深度学习在声纹识别领域的应用研究  

Research on the Application of Deep Learning in Voiceprint Recognition

作　　者：罗娅娅 李智 刘苛 雷智美 LUO Yaya;LI Zhi;LIU Ke;LEI Zhimei(Department of Information Engineering,Guizhou Mechanical and Electrical Vocational and Technical College,Duyun,China,558000)

机构地区：[1]贵州机电职业技术学院信息工程系,贵州都匀558000

出　　处：《福建电脑》2024年第8期27-29,共3页Journal of Fujian Computer

摘　　要：声纹识别是一种生物特征识别技术。为提高声纹识别在噪声复杂环境下的准确程度和识别率,本文提出了一个在噪声复杂环境下的声纹识别深度学习的改进模型。实验的结果表明,在噪声复杂环境下,该模型显著提升了声纹识别的准确程度和识别率。Voiceprint recognition is a biometric recognition technology.To improve the accuracy and recognition rate of voiceprint recognition in noisy and complex environments,this paper proposes an improved deep learning model for voiceprint recognition in noisy and complex environments.The experimental results show that in a noisy and complex environment,the model significantly improves the accuracy and recognition rate of voiceprint recognition.

关 键 词：声纹识别 深度学习 时延神经网络 特征提取 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]