Sinaptik Etkinlik Fonksiyon Tabanlı Sızdıran Entegre ve Ateşleme Nöron Modelini Kullanarak İnsan Ses Sinyallerinde Cinsiyet Tespiti

Günümüzdeki teknolojik gelişmeler, insanların bir ses sinyalinden konuşmacının cinsiyetini belirlemesi mümkün kılmıştır. Frekans türleri, spektral ve entropi gibi sayısal nitelikli veriler ses sinyallerinin akustik bilgilerini oluşturmaktadır. Son zamanlarda, yüksek başarı oranlarına sahip yapay zekâ tabanlı öğrenme modelleri çeşitli alanlarda ilgi görmeye başladı. Ses sinyalleri üzerinde derin öğrenme modelleri ile ilgili birçok çalışma bulunmaktadır. Bu çalışmada, derin öğrenme modellerinden esinlenerek tasarlanmış ve farklı bir mimari yapısı olan ani sivri uçlu sinir ağları kullanılmıştır. Çalışmada kullanılan veri kümesi, insan konuşmalarını ve seslerini içeren akustik bilgiye dayalı parametrelerden oluşmaktadır. Belirlenen veri seti kullanılarak ani sivri uçlu sinir ağı modeli eğitilmiş ve cinsiyet tespitinin gerçekleştirilmesi sağlanmıştır. Önermiş olduğumuz bu çalışmada sonuç olarak, sınıflandırma sürecinde %98,84 genel doğruluk başarısı elde edilmiştir. Bu çalışmada gerçekleştirilen deneysel analizler ile ani sivri uçlu sinir ağı modelinin başarılı bir şekilde çalıştırıldığı, yüksek başarımlar elde edildiği gözlemlenmiştir.

Gender Determination in Human Voice Signals using Synaptic Efficacy Function-based Leaky Integrate and Fire Neuron Model

Today's technological advances have made it possible for people to determine the gender of the speaker from an audio signal. Numerical data such as frequency types, spectral and entropy constitute acoustic information of audio signals. Recently, artificial intelligence-based learning models with high success rates have started to attract attention in various fields. There are many studies on deep learning models on audio signals. In this study, spiked neural networks with a different architectural structure, inspired by deep learning models, were used. The dataset used in the study consists of parameters based on acoustic information including human speech and voices. By using the determined data set, the spiked neural network model was trained and gender determination was achieved. As a result, 98.84% overall accuracy success was achieved in the classification process in this proposed study. With the experimental analyzes carried out in this study, it was observed that the spiked neural network model was successfully run and high performances were obtained.

___

  • [1] C. Pernet and P. Belin, "The Role of Pitch and Timbre in Voice Gender Categorization", Frontiers in Psychology, vol. 3, 2012. Doi: 10.3389/fpsyg.2012.00023.
  • [2] V. Cartei and D. Reby, "Effect of Formant Frequency Spacing on Perceived Gender in Pre-Pubertal Children's Voices", PLoS ONE, vol. 8, no. 12, p. e81022, 2013. Doi: 10.1371/journal.pone.0081022.
  • [3] M. Poon and M. Ng, "The role of fundamental frequency and formants in voice gender identification", Speech, Language and Hearing, vol. 18, no. 3, pp. 161-165, 2014. Doi: 10.1179/2050572814y.0000000058.
  • [4] V. Skuk, L. Dammann and S. Schweinberger, "Role of timbre and fundamental frequency in voice gender adaptation", The Journal of the Acoustical Society of America, vol. 138, no. 2, pp. 1180-1193, 2015. Doi: 10.1121/1.4927696.
  • [5] R. Alkhawaldeh, "DGR: Gender Recognition of Human Speech Using One-Dimensional Conventional Neural Network", Scientific Programming, vol. 2019, pp. 1-12, 2019. Doi: 10.1155/2019/7213717.
  • [6] M. Buyukyilmaz and A. Cibikdiken, "Voice Gender Recognition Using Deep Learning", Proceedings of 2016 International Conference on Modeling, Simulation and Optimization Technologies and Applications (MSOTA2016), 2016. Doi: 10.2991/msota-16.2016.90.
  • [7] E. Salomons and P. Havinga, "A Survey on the Feasibility of Sound Classification on Wireless Sensor Nodes", Sensors, vol. 15, no. 4, pp. 7462-7498, 2015. Doi: 10.3390/s150407462.
  • [8] G. Archana and M. Malleswari, "Gender identification and performance analysis of speech signals", 2015 Global Conference on Communication Technologies (GCCT), 2015. Doi: 10.1109/gcct.2015.7342709.
  • [9] S. İleri, a. Karabina and E. KILIÇ, "Konuşmacı Cinsiyetinin Tespitinde Değişik Normalizasyon Tekniklerinin Kıyaslanması", Mehmet Akif Ersoy Üniversitesi Uygulamalı Bilimler Dergisi, vol. 2, no. 2, pp. 1-12, 2018. Doi: 10.31200/makuubd.410625.
  • [10] D. Doukhan, J. Carrive, F. Vallet, A. Larcher and S. Meignier, "An Open-Source Speaker Gender Detection Framework for Monitoring Gender Equality", 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018. Doi: 10.1109/icassp.2018.8461471.
  • [11] P. Wang and J. Hu, "A hybrid model for EEG-based gender recognition", Cognitive Neurodynamics, vol. 13, no. 6, pp. 541-554, 2019. Doi: 10.1007/s11571-019-09543-y.
  • [12] M. Pfeiffer and T. Pfeil, "Deep Learning With Spiking Neurons: Opportunities and Challenges", Frontiers in Neuroscience, vol. 12, 2018. Doi: 10.3389/fnins.2018.00774.
  • [13] J. Lobo, J. Del Ser, A. Bifet and N. Kasabov, "Spiking Neural Networks and online learning: An overview and perspectives", Neural Networks, vol. 121, pp. 88-100, 2020. Doi: 10.1016/j.neunet.2019.09.004.
  • [14] K. Becker, "Gender Recognition by Voice", Kaggle.com, 2022. [Online]. Doi: https://www.kaggle.com/primaryobjects/voicegender. [Accessed: 01- Apr- 2022].
  • [15] M. Toğaçar, B. Ergen and Z. Cömert, "Detection of weather images by using spiking neural networks of deep learning models", Neural Computing and Applications, vol. 33, no. 11, pp. 6147-6159, 2020. Doi: 10.1007/s00521-020-05388-3.
  • [16] A. Sboev, A. Serenko, R. Rybka and D. Vlasov, "Solving a classification task by spiking neural network with STDP based on rate and temporal input encoding", Mathematical Methods in the Applied Sciences, vol. 43, no. 13, pp. 7802-7814, 2020. Doi: 10.1002/mma.6241.
  • [17] A. Tavanaei, M. Ghodrati, S. Kheradpisheh, T. Masquelier and A. Maida, "Deep learning in spiking neural networks", Neural Networks, vol. 111, pp. 47-63, 2019. Doi: 10.1016/j.neunet.2018.12.002.
  • [18] M. Stimberg, R. Brette and D. Goodman, "Brian 2, an intuitive and efficient neural simulator", eLife, vol. 8, 2019. Doi: 10.7554/elife.47314.
  • [19] A. Jeyasothy, S. Sundaram and N. Sundararajan, "SEFRON: A New Spiking Neuron Model With Time- Varying Synaptic Efficacy Function for Pattern Classification", IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 4, pp. 1231-1240, 2019. Doi: 10.1109/tnnls.2018.2868874.
  • [20] X. Wang, X. Lin and X. Dang, "A Delay Learning Algorithm Based on Spike Train Kernels for Spiking Neurons", Frontiers in Neuroscience, vol. 13, 2019. Doi: 10.3389/fnins.2019.00252.
  • [21] S. Sayyad, M. Shaikh, A. Pandit, D. Sonawane and S. Anpat, "Confusion Matrix-Based Supervised Classification Using Microwave SIR-C SAR Satellite Dataset", Communications in Computer and Information Science, pp. 176-187, 2021. Doi: 10.1007/978-981-16-0493-5_16.
  • [22] M. Toğaçar, Ergen B. Biyomedikal Görüntülerde Derin Öğrenme ile Mevcut Yöntemlerin Kıyaslanması. Fırat Üniversitesi Mühendislik Bilim Derg 2019;31:109–21.
  • [23] E. Basaran, Z. Comert, A. Sengur, U. Budak, Y. Celik and M. Togacar, "Chronic Tympanic Membrane Diagnosis based on Deep Convolutional Neural Network", 2019 4th International Conference on Computer Science and Engineering (UBMK), 2019. Doi: 10.1109/ubmk.2019.8907070.
  • [24] W. Alsaggaf, Z. Cömert, M. Nour, K. Polat, H. Brdesee and M. Toğaçar, "Predicting fetal hypoxia using common spatial pattern and machine learning from cardiotocography signals", Applied Acoustics, vol. 167, p. 107429, 2020. Doi: 10.1016/j.apacoust.2020.107429.
  • [25] I. Livieris, E. Pintelas and P. Pintelas, "Gender Recognition by Voice using an Improved Self-Labeled Algorithm", Machine Learning and Knowledge Extraction, vol. 1, no. 1, pp. 492-503, 2019. Doi: 10.3390/make1010030.
  • [26] M. Kacamarga, T. Cenggoro, A. Budiarto, R. Rahutomo and B. Pardamean, "Analysis of Acoustic Features in Gender Identification Model for English and Bahasa Indonesia Telephone Speeches", Procedia Computer Science, vol. 157, pp. 199-204, 2019. Doi: 10.1016/j.procs.2019.08.158.
Bitlis Eren Üniversitesi Fen Bilimleri Dergisi-Cover
  • Yayın Aralığı: Yılda 4 Sayı
  • Başlangıç: 2012
  • Yayıncı: Bitlis Eren Üniversitesi Rektörlüğü