Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Related Works
Experimental and Discussions Database
Results and Discussions
References
All Topics
Computer Science
Artificial Intelligence

Hybrid PSO-ANFIS for Speaker Recognition

Profile image of samiya silarbisamiya silarbi

International Journal of Cognitive Informatics and Natural Intelligence

https://doi.org/10.4018/IJCINI.20210401.OA7
visibility

…

description

14 pages

link

1 file

Abstract

This paper introduces an evolutionary approach for training the adaptive network-based fuzzy inference system (ANFIS). The previous works are based on gradient descendent (GD); this algorithm converges very slowly and gets stuck down at bad local minima. This study applies one of the swarm intelligent branches, named particle swarm optimization (PSO), where the premise parameters of the rules are optimized by a PSO, and the conclusion part is optimized by least-squares estimation (LSE). The hybrid PSO-ANFIS model is performed for speaker recognition on CHAINS speech dataset. The results obtained by the hybrid model showed an improvement on the accuracy compared to similar ANFIS based on gradient descendent optimization.

Related papers

Balanced the Trade-offs problem of ANFIS Using Particle Swarm Optimisation
Science Park Research Organization & Counselling

Improving the approximation accuracy and interpretability of fuzzy systems is an important issue either in fuzzy systems theory or in its applications. It is known that simultaneous optimisation both issues was the trade-offs problem, but it will improve performance of the system and avoid overtraining of data. Particle swarm optimisation (PSO) is part of evolutionary algorithm that is good candidate algorithms to solve multiple optimal solution and better global search space. This paper introduces an integration of PSO for optimising the ANFIS learning especially for tuning membership function parameters and finding the optimal rule for better classification. The proposed method has been tested on four standard dataset from UCI machine learning i.e. Iris Flower, Haberman's Survival Data, Balloon and Thyroid dataset. The results have shown better classification using the proposed PSO-ANFIS and the time complexity has reduced accordingly.

View PDFchevron_right
A Hybrid Approach Based on Genetic Algorithm and Particle Swarm Optimization to Improve Neural Network Classification
Nabil M. Hewahi

Journal of Information Technology Research, 2017

ArtificialNeuralNetwork(ANN)hasplayedasignificantroleinmanyareasbecauseofitsability tosolvemanycomplexproblemsthatmathematicalmethodsfailedtosolve.However,ithassome shortcomings that lead it to stop working in some cases or decrease the result accuracy. In this research the authors propose a new approach combining particle swarm optimization algorithm (PSO)andgeneticalgorithm(GA),toincreasetheclassificationaccuracyofANN.Theproposed approachutilizestheadvantagesofbothPSOandGAtoovercomethelocalminimaproblemofANN, whichpreventsANNfromimprovingtheclassificationaccuracy.Thealgorithmsstartwithusing backpropagationalgorithm,thenitkeepsrepeatingapplyingGAfollowedbyPSOuntiltheoptimum classificationisreached.Theproposedapproachisdomainindependentandhasbeenevaluatedby applyingitusingninedatasetswithvariousdomainsandcharacteristics.Acomparativestudyhas beenperformedbetweentheauthors'proposedapproachandotherpreviousapproaches,theresults showthesuperiorityofourapproach.

View PDFchevron_right
Evolutionary method combining Particle Swarm Optimisation and Genetic Algorithms using fuzzy logic for parameter adaptation and aggregation: the case neural network optimisation for face recognition
Dr. Fevrier Valdez

International Journal of Artificial Intelligence and Soft Computing, 2010

We describe in this paper a new hybrid approach for optimisation combining Particle Swarm Optimisation (PSO) and Genetic Algorithms (GAs) using Fuzzy Logic for parameter adaptation and to integrate the results. The new evolutionary method combines the advantages of PSO and GA to give us an improved FPSO + FGA hybrid method. Fuzzy Logic is used to combine the results of the PSO and GA in the best way possible. Also, fuzzy logic is used to adjust parameters in the FPSO and FGA. The new hybrid FPSO + FGA approach is compared with the PSO and GA methods with a set of benchmark mathematical functions. The proposed hybrid method is also tested with the problem of neural network architecture optimisation. The new hybrid FPSO + FGA method is shown to be superior with respect to the individual evolutionary methods. The tests were made with 2, 4, 8 and 16 variables.

View PDFchevron_right
Acoustics Recognition with Expert Intelligent System
Dr. RUAA S H A L L A L ABBAS ANOOZ, Ruaa Shallal Abbas Anooz, Ahmad Abdulsadda

2020

In this article, we present a creative scheme for improving the noisy voice speech signal within a multi-channel voice improving and enhancement system. A hybrid optimization algorithm is a new approach using the mix of traditional fuzzy-PSO and hybrid fuzzy PSO (HFPSO) methodology. The F-PSO algorithm considered to have higher efficiency in optimization than regular PSO. It proposed that the F-PSO algorithm increases the variety of particles of a swarm by choosing a particular value for the specified parameters to more improve the performance of the conventional PSO. The suggested speech enhancement process called FHPSO is a hybrid strategy that combines both F-PSO and HPSO to optimize the benefits of both algorithms. The new FHPSO algorithm is shown to be very successful in obtaining global convergence for adaptive filters and resulting in a powerful funnel of noise from the input voice signal. The findings of the experimental simulation show in terms of convergence rate and SNR-amelioration the current algorithm goes beyond the conventional PSO, F-PSO, and HFPSO.

View PDFchevron_right
Adaptive Network Based Fuzzy Inference System for Speech Recognition Through Subtractive Clustering
samiya silarbi

International Journal of Artificial Intelligence & Applications, 2014

Fuzzy modeling require two main steps which are structure identification and parameter optimization, the first one determines the numbers of membership functions and fuzzy if-then rules, while the second identifies a feasible set of parameters under the given structure. However, the increase of input dimension, rule numbers will have an exponential growth and there will cause problem of “rule disaster”. In this paper, we have applied adaptive network fuzzy inference system ANFIS for phonemes recognition. The appropriate learning algorithm is performed on TIMIT speech database supervised type, a pre-processing of the acoustic signal and extracting the coefficients MFCCs parameters relevant to the recognition system. First learning of the network structure by subtractive clustering, in order to define an optimal structure and obtain small number of rules, then learning of parameters network by hybrid learning which combine the gradient decent and least square estimation LSE to find a ...

View PDFchevron_right
Voice Recognition with Neural Networks, Type2 Fuzzy Logic and Genetic Algorithms
Miguel Soto

Engineering Letters, 2006

We describe in this paper the use of neural networks, fuzzy logic and genetic algorithms for voice recognition. In particular, we consider the case of speaker recognition by analyzing the sound signals with the help of intelligent techniques, such as the neural networks and fuzzy systems. We use the neural networks for analyzing the sound signal of an unknown speaker, and after this first step, a set of type-2 fuzzy rules is used for decision making. We need to use fuzzy logic due to the uncertainty of the decision process. We also use genetic algorithms to optimize the architecture of the neural networks. We illustrate our approach with a sample of sound signals from real speakers in our institution.

View PDFchevron_right
Classification with Some Artificial Neural Network Classifiers Trained a Modified Particle Swarm Optimization
erdinç Kolay

American Journal of Intelligent Systems, 2016

In this paper, we propose a new modified particle swarm algorithm for training some neural network classifiers for the most used classification problems in literature. Researches in artificial neural network field are based on different network architectures including multilayer perceptron, single multiplicative neuron and pi-sigma neuron model. To obtain a satisfactory performance for these classifiers, one of the most important issues is network training. Evolutionary algorithms are commonly used for training neural network classifiers. Particle swarm algorithm is population based, stochastic and meta-heuristic algorithm to solve optimization problems. As all evolutionary algorithms, the particle swarm algorithm may fall into local optimum and convergence rate may incredibly decline in iterative process. To overcome these shortcomings we refer to modify the particle swarm optimization with changing position matrix for each generation at iterative process. Experimental results show...

View PDFchevron_right
Optimal Learning of Fuzzy Neural Network Using Particle Swarm Optimization Algorithm
Dong Hwa Kim

2005

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision making in complex systems. The fuzzy-neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes particle swarm optimization algorithm based optimal learning fuzzy-neural network (PSOA-FNN). The proposed learning scheme is the fuzzy-neural network structure which can handle linguistic knowledge as tuning membership function of fuzzy logic by particle swarm optimization algorithm. The learning algorithm of the PSOA-FNN is composed of two phases. The first phase is to find the initial membership functions of the fuzzy neural network model. In the second phase, particle swarm optimization algorithm is used for tuning of membership functions of the proposed model.

View PDFchevron_right
Application of a modified neural fuzzy network and an improved genetic algorithm to speech recognition
H.K. Lam

Neural Computing and Applications, 2007

This paper presents the recognition of speech commands using a modified neural fuzzy network (NFN). By introducing associative memory (the tuner NFN) into the classification process (the classifier NFN), the network parameters could be made adaptive to changing input data. Then, the search space of the classification network could be enlarged by a single network. To train the parameters of the modified NFN, an improved genetic algorithm is proposed. As an application example, the proposed speech recognition approach is implemented in an eBook experimentally to illustrate the design and its merits.

View PDFchevron_right
A HYBRID METHOD OF MODIFIED CAT SWARM OPTIMIZATION AND GRADIENT DESCENT ALGORITHM FOR TRAINING ANFIS (2013)
Maysam Orouskhani

2013

This paper introduces a novel approach for tuning the parameters of the adaptive network-based fuzzy inference system (ANFIS). In the commonly used training methods, the antecedent and consequent parameters of ANFIS are trained by gradient-based algorithms and recursive least square method, respectively. In this study, a new swarm-based meta-heuristic optimization algorithm, so-called \Cat Swarm Optimization", is used in order to train the antecedent part parameters and gradient descent algorithm is applied for training the consequent part parameters. Experimental results for prediction of MackeyÀGlass model and identi¯cation of two nonlinear dynamic systems reveal that the performance of proposed algorithm is much better and it shows quite satisfactory results.

View PDFchevron_right

References (45)

  1. Abraham, A. (2001, June). Neuro Fuzzy Systms: State-of-the-Art Modeling Techniques. In Artificial and Natural Neural Networks IWANN, 6th International Work-Conference on (Vol. 2084, pp. 269-276). Academic Press.
  2. Algabri, M., Mathkour, H., Bencherif, M. A., Alsulaiman, M., & Mekhtiche, M. A. (2017). Automatic Speaker Recognition for Mobile Forensic Applications. Hindawi Mobile Information Systems, 2017, 1-6. doi:10.1155/2017/6986391
  3. Apsingekar, V. R., & De Leon, P. L. (2009, November). Support Vector Machine Based Speaker Identification Systems Using GMM Parameters. In Signals, Systems and Computers, 2009 Conference Record of the Forty- Third Asilomar Conference on, (pp. 1766-1769). IEEE. doi:10.1109/ACSSC.2009.5470201
  4. Bojadziev, G., & Bojadziev, M. (1995). Fuzzy Sets, Fuzzy Logic, Applications, Advances in fuzzy systems applications and theory. World Scientific. doi:10.1142/2867
  5. Campbell, W. M., Campbell, J. P., Reynolds, D. A., Singer, E., & Torres-Carrasquillo, P. A. (2006). Support vector machines for speaker and language recognition. Computer Speech & Language, 20(2-3), 210-229. doi:10.1016/j.csl.2005.06.003
  6. Campbell, W. M., Sturim, D. E., & Reynolds, D. A. (2006). Support Vector Machines Using GMM Supervectors for Speaker Verification. IEEE Signal Processing Letters, 13(5), 308-311. doi:10.1109/LSP.2006.870086
  7. Chakroun, R., Zouari, L. B., Frikha, M., & Hamida, A. B. (2015, December). A hybrid system based on GMM- SVM for Speaker Identification. In Intelligent Systems DeSign and Applications(ISDA), 2015 15th International Conference on, (pp. 645-658). IEEE. doi:10.1109/ISDA.2015.7489195
  8. Chen, Y., Wang, L., Lin, H., & Li, J. (2012, October). Design of speaker recognition system based on artificial neural network. In Advanced Optical Manufacturing and Testing Technologies: Optical System Technologies for Manufacturing and Testing. Proceedings of the SPIE, 2012. AOMATT 6th International Symposium on (Vol. 8420, pp. 1-7). doi:10.1117/12.970642
  9. Cummins, F., Leonard, M., Leonardo, T., & Simko, J. (2006, June). The CHAINS corpus CHAracterizing INdividual Speakers. In Speech and Computer SPECOM, The International Conference on (pp. 431-435). Academic Press.
  10. Daqrouqa, K., & Tutunjib, T. A. (2015). Speaker identification using vowels features through a combined method of formants, wavelets, and neural network classifiers. Applied Soft Computing, 27, 231-239. doi:10.1016/j. asoc.2014.11.016
  11. Dhineshkumar, R., Ganesh, A. B., & Sasikala, S. (2016). Speaker Identification System using Gaussian Mixture Model and Support Vector Machines (GMM-SVM) under Noisy Conditions. Indian Journal of Science and Technology, 9(19), 1-6.
  12. Eberhart, R. C., & Shi, Y. (2001). Particle swarm optimization: developments, applications and resources. In Proceedings of the 2001 Congress on of IEEE international conference on, (pp. 81-86). IEEE. doi:10.1109/ CEC.2001.934374
  13. Elwakdy, A. M., Elsehely, B. E., Eltokhy, C. M., & Elhennawy, D. A. (2008, July). Speech recognition using a wavelet transform to establish fuzzy inference system through subtractive clustering and neural network (ANFIS).
  14. In ICS'08 Proceedings. the 12th WSEAS international conference on Systems (pp. 381-386). Academic Press.
  15. Fatemeh, Z., & Zahra, Z. (2018). A review of neuro-fuzzy systems based on intelligent control. Journal of Electrical and Electronic Engineering, 3(2-1), 58-61.
  16. Fazakis, N., Karlos, S., Kotsiantis, S., & Sgarbas, K. (2015). Speaker Identification Using Semi-supervised Learning. Lecture Notes in Computer Science, 9319, 389-396. doi:10.1007/978-3-319-23132-7_48 Fuzzy Logic Toolbox. (2000). Fuzzy Logic Toolbox User's Guide, Version 2. The MathWorks, Inc.
  17. Ge, Z., Iyer, A. N., Cheluvaraja, S., Sundaram, R., & Ganapathiraju, A. (2017, September). Neural Network Based Speaker Classification and Verification Systems with Enhanced Features. In Intelligent Systems Conference IntelliSys (pp. 1-6). IEEE. doi:10.1109/IntelliSys.2017.8324265
  18. Gunasekaran, M., Varatharajan, R., & Priyan, M. K. (2018). Hybrid Recommendation System for Heart Disease Diagnosis based on Multiple Kernel Learning with Adaptive Neuro-Fuzzy Inference System. An International Journal Multimedia Tools and Applications, 77(4), 4379-4399. doi:10.1007/s11042-017-5515-y He, X., & Deng, L. (2008). Discriminative Learning for Speech Recognition: Theory and practice. Morgan & Claypool.
  19. Helmi, N., & Helmi, B. H. (2008, October). Speech recognition with fuzzy neural network for discrete words. In Natural Computation 2008, Proceedings ICNC Fourth International Conference on (Vol. 7, pp. 265-269). IEEE. doi:10.1109/ICNC.2008.666
  20. Huang, X., Acero, A., Hon, H., & Reddy, R. (2001). Spoken Language Processing: A guide to Theory, Algorithm, And System Development. Prentice-Hall.
  21. Jang, J. S. R. (1993). ANFIS: Adaptive Network Based Fuzzy Inference Systems. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665-685. doi:10.1109/21.256541
  22. Jang, J. S. R., Sun, C. T., & Mizutani, E. (1997). Neuro-Fuuzy and Soft Computing: a Computational Approach to Learning and Machine Intelligence. Prentice-Hall.
  23. Kamaruddin, N., & Wahab, A. (2008, July). Speech Emotion Verification System (SEVS) based on MFCC for real time application. In Intelligent Environments, IET 4th International Conference on (pp. 1-7). IEEE.
  24. Karlos, S., Fazakis, N., Karanikola, K., Kotsiantis, S., & Sgarbas, K. (2016). Speech Recognition CombiningMFCCs and Image Features. Lecture Notes in Computer Science, 9811, 651-658. doi:10.1007/978-3-319-43958-7_79
  25. Karlos, S., Kaleris, K., Fazakis, N., Kanas, V. G., & Kotsiantis, S. (2018). Optimized Active Learning Strategy for Audiovisual Speaker Recognition. Lecture Notes in Computer Science, 11096, 281-290. doi:10.1007/978- 3-319-99579-3_30
  26. Kennedy, J., & Eberhart, R. C. (1995). Particle swarm optimization. In Neural Networks, 1995. Proceedings. IEEE International Conference on (pp. 1942-1948). IEEE. doi:10.1109/ICNN.1995.488968
  27. Kosko, B. (1991). Neural Networks and Fuzzy Systems A Dynamic Systems Approach. Prentice-Hall.
  28. Li, J., Yang, L., Qu, Y., & Sexton, G. (2018). An extended Takagi-Sugeno-Kang inference system (TSK+) with fuzzy interpolation and its rule base generation. Soft Computing, 22(10), 3155-3170. doi:10.1007/s00500- 017-2925-8
  29. Liu, Y., Qian, Y., Chen, N., Fu, T., Zhang, Y., & Yu, K. (2015). Deep feature for text-dependent speaker verification. Speech Communication, 73, 1-13. doi:10.1016/j.specom.2015.07.003
  30. Milani, A., & Santucci, V. (2009). Online PSO for Web Marketing Optimization. IEEE International Conference on e-Business Engineering, Macau, 2009, 583-587. doi:10.1109/ICEBE.2009.92
  31. Nayyar, A., Garg, S., Gupta, D., & Khanna, A. (2018). Evolutionary computation: theory and algorithms. In Advances in Swarm Intelligence for Optimizing Problems in Computer Science (pp. 1-26). Chapman and Hall/ CRC. doi:10.1201/9780429445927-1
  32. Nayyar, A., Le, D. N., & Nguyen, N. G. (Eds.). (2018). Advance in Swarm Intelligence for Optimizing Problems in Computer Science. CRC Press. doi:10.1201/9780429445927
  33. Nayyar, A., & Nguyen, N. G. (2018). Introduction to Swarm Intelligence. In Advances in Swarm Intelligence for Optimizing Problems in Computer Science (pp. 53-78). Chapman and Hall/CRC. doi:10.1201/9780429445927-3
  34. Novakovic, J. (2011). Speaker identification in smart environments with multilayer perceptron. 2011 19thTelecommunications Forum (TELFOR) Proceedings of Papers, 1418-1421.
  35. Pandey, B., Ranjan, A., Kumar, R., & Shukla, A. (2010, July). Multilingual Speaker Recognition Using ANFIS. Signal Processing Systems (ICSPS), 2010 2nd International Conference on, 3, 714-718.
  36. Priyono, A., Ridwan, M., Alias, A. J., Rahmat, R. A. O. K., Hassan, A., & Ali, M. A. M. (2005). Generation of fuzzy rules with subtractive clustering. Journal Teknologi, 43(1), 143-153. doi:10.11113/jt.v43.782
  37. Sabah, R., & Ainon, R. N. (2009, May). Isolated Digit Speech Recognition in Malay Language using Neuro- Fuzzy Approach. In Modelling & Simulation, 2009. AMS '09. Third Asia International Conference on, (pp. 336-340). IEEE.
  38. Silarbi, S., Bendahmane, A., & Benyettou, A. (2014). Adaptive Network Based Fuzzy Inference System For Speech Recognition Through Subtractive Clustering. International Journal of Artificial Intelligence & Applications, 5(6), 43-52. doi:10.5121/ijaia.2014.5604
  39. Srihari, V., Karthik, R., Anitha, R., & Suganthi, S. D. (2010, December). Speaker verification using combinational features and adaptive neuro-fuzzy inference systems. In Intelligent Interactive Technologies and Multimedia. IIMT'10 the First International Conference on (pp. 98-103). doi:10.1145/1963564.1963580
  40. Sun, C. T. (1994). Rule-Base Structure Identification in an Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Fuzzy Systems, 2(1), 64-73. doi:10.1109/91.273127
  41. Takagi, T., & Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control. Syst Man and Cybern IEEETrans SMC, 15(1), 116-132. doi:10.1109/TSMC.1985.6313399
  42. Tolba, H. (2011). A high-performance text-independent speaker identification of Arabic speakers using a CHMM- based approach. Alexandria Engineering Journal, 50(1), 43-47. doi:10.1016/j.aej.2011.01.007
  43. Wali, S. S., & Hatture, S. M. (2015). MFCC Based Text-Dependent Speaker Identification Using BPNN. International Journal of Signal Processing Systems, 3(1), 30-34.
  44. Wong, C. C., & Chen, C. C. (1999). A Hybrid Clustering and Gradient Descent Approach for Fuzzy Modeling. IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics, 29(6), 686-693. doi:10.1109/3477.809024 PMID:18252349
  45. Wu, J. D., & Tsai, Y. J. (2011). Speaker identification system using empirical mode decomposition and an artificial neural network. Expert Systems with Applications, 38(5), 6112-6117. doi:10.1016/j.eswa.2010.11.013

Related papers

Speaker Verification System Using a Hierarchical Adaptive Network-Based Fuzzy Inference Systems (HANFIS)
saeed quchani

2010

HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

View PDFchevron_right
Training ANFIS as an identifier with intelligent hybrid stable learning algorithm based on particle swarm optimization and extended Kalman filter
Ali Sedigh

Fuzzy Sets and Systems, 2009

This paper proposes a novel hybrid learning algorithm with stable learning laws for Adaptive Network-based Fuzzy Inference System (ANFIS) as a system identifier. The proposed hybrid learning algorithm is based on the particle swarm optimization (PSO) for training the antecedent part and the extended Kalman filter (EKF) for training the conclusion part. Lyapunov stability theory is used to study the stability of the proposed algorithm. Comparison results of the proposed approach, PSO algorithm for training the antecedent part and recursive least squares (RLSs) or EKF algorithm for training the conclusion part, with the other classical approaches such as, gradient descent, resilient propagation, quick propagation, Levenberg-Marquardt for training the antecedent part and RLSs algorithm for training the conclusion part are provided. Moreover, it is shown that applying PSO, a powerful optimizer, to optimally train the parameters of the membership function on the antecedent part of the fuzzy rules in ANFIS system is a stable approach which results in an identifier with the best trained model. Stability constraints are obtained and different simulation results are given to validate the results. Also, the stability of Levenberg-Marquardt algorithms for ANFIS training is analyzed.

View PDFchevron_right
Voice Recognition with Neural Networks, Fuzzy Logic and Genetic Algorithms
Oscar Castillo

Hybrid Intelligent Systems for Pattern Recognition Using Soft Computing, 2005

We describe in this paper the use of neural networks, fuzzy logic and genetic algorithms for voice recognition. In particular, we consider the case of speaker recognition by analyzing the sound signals with the help of intelligent techniques, such as the neural networks and fuzzy systems. We use the neural networks for analyzing the sound signal of an unknown speaker, and after this first step, a set of type-2 fuzzy rules is used for decision making. We need to use fuzzy logic due to the uncertainty of the decision process. We also use genetic algorithms to optimize the architecture of the neural networks. We illustrate our approach with a sample of sound signals from real speakers in our institution.

View PDFchevron_right
PHONETIC CLASSIFICATION BY ADAPTIVE NETWORK BASED FUZZY INFERENCE SYSTEM AND SUBTRACTIVE CLUSTERING
Computer Science & Information Technology (CS & IT) Computer Science Conference Proceedings (CSCP)

This paper presents the application of Adaptive Network Based Fuzzy Inference System ANFIS on speech recognition. The primary tasks of fuzzy modeling are structure identification and parameter optimization, the former determines the numbers of membership functions and fuzzy if-then rules while the latter identifies a feasible set of parameters under the given structure. However, the increase of input dimension, rule numbers will have an exponential growth and there will cause problem of “rule disaster”. Thus, determination of an appropriate structure becomes an important issue where subtractive clustering is applied to define an optimal initial structure and obtain small number of rules. The appropriate learning algorithm is performed on TIMIT speech database supervised type, a pre-processing of the acoustic signal and extracting the coefficients MFCCs parameters relevant to the recognition system. Finally, hybrid learning combines the gradient decent and least square estimation LSE of parameters network. The results obtained show the effectiveness of the method in terms of recognition rate and number of fuzzy rules generated.

View PDFchevron_right
Feature Reduction Method for Speaker Identification Systems Using Particle Swarm Optimization
khaled daqrouq

International Journal of Engineering and Technology, 2017

Feature selection (FS) is a process in which the most informative and descriptive characteristics of a signal that will lead to better classification are chosen. The process is utilized in many areas, such as machine learning, pattern recognition and signal processing. FS reduces the dimensionality of a signal and preserves the most informative features for further processing. A speech signal can consist of thousands of features. Feature extraction methods such as Average Framing Linear Prediction Coding (AFLPC) using wavelet transform reduce the number of features from thousands to hundreds. However, the vector of features involves some redundancy. In addition, some features are similar and do not give discrimination to classes. Taking such features into consideration in the classification process will not help to identify certain classes; conversely, they will only serve to confuse the classifier and inhibit identification of accurate classes. This paper proposes an FS method that uses evolution optimization techniques to select the most informative features that maximize the classification rates of Bayesian classifiers. The classification rate is also maximized by modeling the features with the proper number of Gaussian distributions. The results of comparative analysis conducted show that the selection based individual speaker model gives the best classification rate performance. Keyword-Feature Selection, Speaker Identification, Bayes Theorem. I. INTRODUCTION Research on automatic speech recognition (ASR) has actively been conductedover the past four decades[1]. ASR is a tool with many potential applications such as automation of operator-assisted services and speech to text systems for hearing-impaired individuals [2]. In speaker recognition systems, the speech signal is represented by several features, which play a major part in system design. Karhunen-Loeve transform (KLT) based features [3], Mel Frequency Cepstral Coefficient (MFCC) [4], Linear Predictive Cepstral Coefficient (LPCC) [5], and wavelet transform-based features [6]-[8] are examples of signal speech features. Various approaches have been proposed to reduce the number of features required for speech recognition. Paliwal[9] reduced the dimensionality of feature vectors in speech recognition systems and tested the technique on four methods. In [10], the Laplacian Eigenmaps Latent Variable Model (LEVLM) used fewer MFCC vectors without affecting the recognition rate, and it exhibited better performance than Principal Component Analysis (PCA). Feature frame selection based on phonetic information has also been investigated to increase classification rate; however, the exact phonemes cannot be easily extracted [11]. Joint factor analysis (JFA) [12]-[14]is commonly used to enhance the performance of text independent speaker verification systems by modeling speaker and session variability. This work has been extended to ivector, which outperforms JFA in terms of complexity and model size [15]. The classification rate increaseswith the number of feature frames available for training and testing [16]. However, the performance does not continue to improve if more features are added and redundancies exist in the features; consequently, some features can be ignored with no effect on recognition performance [17]. Researchers have also focused on selecting valuable features in speech recognition systems. For example, Euclidean distance measure has been used to determine frame rate [18], anentropy-based approach has been utilized in speech signal in-frame selection [19], andmaximum likelihood-based feature selection has also been investigated [20]. The previous methods select valuable features in speech signals, but they tend to ignore the redundancy of features in feature frames. Further, reports indicate that maximizing feature information does not lead to a better classification rate [21], [22]. Features should contain minimum redundancy within the selected

View PDFchevron_right

Related topics

  • Cognitive Science
  • Computer Science
  • Artificial Intelligence
  • adaptive neuro fuzzy inference s...
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved