首页|基于Group-Res2Block的智能合成语音说话人确认方法

基于Group-Res2Block的智能合成语音说话人确认方法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
针对现有说话人确认任务基于自然语音条件下并不适用于智能合成语音的问题,提出一种基于Group-Res2Block的智能合成语音说话人确认方法.首先,设计了 Group-Res2Block结构,在Res2Block的基础上将当前分组与相邻前后分组进行合并形成新的分组,以增强说话人局部特征的上下文联系;其次,设计了并行结构的多尺度通道注意力特征融合机制,利用不同大小卷积核实现同一层级的特征在通道维度的特征选择,以获取更具表现力的说话人特征,避免信息冗余;最后,设计了串行结构的多尺度层注意力特征融合机制,构建层结构,将深浅层特征整体进行融合并赋予不同权重,以获取最优的特征表达.为验证所提出特征提取网络的有效性,构建了中英文两种智能合成语音数据集进行消融实验和对比实验.结果表明本文方法在该任务的评价指标精确度(accuracy,ACC)、等错误率(equal error rate,EER)和最小检测代价函数(minimum detection cost function,minDCF)上是最优的.此外,通过对模型泛化性能进行测试,验证了本文方法对未知智能语音算法的适用性.
Intelligent Synthetic Voice Speaker Verification Method Based on Group-Res2Block
The existing speaker verification task is primarily based on natural speech con-ditions,rendering it unsuitable for intelligent speech synthesis.In response,this paper pro-poses an intelligent synthetic voice speaker verification method based on Group-Res2Block.Firstly,the Group-Res2Block structure is designed,integrating the current group with ad-jacent front and rear groups to foster a stronger contextual connection of the speaker's local characteristics.Secondly,a multi-scale channel attention feature fusion mechanism with parallel structure is designed.This mechanism employs various-sized convolution ker-nels to select features of the same level in the channel dimension,thereby extracting more expressive speaker features and avoiding information redundancy.Finally,a multi-scale attention feature fusion mechanism of serial structure is designed,and a layer structure is constructed to integrate the deep and shallow features as a whole and give different weights to obtain the optimal feature expression.To verify the effectiveness of the pro-posed feature extraction network,this paper constructs two kinds of intelligent synthetic speech datasets in Chinese and English.Through ablation and comparative experiments,it is shown that the proposed method outperforms others on evaluation metrics such as accuracy(ACC),equal error rate(EER)and minimum detection cost function(minDCF)for the task.Furthermore,the test results of the generalization performance of the model verify its applicability to unknown intelligent speech algorithms.

speaker verificationintelligent voice synthesisGroup-Res2Block deep neural networkmulti-scale featuresattention mechanism

李菲、苏兆品、王年松、杨波、张国富

展开 >

合肥工业大学计算机与信息学院,安徽合肥 230601

合肥工业大学工业安全与应急技术安徽省重点实验室,安徽合肥 230601

安徽省公安厅物证鉴定管理处,安徽合肥 230000

说话人确认 智能合成语音 Group-Res2Block深度神经网络 多尺度特征 注意力机制

安徽省重点研发计划安徽省重点研发计划广东省类脑智能计算重点实验室开放基金中央高校基本科研业务费专项中央高校基本科研业务费专项中央高校基本科研业务费专项

202004d07020011202104d07020001GBL202117PA2021GDSK0073PA2021GDSK0074PA2022GDSK0037

2024

10.3969/j.issn.0255-8297.2024.04.012

应用科学学报
上海大学 中国科学院上海技术物理研究所

应用科学学报

CSTPCD北大核心
影响因子：0.594
ISSN：0255-8297
年,卷(期)：2024.42(4)
  • 1