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

facebooktwittermailshare

First Investigation of Universal Speech Attributes for Speaker Verification

Abstract: 

The universal speech attributes to speaker verification (SV) is addressed in this paper. The manner and place of articulation form the universal attribute unit inventory, and deep neural network (DNN) is used as acoustic model. Two methods to generate the attribute units are proposed in this paper: one is that the manner and place of articulation are directly combined to generate more robust universal speech attribute units, and the other is that the different context-dependent speech arttribute units are merged to a new speech attribute unit set by means of automatic clustering in accordance with likelihood calculation. Evaluated on the core test from the 2008 NIST speaker verification evaluation (SRE), the novel generated attribute units based system can achieve a better performance than that of the phoneme based system. Furthermore, the attribute based system has demonstrated a good complementarity with the GMM-UBM/i-vector and phoneme based DNN/i-vector systems

up
0 users have voted:

Paper Details

Authors:
Sheng Zhang, Wu Guo, Guoping Hu
Submitted On:
13 October 2016 - 4:25am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Sheng Zhang
Paper Code:
ISCSLP1601
Document Year:
2016
Cite

Document Files

ISCSLP-张圣.pdf

(0)

Subscribe

[1] Sheng Zhang, Wu Guo, Guoping Hu, "First Investigation of Universal Speech Attributes for Speaker Verification", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1169. Accessed: Sep. 20, 2018.
@article{1169-16,
url = {http://sigport.org/1169},
author = {Sheng Zhang; Wu Guo; Guoping Hu },
publisher = {IEEE SigPort},
title = {First Investigation of Universal Speech Attributes for Speaker Verification},
year = {2016} }
TY - EJOUR
T1 - First Investigation of Universal Speech Attributes for Speaker Verification
AU - Sheng Zhang; Wu Guo; Guoping Hu
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1169
ER -
Sheng Zhang, Wu Guo, Guoping Hu. (2016). First Investigation of Universal Speech Attributes for Speaker Verification. IEEE SigPort. http://sigport.org/1169
Sheng Zhang, Wu Guo, Guoping Hu, 2016. First Investigation of Universal Speech Attributes for Speaker Verification. Available at: http://sigport.org/1169.
Sheng Zhang, Wu Guo, Guoping Hu. (2016). "First Investigation of Universal Speech Attributes for Speaker Verification." Web.
1. Sheng Zhang, Wu Guo, Guoping Hu. First Investigation of Universal Speech Attributes for Speaker Verification [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1169