arrow
返回

Moving average multi directional local features for speaker recognition

delete2018-02-23
delete4
PRE
AI
A
Awais Mahmood *
G
Ghulam Muhammad
M
Mansour Alsulaiman
H
Habib Dhahri
M
Mohammed Faisal
DOI:10.1007/s10586-018-2030-5delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
A new speech feature extraction technique called moving average multi directional local features (MA-MDLF) is presented in this paper. This method is based on linear regression (LR) and moving average (MA) in the time-frequency plane. Three-point LR is taken along time axis and frequency axis, and 3 points MA is taken along 45 degrees and 135 degrees in the time-frequency plane. The LR captures the voice onset\offset, formant contour, while the moving average captures the dynamics on time-frequency axes which can be seen as voiceprints. The MA-MDLF performance is compared to commonly used speech features in speaker recognition. The comparison is performed in a speaker recognition system (SRS) for three different conditions, namely clean speech, mobile speech, and cross channel. MA-MDLF has shown better performance than the baseline MFCC, RASTA-PLP and LPCC. In clean and mobile speech, MA-MDLF feature performs the best and also in the cross channel task MA-MDLF performed excellent. We also evaluated the MA-MDLF using three speech databases, namely KSU, LDC Babylon and TIMITdatabases, and found that MA-MDLF outperformed the other commonly used features with speech from all the three databases. The first and second databases are for Arabic speech while third is for English speech.
Keyword:
Speaker recognition
MDLF
MA-MDLF
Local feature
MFCC
LPCC
RASTA-PLP
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

C
Cluster Computing-The Journal of Networks Software Tools and Applications
IF:
4.1
论文数:
5.1K
被引数:
7.5K

机构

K
King Saud University
学者数:
3.4W
论文数: 3.8W
被引数: 815
引用论文

引用论文

Current Enhancement via a TiO2 Window Layer for CSS Sb2Se3 Solar Cells: Performance Limits and High V oc
err2019-03-01
err0
errOAAI
errLaurie J. Phillips; Christopher N. Savory; Oliver S. Hutter; Peter J. Yates; Huw Shiel; Silvia Mariotti; Leon Bowen; Max Birkett; Ken Durose; David O. Scanlon; Jonathan D. Major
err分享
err收藏
Prediction of Wenckebach Behavior and Block Response in DDD Pacemakers
err2006-06-30
err0
PREAI
errROLAND STROOBANDT; ROGER WILLEMS; GERMAIN HOLVOET; JOS BACKERS; ALFONS SINNAEVE
err分享
err收藏
err分享
err收藏
学者 查看更多内容