arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.09231cs.SDeess.AS
收藏

基于线性和非线性预测模型残差信号的说话人识别

Speaker recognition using residual signal of linear and nonlinear prediction models

Escola Universitària Politècnica de Mataró(马塔罗理工学院);Universitat Politècnica de Catalunya(加泰罗尼亚理工大学)

Marcos Faundez-Zanuy, Daniel Rodríguez-Porcheron

摘要:

本文讨论了残差信号在说话人识别中的作用。它示出的LPCC系数定义的一个措施和一个措施定义的剩余信号的能量的组合产生了一个改进的经典方法,只考虑LPCC系数。如果从线性预测分析获得残差信号,则改进为2.63%(出错率从6.31%下降到3.68%),并且如果通过基于非线性预测神经网络的模型计算残差信号,则改进为3.68%。

英文摘要:

This Paper discusses the usefulness of the residual signal for speaker recognition. It is shown that the combination of both a measure defined over LPCC coefficients and a measure defined over the energy of the residual signal gives rise to an improvement over the classical method which considers only the LPCC coefficients. If the residual signal is obtained from a linear prediction analysis, the improvement is 2.63% (error rate drops from 6.31% to 3.68%) and if it is computed through a nonlinear predictive neural nets based model, the improvement is 3.68%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑