Speaker recognition is the most natural biometric identification technique. It can be divided into two sub-fields: speaker identification and speaker verification.
说话人识别是最自然的生物特征身份鉴定方式,可分为说话人辨认和说话人确认。
In this paper, a novel adaptive text independent speaker verification method is proposed.
该文提出一种与文本无关的自适应说话人确认方法。
This paper is mainly about techniques to complement a text-dependent speaker verification system.
本文主要针对文本相关的说话人认证技术做了研究。
A speaker verification system based on support vector regression machine (SVR) is presented in this paper.
提出一种基于支持向量回归机的说话者确认方法。
The code mismatch problem in speaker verification systems in multi-code environment always causes significant performance deterioration.
多编码环境下的说话人确认常常遇到训练和测试语音编码不匹配问题,导致性能显著下降。
In this paper, the implementation of a real-time, speaker-cooperant and Text-dependent speaker verification system is expounded in detail.
本文详细介绍了一个说话人合作的、文本相关的说话人验证系统的实现。
This paper proposes a high frequency weighted MFCC extraction method to improve the performance of speaker verification in noise conditions.
本文提出了一种可提高噪声环境下的说话人确认识别率的语音MFCC参数高频加权方法。
Therefore this thesis studies on text-independent speaker verification and channel robustness methods on feature level, model level and system level.
因此本文着重研究了与文本无关的说话人确认系统,从参数级、模型级、系统级三个方面加强了系统的信道鲁棒性。
Based on feature processing and model compensation, a weighted features compensation transformation method based on GMM for robust speaker verification was proposed.
从特征值处理和模型补偿两方面考虑,提出了基于高斯混合模型的加权特征补偿变换的抗噪声方法。
We use Bayesian maximum a posteriori estimation training a speaker model from background model, to solve the problem of model miss matching in speaker verification system.
采用贝叶斯最大后验概率估计的方式,从统一背景模型中生成说话人模型。
We use Bayesian maximum a posteriori estimation training a speaker model from background model, to solve the problem of model miss matching in speaker verification system.
采用贝叶斯最大后验概率估计的方式,从统一背景模型中生成说话人模型。
应用推荐