applications. Applied Acoustics 2021; 177:107665.
Sidorov M et al. Survey of Automated Speaker Identification Methods. Proceedings of the 9th International Conference on Intelligent Environments 2013; 236-239.
Dey N. Applied Speech Processing: Algorithms and Case Studies. Academic Press; 2021.
Dawood A et al. Simulation of Multimedia Data Transmission Over WSN Based on MATLAB/SIMULINK. International Journal of Computing and Digital Systems 2023; 14(1):147-157.
Shi Y, Huang Q, Hain T. H-VECTORS: Improving the Robustness in Utterance-Level Speaker Embeddings Using a Hierarchical Attention Model. Neural Networks 2021; 42:329-339.
Alshaykha AM. E-Learning Visual Design Elements of User Experience Perspective. Tikrit Journal of Engineering Sciences 2022; 29(1):111-118.
Mokgonyane TB et al. A Cross-Platform Interface for Automatic Speaker Identification and Verification. Proceedings of the International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems 2021; 1-6.
Wang X et al. A Network Model of Speaker Identification with New Feature Extraction Methods and Asymmetric BLSTM. Neurocomputing 2020; 403:167-181.
Lawson A et al. Survey and Evaluation of Acoustic Features for Speaker Recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 2011; 5444-5447.
Antony A, Gopikakumari R. Speaker Identification Based on Combination of MFCC and UMRT Based Features. Procedia Computer Science 2018; 143:250-257.
Shahin I, Nassif AB, Bahutair M. Emirati-Accented Speaker Identification in Each of Neutral and Shouted Talking Environments. International Journal of Speech Technology 2018; 21:265-278.
Yadav S, Rai A. Learning Discriminative Features for Speaker Identification and Verification. Proceedings of Interspeech 2018; 2237-2241.
Chakroun R, Frikha M. Improved Text-Independent Speaker Identification and Verification with Gaussian Mixture Models. 12th International Conference on Knowledge Science, Engineering and Management 2019; 3-10.
Pawar MD, Kokate R. A Robust Wavelet Based Decomposition and Multilayer Neural Network for Speaker Identification. 7th Innovations in Electronics and Communication Engineering 2019; 197-209.
Sekkate S, Khalil M, Adib A. Speaker Identification for OFDM-Based Aeronautical Communication System. Circuits, Systems, and Signal Processing 2019; 38(8):3743-3761.
Bunrit S et al. Text-Independent Speaker Identification Using Deep Learning Model of Convolution Neural Network. International Journal of Machine Learning and Computing 2019; 9(2):143-148.
Shi Y, Huang Q, Hain T. Improving Noise Robustness in Speaker Identification Using a Two-Stage Attention Model. arXiv preprint arXiv 2019 Sep 24.
Nicolson A, Paliwal KK. Sum-Product Networks for Robust Automatic Speaker Identification. arXiv preprint arXiv 2019 Oct 26.
Tiwari V et al. Speaker Identification Using Multi-Modal I-Vector Approach for Varying Length Speech in Voice Interactive Systems. Cognitive Systems Research 2019; 57:66-77.
Wilkinghoff K. On Open-Set Speaker Identification With I-Vectors. Proceedings of Odyssey 2020; 408-414.
Roumiassa F, Chelali FZ. Speaker Identification and Verification System for Arabic and Berber Language. 1st International Conference on Communications, Control Systems and Signal Processing 2020; 242-247.
Benesty J, Sondhi MM, Huang Y (Eds). Springer Handbook of Speech Processing. Springer; 2008; 1.
Dawood AAM, Abdulaziz AS, Mohammed AJ. RLC-Based Image Compression Using Wavelet Decomposition with Zero-Setting of Unnecessary Sub-Bands. Journal of Engineering Science and Technology 2022; 17(1):391-403.
Reynolds DA. Gaussian Mixture Models. Encyclopedia of Biometrics 2009; 659-663.
Mahmood MS, Al Dabagh NB. Improving IoT Security Using Lightweight Based Deep Learning Protection Model. Tikrit Journal of Engineering Sciences 2023; 30(1):119-129.
Divya V et al. Improving EEG Electrode Sensitivity with Graphene Nano Powder and Neural Network for Schizophrenia Diagnosis. Tikrit Journal of Engineering Sciences 2023; 30(1):84-93.
Hamsa S et al. Speaker Identification from Emotional and Noisy Speech Using Learned Voice Segregation and Speech VGG. Expert Systems with Applications 2023; 224:119871.
Pentapati HK. Enhancement in Speaker Identification Through Feature Fusion Using Advanced Dilated Convolution Neural Network. International Journal of Electrical and Computer Engineering Systems 2023; 14(3):301-310.