WAVELETS FOR SPEAKER RECOGNITION USING GMM CLASSIFIER
Speaker recognition plays an important role in a biometric based identification of the person using the information available in their speech signals. In any speaker recognition system, feature extraction using signal processing approaches is an important stage. In this paper, an efficient speaker recognition system is presented by extracting the energy features of the speech signals using Discrete Wavelet Transform (DWT). Then, the extracted DWT energy features are modeled using Gaussian mixture model (GMM) classifier for the recognition of the speaker. Results prove the efficiency of the speaker recognition system with an accuracy of 96.31% at 4th level DWT features with 16 Gaussian densities.
 Z. Senturk and O. Salor, â€œEffect of plosives on isolated speaker recognition system performanceâ€, IEEE 9th International Conference on Electrical and Electronics Engineering, 2015, pp. 1263-1265.
 D. Snyder, D. Garcia-Romero, and D. Povey, â€œTime delay deep neural network-based universal background models for speaker recognitionâ€, IEEE Workshop on Automatic Speech Recognition and Understanding, 2015 pp. 92-97.
 L. Li, Y. Lin, Z. Zhang, and D. Wang, â€œImproved deep speaker feature learning for text-dependent speaker recognitionâ€, IEEE Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2015, pp. 426-429.
 M. Jamali, V. Ghafarinia, and M. A. Montazeri, â€œRecognition of speaker-independent isolated Persian digits using an enhanced vector quantization algorithmâ€, IEEE Signal Processing and Intelligent Systems Conference, 2015, pp. 164-168.
 A. Poddar, M. Sahidullah, and G. Saha, â€œPerformance comparison of speaker recognition systems in presence of duration variabilityâ€, IEEE Annual India Conference, 2015, pp. 1-6.
 M. Y. A. Khan, S. M. Hossain, and M. M. Hoque, â€œIsolated Bangla word recognition and speaker detection by semantic modular time delay neural network (MTDNN)â€, IEEE 18th International Conference on Computer and Information Technology, 2015, pp. 560-565.
 P. Bansal, S. A. Imam, and R. Bharti, â€œSpeaker recognition using MFCC, shifted MFCC with vector quantization and fuzzyâ€, IEEE International Conference on Soft Computing Techniques and Implementations, 2015, pp. 41-44.
 G. Liu, and J. H. Hansen, â€œAn investigation into back-end advancements for speaker recognition in multi-session and noisy enrollment scenariosâ€, IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 22, No. 12, 2014, 1978-1992.
 D. An, M. Shao, Z. Yuan, H. Shi, and Q. Pan, â€œSpeaker Recognition Method Based on CPSO Clustering and KMP Algorithmâ€, IEEE 7th International Symposium on Computational Intelligence and Design, Vol. 1, 2014, pp. 556-559.
 M. Alsulaiman, â€œEffect of Spoken Text on Text-Independent Speaker Recognitionâ€, IEEE 5th International Conference on Intelligent Systems, Modelling and Simulation, 2014, pp. 279-284.
 M. Zamalloa, L.J RodrÃguez-Fuentes, M. Penagarikano, G. Bordel, and J. P. Uribe, â€œFeature dimensionality reduction through genetic algorithms for faster speaker recognitionâ€, IEEE 16th European Signal Processing Conference, 2008, pp. 1-5.
 C.M Bishop), â€œPattern recognition and machine learningâ€, Springer, Chapter 9, Vol. 1, 2006, pp.435.
 F. Cummins, M. Grimaldi, T. Leonard, and J. Simko, The CHAINS corpus: CHAracterizing INdividual Speakers. In Proc of SPECOM & rquo; 2006, pp. 431-435
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).