Araştırma Makalesi
BibTex RIS Kaynak Göster

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

Yıl 2022, Cilt: 11 Sayı: 2, 469 - 477, 30.06.2022
https://doi.org/10.17798/bitlisfen.1024236

Öz

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.

Kaynakça

  • [1]Pernet CR, Belin P. The role of pitch and timbre in voice gender categorization. Front Psychol 2012;3:23. doi:10.3389/fpsyg.2012.00023.
  • [2]Cartei V, Reby D. Effect of Formant Frequency Spacing on Perceived Gender in Pre-Pubertal Children’s Voices. PLoS One 2013;8:e81022.
  • [3]Poon MSF, Ng ML. The role of fundamental frequency and formants in voice gender identification. Speech, Lang Hear 2015;18:161–5. doi:10.1179/2050572814Y.0000000058.
  • [4]Skuk VG, Dammann LM, Schweinberger SR. Role of timbre and fundamental frequency in voice gender adaptation. J Acoust Soc Am 2015;138:1180–93. doi:10.1121/1.4927696.
  • [5]Alkhawaldeh RS. DGR: Gender Recognition of Human Speech Using One-Dimensional Conventional Neural Network. Sci Program 2019;2019:7213717. doi:10.1155/2019/7213717.
  • [6]Buyukyilmaz M, Cibikdiken AO. Voice Gender Recognition Using Deep Learning 2016;58:409–11. doi:10.2991/msota-16.2016.90.
  • [7]Salomons EL, Havinga PJM. A survey on the feasibility of sound classification on wireless sensor nodes. Sensors (Basel) 2015;15:7462–98. doi:10.3390/s150407462.
  • [8]Archana GS, Malleswari M. Gender identification and performance analysis of speech signals. 2015 Glob. Conf. Commun. Technol., 2015, p. 483–9. doi:10.1109/GCCT.2015.7342709.
  • [9]İleri SC, Karabina A, Kiliç E. Comparison of Different Normalization Techniques on Speakers ’ Gender Detection Konuşmacı Cinsiyetinin Tespitinde Değişik Normalizasyon Tekniklerinin Kıyaslanması 2018;2:1–12.
  • [10]Doukhan D, Carrive J, Vallet F, Larcher A, Meignier S. An Open-Source Speaker Gender Detection Framework for Monitoring Gender Equality. ICASSP, IEEE Int Conf Acoust Speech Signal Process - Proc 2018;2018-April:5214–8. doi:10.1109/ICASSP.2018.8461471.
  • [11]Wang P, Hu J. A hybrid model for EEG-based gender recognition. Cogn Neurodyn 2019;13:541–54. doi:10.1007/s11571-019-09543-y.
  • [12]Becker K. Gender Recognition by Voice / Identify a voice as male or female. Kaggle 2016. https://www.kaggle.com/primaryobjects/voicegender (Erişim Tarihi: October 17, 2021).
  • [13]Toğaçar M, Ergen B, Cömert Z. Detection of weather images by using spiking neural networks of deep learning models. Neural Comput Appl 2021. doi:10.1007/s00521-020-05388-3.
  • [14]Sboev A, Serenko A, Rybka R, Vlasov D. Solving a classification task by spiking neural network with STDP based on rate and temporal input encoding. Math Methods Appl Sci 2020;43:7802–14. doi:10.1002/mma.6241.
  • [15]Tavanaei A, Ghodrati M, Kheradpisheh SR, Masquelier T, Maida A. Deep learning in spiking neural networks. Neural Networks 2019;111:47–63. doi:https://doi.org/10.1016/j.neunet.2018.12.002.
  • [16]Stimberg M, Brette R, Goodman DF. Brian 2, an intuitive and efficient neural simulator. Elife 2019;8:e47314. doi:10.7554/elife.47314.
  • [17]Jeyasothy A, Sundaram S, Sundararajan N. SEFRON: A New Spiking Neuron Model With Time-Varying Synaptic Efficacy Function for Pattern Classification. IEEE Trans Neural Networks Learn Syst 2019;30:1231–40. doi:10.1109/tnnls.2018.2868874.
  • [18]Wang X, Lin X, Dang X. A Delay Learning Algorithm Based on Spike Train Kernels for Spiking Neurons. Front Neurosci 2019;13:252. doi:10.3389/fnins.2019.00252.
  • [19]Sayyad S, Shaikh M, Pandit A, Sonawane D, Anpat S. Confusion Matrix-Based Supervised Classification Using Microwave SIR-C SAR Satellite Dataset BT - Recent Trends in Image Processing and Pattern Recognition. In: Santosh KC, Gawali B, editors., Singapore: Springer Singapore; 2021, p. 176–87.
  • [20]Toğaçar M, Ergen B. Biyomedikal Görüntülerde Derin Öğrenme ile Mevcut Yöntemlerin Kıyaslanması. Fırat Üniversitesi Mühendislik Bilim Derg 2019;31:109–21.
  • [21]Başaran E, Cömert Z, Şengür A, Budak Ü, Çelik Y, Toğaçar M. Chronic Tympanic Membrane Diagnosis based on Deep Convolutional Neural Network. 2019 4th Int. Conf. Comput. Sci. Eng., 2019, p. 1–4. doi:10.1109/ubmk.2019.8907070.
  • [22] Livieris I, Pintelas E, Pintelas P. Gender Recognition by Voice using an Improved Self-Labeled Algorithm. Mach Learn Knowl Extr 2019;1:492–503. doi:10.3390/make1010030.
  • [23]Kacamarga MF, Cenggoro TW, Budiarto A, Rahutomo R, Pardamean B. Analysis of Acoustic Features in Gender Identification Model for English and Bahasa Indonesia Telephone Speeches. Procedia Comput Sci 2019;157:199–204. doi:https://doi.org/10.1016/j.procs.2019.08.158.

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

Yıl 2022, Cilt: 11 Sayı: 2, 469 - 477, 30.06.2022
https://doi.org/10.17798/bitlisfen.1024236

Öz

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.

Kaynakça

  • [1]Pernet CR, Belin P. The role of pitch and timbre in voice gender categorization. Front Psychol 2012;3:23. doi:10.3389/fpsyg.2012.00023.
  • [2]Cartei V, Reby D. Effect of Formant Frequency Spacing on Perceived Gender in Pre-Pubertal Children’s Voices. PLoS One 2013;8:e81022.
  • [3]Poon MSF, Ng ML. The role of fundamental frequency and formants in voice gender identification. Speech, Lang Hear 2015;18:161–5. doi:10.1179/2050572814Y.0000000058.
  • [4]Skuk VG, Dammann LM, Schweinberger SR. Role of timbre and fundamental frequency in voice gender adaptation. J Acoust Soc Am 2015;138:1180–93. doi:10.1121/1.4927696.
  • [5]Alkhawaldeh RS. DGR: Gender Recognition of Human Speech Using One-Dimensional Conventional Neural Network. Sci Program 2019;2019:7213717. doi:10.1155/2019/7213717.
  • [6]Buyukyilmaz M, Cibikdiken AO. Voice Gender Recognition Using Deep Learning 2016;58:409–11. doi:10.2991/msota-16.2016.90.
  • [7]Salomons EL, Havinga PJM. A survey on the feasibility of sound classification on wireless sensor nodes. Sensors (Basel) 2015;15:7462–98. doi:10.3390/s150407462.
  • [8]Archana GS, Malleswari M. Gender identification and performance analysis of speech signals. 2015 Glob. Conf. Commun. Technol., 2015, p. 483–9. doi:10.1109/GCCT.2015.7342709.
  • [9]İleri SC, Karabina A, Kiliç E. Comparison of Different Normalization Techniques on Speakers ’ Gender Detection Konuşmacı Cinsiyetinin Tespitinde Değişik Normalizasyon Tekniklerinin Kıyaslanması 2018;2:1–12.
  • [10]Doukhan D, Carrive J, Vallet F, Larcher A, Meignier S. An Open-Source Speaker Gender Detection Framework for Monitoring Gender Equality. ICASSP, IEEE Int Conf Acoust Speech Signal Process - Proc 2018;2018-April:5214–8. doi:10.1109/ICASSP.2018.8461471.
  • [11]Wang P, Hu J. A hybrid model for EEG-based gender recognition. Cogn Neurodyn 2019;13:541–54. doi:10.1007/s11571-019-09543-y.
  • [12]Becker K. Gender Recognition by Voice / Identify a voice as male or female. Kaggle 2016. https://www.kaggle.com/primaryobjects/voicegender (Erişim Tarihi: October 17, 2021).
  • [13]Toğaçar M, Ergen B, Cömert Z. Detection of weather images by using spiking neural networks of deep learning models. Neural Comput Appl 2021. doi:10.1007/s00521-020-05388-3.
  • [14]Sboev A, Serenko A, Rybka R, Vlasov D. Solving a classification task by spiking neural network with STDP based on rate and temporal input encoding. Math Methods Appl Sci 2020;43:7802–14. doi:10.1002/mma.6241.
  • [15]Tavanaei A, Ghodrati M, Kheradpisheh SR, Masquelier T, Maida A. Deep learning in spiking neural networks. Neural Networks 2019;111:47–63. doi:https://doi.org/10.1016/j.neunet.2018.12.002.
  • [16]Stimberg M, Brette R, Goodman DF. Brian 2, an intuitive and efficient neural simulator. Elife 2019;8:e47314. doi:10.7554/elife.47314.
  • [17]Jeyasothy A, Sundaram S, Sundararajan N. SEFRON: A New Spiking Neuron Model With Time-Varying Synaptic Efficacy Function for Pattern Classification. IEEE Trans Neural Networks Learn Syst 2019;30:1231–40. doi:10.1109/tnnls.2018.2868874.
  • [18]Wang X, Lin X, Dang X. A Delay Learning Algorithm Based on Spike Train Kernels for Spiking Neurons. Front Neurosci 2019;13:252. doi:10.3389/fnins.2019.00252.
  • [19]Sayyad S, Shaikh M, Pandit A, Sonawane D, Anpat S. Confusion Matrix-Based Supervised Classification Using Microwave SIR-C SAR Satellite Dataset BT - Recent Trends in Image Processing and Pattern Recognition. In: Santosh KC, Gawali B, editors., Singapore: Springer Singapore; 2021, p. 176–87.
  • [20]Toğaçar M, Ergen B. Biyomedikal Görüntülerde Derin Öğrenme ile Mevcut Yöntemlerin Kıyaslanması. Fırat Üniversitesi Mühendislik Bilim Derg 2019;31:109–21.
  • [21]Başaran E, Cömert Z, Şengür A, Budak Ü, Çelik Y, Toğaçar M. Chronic Tympanic Membrane Diagnosis based on Deep Convolutional Neural Network. 2019 4th Int. Conf. Comput. Sci. Eng., 2019, p. 1–4. doi:10.1109/ubmk.2019.8907070.
  • [22] Livieris I, Pintelas E, Pintelas P. Gender Recognition by Voice using an Improved Self-Labeled Algorithm. Mach Learn Knowl Extr 2019;1:492–503. doi:10.3390/make1010030.
  • [23]Kacamarga MF, Cenggoro TW, Budiarto A, Rahutomo R, Pardamean B. Analysis of Acoustic Features in Gender Identification Model for English and Bahasa Indonesia Telephone Speeches. Procedia Comput Sci 2019;157:199–204. doi:https://doi.org/10.1016/j.procs.2019.08.158.
Toplam 23 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Mühendislik
Bölüm Araştırma Makalesi
Yazarlar

Vedat Tümen 0000-0003-0271-216X

Yayımlanma Tarihi 30 Haziran 2022
Gönderilme Tarihi 1 Aralık 2021
Kabul Tarihi 5 Nisan 2022
Yayımlandığı Sayı Yıl 2022 Cilt: 11 Sayı: 2

Kaynak Göster

IEEE V. Tümen, “Sinaptik Etkinlik Fonksiyon Tabanlı Sızdıran Entegre ve Ateşleme Nöron Modelini Kullanarak İnsan Ses Sinyallerinde Cinsiyet Tespiti”, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, c. 11, sy. 2, ss. 469–477, 2022, doi: 10.17798/bitlisfen.1024236.



Bitlis Eren Üniversitesi
Fen Bilimleri Dergisi Editörlüğü

Bitlis Eren Üniversitesi Lisansüstü Eğitim Enstitüsü        
Beş Minare Mah. Ahmet Eren Bulvarı, Merkez Kampüs, 13000 BİTLİS        
E-posta: fbe@beu.edu.tr