强大的依赖文本的扬声器验证系统使用性别意识的语三重体深度神经网络
1Department of Electronics and Communication Engineering, Dronacharya Group of Institutions, Greater Noida, UP, India.
Network (Bristol, England)
|December 29, 2024
概括
这项研究引入了一种性别意识的语三元网络-深度神经网络 (ST-DNN),以改进扬声器验证. 新型架构显著降低了错误率,提高了语音认证系统的安全性.
科学领域:
- 语音处理 语音处理
- 机器学习 机器学习
- 生物识别信息 生物识别信息
背景情况:
- 基于文本的扬声器验证对于安全至关重要,但由于语音变化而受到挑战.
- 现有的方法与语言多样性和性别特定的音调差异作斗争,影响准确性.
研究的目的:
- 引入一个性别意识的语三元网络-深度神经网络 (ST-DNN) 进行增强的扬声器验证.
- 解决语音质量,语言多样性和性别差异引起的扬声器认证方面的挑战.
主要方法:
- 使用卷积式2D层与RELU激活用于特征提取.
- 实现了多融合密度跳过连接和批量规范化以实现功能集成.
- 采用了独立的男性和女性ST-DNN模型,包括个人,族和三重网络.
主要成果:
- 在男性 (32.31%54.55%) 和女性 (33.73%38.98%) 中,实现了同等错误率 (EER) 的显著降低.
- 在男性 (53.47%86.36%) 和女性 (39.46%71.19%) 的最低决策成本函数 (MinDCF) 中显著降低.
- 验证了ST-DNN架构在RSR2015和RedDots挑战2016数据集上的有效性.
结论:
- 性别意识的ST-DNN架构有效地提高了依赖文本的扬声器验证准确性.
- 拟议的方法稳定地处理语音质量,语言多样性和性别特征的变化.
- 结果证实了ST-DNN适用于现实世界高安全语音认证应用的适用性.
更多相关视频
相关概念视频
02:07Improving Translational Accuracy
8.5K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
8.5K
02:16Stereotype Content Model
13.9K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
13.9K
01:17Sign Test for Matched Pairs
58
The sign test for matched pairs offers a robust method for comparing two paired samples, often for the effects of an intervention in one of them. This method is very useful in situations where the underlying distribution of the data is unknown. The test compares two related samples—often pre- and post-treatment measurements on the same subjects—to determine if there are significant differences in their median values.
To conduct the sign test, we first calculate the differences in...
To conduct the sign test, we first calculate the differences in...
58
02:30Small interfering RNAs (siRNA)
3.3K
3.3K