An empirical study of exploring nonphonetic forensic speaker recognition features
So far, phonetic features have been the main type of forensic speaker recognition features studied and used in practice. One problem with phonetic forensic speaker recognition features is that they are affected dramatically by the real-world conditions, which results in within-speaker variations and...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Wolters Kluwer Medknow Publications
2018-01-01
|
Series: | Journal of Forensic Science and Medicine |
Subjects: | |
Online Access: | http://www.jfsmonline.com/article.asp?issn=2349-5014;year=2018;volume=4;issue=3;spage=142;epage=149;aulast=Guan |
id |
doaj-eaae462d096649c9a2df45718a05d02e |
---|---|
record_format |
Article |
spelling |
doaj-eaae462d096649c9a2df45718a05d02e2020-11-24T22:03:00ZengWolters Kluwer Medknow PublicationsJournal of Forensic Science and Medicine2349-50142018-01-014314214910.4103/jfsm.jfsm_20_18An empirical study of exploring nonphonetic forensic speaker recognition featuresXin GuanSo far, phonetic features have been the main type of forensic speaker recognition features studied and used in practice. One problem with phonetic forensic speaker recognition features is that they are affected dramatically by the real-world conditions, which results in within-speaker variations and consequently reduces the reliability of forensic speaker cognition results. In this context, supported by Sapir's description of the structure of speech behavior and discourse information theory, natural conversations are adopted as experiment materials to explore nonphonetic features that are supposed to be less affected by real-world conditions. The results of experiments show that first there exist nonphonetic features besides phonetic features, and what's more, the nonphonetic features are less affected by real-world conditions as expected.http://www.jfsmonline.com/article.asp?issn=2349-5014;year=2018;volume=4;issue=3;spage=142;epage=149;aulast=GuanForensic speaker recognitionnatural conversationsnonphoneticreal-world conditions |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xin Guan |
spellingShingle |
Xin Guan An empirical study of exploring nonphonetic forensic speaker recognition features Journal of Forensic Science and Medicine Forensic speaker recognition natural conversations nonphonetic real-world conditions |
author_facet |
Xin Guan |
author_sort |
Xin Guan |
title |
An empirical study of exploring nonphonetic forensic speaker recognition features |
title_short |
An empirical study of exploring nonphonetic forensic speaker recognition features |
title_full |
An empirical study of exploring nonphonetic forensic speaker recognition features |
title_fullStr |
An empirical study of exploring nonphonetic forensic speaker recognition features |
title_full_unstemmed |
An empirical study of exploring nonphonetic forensic speaker recognition features |
title_sort |
empirical study of exploring nonphonetic forensic speaker recognition features |
publisher |
Wolters Kluwer Medknow Publications |
series |
Journal of Forensic Science and Medicine |
issn |
2349-5014 |
publishDate |
2018-01-01 |
description |
So far, phonetic features have been the main type of forensic speaker recognition features studied and used in practice. One problem with phonetic forensic speaker recognition features is that they are affected dramatically by the real-world conditions, which results in within-speaker variations and consequently reduces the reliability of forensic speaker cognition results. In this context, supported by Sapir's description of the structure of speech behavior and discourse information theory, natural conversations are adopted as experiment materials to explore nonphonetic features that are supposed to be less affected by real-world conditions. The results of experiments show that first there exist nonphonetic features besides phonetic features, and what's more, the nonphonetic features are less affected by real-world conditions as expected. |
topic |
Forensic speaker recognition natural conversations nonphonetic real-world conditions |
url |
http://www.jfsmonline.com/article.asp?issn=2349-5014;year=2018;volume=4;issue=3;spage=142;epage=149;aulast=Guan |
work_keys_str_mv |
AT xinguan anempiricalstudyofexploringnonphoneticforensicspeakerrecognitionfeatures AT xinguan empiricalstudyofexploringnonphoneticforensicspeakerrecognitionfeatures |
_version_ |
1725833631256018944 |