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。
Firstly, a weighted realized variance and a weighted realized covariance which are based on high frequency data are put forward.
首先提出了基于高频数据的赋权已实现变差估计量和赋权已实现协变差估计量。
Firstly, a weighted realized variance and a weighted realized covariance which are based on high frequency data are put forward.
首先提出了基于高频数据的赋权已实现变差估计量和赋权已实现协变差估计量。
应用推荐