arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1406.7314cs.CLcs.LG
收藏

关于线性和非线性核的不同特征提取方法的使用

On the Use of Different Feature Extraction Methods for Linear and Non Linear kernels

Institute of Computer Science of Tunis (ISI)(突尼斯计算机科学研究所);National School of Engineer of Tunis (ENIT)(突尼斯国家工程师学院)

Imen Trabelsi, Dorra Ben Ayed

摘要:

语音特征提取一直是鲁棒语音识别研究的重点,它对识别性能有着重要的影响。在本文中,我们首先研究了一组不同的特征提取方法,如线性预测编码(LPC),梅尔频率倒谱系数(MFCC)和感知线性预测(PLP)与几个特征归一化技术,如拉斯塔滤波和倒谱均值减法(CMS)。在此基础上,这些功能的比较评估的文本无关的说话人辨识使用高斯混合模型(GMM)和线性和非线性内核之间的组合基于支持向量机(SVM)的任务。

英文摘要:

The speech feature extraction has been a key focus in robust speech recognition research; it significantly affects the recognition performance. In this paper, we first study a set of different features extraction methods such as linear predictive coding (LPC), mel frequency cepstral coefficient (MFCC) and perceptual linear prediction (PLP) with several features normalization techniques like rasta filtering and cepstral mean subtraction (CMS). Based on this, a comparative evaluation of these features is performed on the task of text independent speaker identification using a combination between gaussian mixture models (GMM) and linear and non-linear kernels based on support vector machine (SVM).

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。

↑