The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kertas kerja ini membentangkan kaedah pengesahan pembesar suara yang lebih baik menggunakan ujian nisbah kebarangkalian berjujukan (SPRT), yang boleh merawat korelasi antara vektor ciri berturut-turut. Model Markov tersembunyi dengan anggaran medan min membolehkan kita mempertimbangkan korelasi dalam SPRT, iaitu, menggunakan medan min keadaan sebelumnya, pengiraan kebarangkalian boleh dijalankan seolah-olah sampel input adalah bebas antara satu sama lain.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Hideki NODA, Katsuya HARADA, Eiji KAWAGUCHI, "A Context-Dependent Sequential Decision for Speaker Verification" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 10, pp. 1433-1436, October 1999, doi: .
Abstract: This paper presents an improved method of speaker verification using the sequential probability ratio test (SPRT), which can treat the correlation between successive feature vectors. The hidden Markov model with the mean field approximation enables us to consider the correlation in the SPRT, i. e. , using the mean field of previous state, probability computation can be carried out as if input samples were independent each other.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_10_1433/_p
Salinan
@ARTICLE{e82-d_10_1433,
author={Hideki NODA, Katsuya HARADA, Eiji KAWAGUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={A Context-Dependent Sequential Decision for Speaker Verification},
year={1999},
volume={E82-D},
number={10},
pages={1433-1436},
abstract={This paper presents an improved method of speaker verification using the sequential probability ratio test (SPRT), which can treat the correlation between successive feature vectors. The hidden Markov model with the mean field approximation enables us to consider the correlation in the SPRT, i. e. , using the mean field of previous state, probability computation can be carried out as if input samples were independent each other.},
keywords={},
doi={},
ISSN={},
month={October},}
Salinan
TY - JOUR
TI - A Context-Dependent Sequential Decision for Speaker Verification
T2 - IEICE TRANSACTIONS on Information
SP - 1433
EP - 1436
AU - Hideki NODA
AU - Katsuya HARADA
AU - Eiji KAWAGUCHI
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 1999
AB - This paper presents an improved method of speaker verification using the sequential probability ratio test (SPRT), which can treat the correlation between successive feature vectors. The hidden Markov model with the mean field approximation enables us to consider the correlation in the SPRT, i. e. , using the mean field of previous state, probability computation can be carried out as if input samples were independent each other.
ER -