Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification

Abstract: 

Phonetic variability is one of the primary challenges in short duration speaker verification. This paper proposes a novel method that modifies the standard normal distribution prior in the total variability model to use a mixture of Gaussians as the prior distribution. The proposed speaker-phonetic vectors are then estimated from the posterior probability of latent variables, and each vector has a phonetic meaning. Unlike the standard total variability model, the proposed method can incorporate a phoneme classifier to perform soft content matching, which has the potential to solve the phonetic variability problem. Parameter estimation and scoring formulae for speaker-phonetic vectors method are presented. Experimental results obtained using NIST 2010 data show that the proposed technique leads to relative improvements of more than 30% when fused with total variability model and tested on 3 second duration test files.

up
0 users have voted:

Paper Details

Authors:
Jianbo Ma, Vidhyasaharan Sethu, Eliathamby Ambikairajah, Kong Aik Lee
Submitted On:
18 April 2018 - 3:07am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Kong Aik Lee
Paper Code:
4426
Document Year:
2018
Cite

Document Files

JIANBOMA_ICASSP_2018.pdf

(222)

Subscribe

[1] Jianbo Ma, Vidhyasaharan Sethu, Eliathamby Ambikairajah, Kong Aik Lee, "Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2960. Accessed: Jul. 13, 2020.
@article{2960-18,
url = {http://sigport.org/2960},
author = {Jianbo Ma; Vidhyasaharan Sethu; Eliathamby Ambikairajah; Kong Aik Lee },
publisher = {IEEE SigPort},
title = {Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification},
year = {2018} }
TY - EJOUR
T1 - Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification
AU - Jianbo Ma; Vidhyasaharan Sethu; Eliathamby Ambikairajah; Kong Aik Lee
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2960
ER -
Jianbo Ma, Vidhyasaharan Sethu, Eliathamby Ambikairajah, Kong Aik Lee. (2018). Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification. IEEE SigPort. http://sigport.org/2960
Jianbo Ma, Vidhyasaharan Sethu, Eliathamby Ambikairajah, Kong Aik Lee, 2018. Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification. Available at: http://sigport.org/2960.
Jianbo Ma, Vidhyasaharan Sethu, Eliathamby Ambikairajah, Kong Aik Lee. (2018). "Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification." Web.
1. Jianbo Ma, Vidhyasaharan Sethu, Eliathamby Ambikairajah, Kong Aik Lee. Speaker-Phonetic Vector Estimation for Short Duration Speaker Verification [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2960