Equal Error Rate and Audio Digitization and Sampling Rate for Speaker Recognition System

被引：2

作者：

Singh, Nilu ^{[1
]}

Khan, R. A. ^{[1
]}

Rajshree ^{[1
]}

机构：

[1] Babasaheb Bhimrao Ambedkar Univ Cent Univ, SIST DIT, Lucknow, Uttar Pradesh, India

来源：

ADVANCED SCIENCE LETTERS | 2014年 / 20卷 / 5-6期

关键词：

Speaker Recognition; Pitch; Sampling Rate; Equal Error Rate (EER); Frequency and Resonance; Voice Fundamental;

D O I：

10.1166/asl.2014.5458

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

In this paper we try to explain some basic but important factors which are a crucial part of the Automatic Speaker recognition (ASR) System such as Voice fundamental, sampling rate, pitch, equal error rate etc. these factors are used to design and construct an Automatic Speaker Recognition System. ASR is a technology by which a person can be recognize with their voice using a machine. Speaker Recognition technology based on the speech signal which is most suitable technology to recognizing the person. ASR system can be design for Speaker Verification and Speaker Identification. Speaker Recognition/voiceprint recognition is an example of Biometrics i.e., it is a type technology using this person's physiological/behavioral characteristics can be measured, which is useful information to recognize a person.

引用

页码：1085 / 1088

页数：4