首页|基于ASP-SERes2Net的说话人识别算法

基于ASP-SERes2Net的说话人识别算法

扫码查看
原文链接
  • 万方数据
  • 维普
为提升说话人识别的特征提取能力,解决在噪声环境下识别率低的问题,提出一种基于残差网络的说话人识别算法—ASP-SERes2Net.首先,采用梅尔语谱图作为神经网络的输入;其次,改进Res2Net网络的残差块,并且在每个残差块后引入压缩激活(squeeze-and-excitation,SE)注意力模块;然后,用注意力统计池化(attention statistics pooling,ASP)代替原来的平均池化;最后,采用附加角裕度的 Softmax(additive angular margin Softmax,AAM-Softmax)对说话人身份进行分类.通过实验,将ASP-SERes2Net算法与时延神经网络(time delay neural network,TDNN)、ResNet34 和 Res2Net 进行对比,ASP-SERes2Net 算法的最小检测代价函数(minimum detection cost function,MinDCF)值为0.040 1,等误率(equal error rate,EER)为0.52％,明显优于其他3个模型.结果表明,ASP-SERes2Net算法性能更优,适合应用于噪声环境下的说话人识别.
Speaker Recognition Algorithm Based on ASP-SERes2Net
To improve the feature extraction ability of speaker recognition and enhance the low recognition rate in noise environment,a speaker recognition algorithm—ASP-SERes2Net is proposed based on residual network.First,the Mel spectrum was used as the input of the neural network.Second,the residual block of the Res2Net was improved and squeeze-and-excitation(SE)attention module was introduced.Then,the average pooling was replaced by the attention statistics pooling(ASP).Finally,the additive angular margin Softmax(AAM-Softmax)function was used to classify the identity of the speaker.Through experiments,the performance of the ASP-SERes2Net algorithm was compared with that of time delay neural network(TDNN),ResNet34 and Res2Net.The minimum detection cost function(MinDCF)value of the ASP-SERes2Net algorithm was 0.040 1 and equal error rate(EER)was 0.52％,which were significantly better than the other three models.Results show that the ASP-SERes2Net algorithm has better performance and is suitable for speaker recognition applied in noise environment.

speaker recognitionMel spectrogramRes2Netsqueeze-and-excitation(SE)attention moduleattention statistics pooling(ASP)additive angular margin Softmax(AAM-Softmax)

令晓明、陈鸿雁、张小玉、张真

展开 >

兰州交通大学光电技术与智能控制教育部重点实验室,兰州 730070

兰州交通大学国家绿色镀膜技术与装备工程技术研究中心,兰州 730070

说话人识别 梅尔语谱图 Res2Net 压缩激活(squeeze-and-excitation,SE)注意力模块 注意力统计池化(attention statistics pooling,ASP) 附加角裕度的 Softmax(additive angular margin Softmax,AAM-Softmax)

2025

10.11936/bjutxb2023060027

北京工业大学学报
北京工业大学

北京工业大学学报

北大核心
影响因子：0.418
ISSN：0254-0037
年,卷(期)：2025.51(1)