Gender Recognition Using Deep Neural Networks

سال انتشار: 1401
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 318

فایل این مقاله در 12 صفحه با فرمت PDF و WORD قابل دریافت می باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

SETT05_008

تاریخ نمایه سازی: 27 اسفند 1401

چکیده مقاله:

Voice gender recognition plays an important role in speech-processing systems and voice-based identity recognition systems. Due to the tremendous growth of artificial intelligence technologies and computer systems, voice data can be classified using deep neural networks to recognize the gender of the speaker. The voice gender recognition system with accent and English language has been investigated and implemented before, but despite the huge difference between the language, dialect, and accent of English and Persian, this work was done on the Persian dataset for the first time. In this research, deep neural networks ۱D-CNN, ۲D-CNN, LSTM, GRU, and SimpleRNN were used to classify the voice data set for the purpose of recognition and recognition, Finally, a ۲D-CNN neural network with ۹۹% accuracy is known as the best neural network for voice gender detection

نویسندگان

Seyed Amirreza Kabodian

Department of Computer Engineering, Khorasgan Branch, Islamic Azad University, Esfahan, Iran

Nima Rajaeian

Digital Processing and Machine Vision Research Center, Najafabad Branch, Islamic Azad University, Najafabad, Iran