本文已被：浏览 1185次 下载 3252次
Received:September 25, 2020 Revised:October 21, 2020
Received:September 25, 2020 Revised:October 21, 2020
中文摘要: 针对传统声纹识别方法实现过程复杂、识别率低等问题, 提出了一种基于ResNet-LSTM的声纹识别方法. 首先采用ResNet残差网络提取声纹的空间特征, 其次采用LSTM长短期记忆循环神经网络提取声纹的时序特征, 通过ResNet与LSTM结合的特征提取方法获得了同时包含空间特征与时序特征的深度声纹特征. 实验结果表明, 采用ResNet-LSTM网络的声纹识别方法的等错误率降低至1.196%, 较基线方法d-vector以及VGGNet分别降低了3.68%与1.95%, 识别准确率达到了98.8%.
中文关键词: 声纹识别 ResNet-LSTM 空间特征 时序特征
Abstract:Aiming at the complex process and low recognition rate of traditional methods, this study proposes a voiceprint recognition method based on ResNet-LSTM. In this method, ResNet and LSTM are respectively used to extract the spatial and temporal features of voiceprints. Thus, the deep voiceprint features including both spatial and temporal features are obtained. The experimental results show that the equal error rate of the proposed method is 1.196%, which is 3.68% and 1.95% lower than that of the baseline methods d-vector and VGGNet, respectively, and the recognition accuracy reaches 98.8%.
文章编号： 中图分类号： 文献标志码：
基金项目:国家自然科学基金(61973180)
引用文本：
刘勇,梁宏涛,刘国柱,胡强.基于ResNet-LSTM的声纹识别方法.计算机系统应用,2021,30(6):215-219
LIU Yong,LIANG Hong-Tao,LIU Guo-Zhu,HU Qiang.Voiceprint Recognition Method Based on ResNet-LSTM.COMPUTER SYSTEMS APPLICATIONS,2021,30(6):215-219
刘勇,梁宏涛,刘国柱,胡强.基于ResNet-LSTM的声纹识别方法.计算机系统应用,2021,30(6):215-219
LIU Yong,LIANG Hong-Tao,LIU Guo-Zhu,HU Qiang.Voiceprint Recognition Method Based on ResNet-LSTM.COMPUTER SYSTEMS APPLICATIONS,2021,30(6):215-219
