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

facebooktwittermailshare

A study of speaker verification performance with expressive speech

Abstract: 

Expressive speech introduces variations in the acoustic features affecting the performance of speech technology such as speaker verification systems. It is important to identify the range of emotions for which we can reliably estimate speaker verification tasks. This paper studies the performance of a speaker verification system as a function of emotions. Instead of categorical classes such as happiness or anger, which have important intra-class variability, we use the continuous attributes arousal, valence, and dominance which facili- tate the analysis. We evaluate an speaker verification system trained with the i-vector framework with a probabilistic linear discriminant analysis (PLDA) back-end. The study relies on a subset of the MSP- PODCAST corpus, which has naturalistic recordings from 40 speak- ers. We train the system with neutral speech, creating mismatches on the testing set. The results show that speaker verification errors increase when the values of the emotional attributes increase. For neutral/moderate values of arousal, valence and dominance, the speaker verification performance are reliable. These results are also observed when we artificially force the sentences to have the same duration.

up
0 users have voted:

Paper Details

Authors:
Srinivas Parthasarathy, Chunlei Zhang, John H.L. Hansen, Carlos Busso
Submitted On:
20 May 2020 - 10:37am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Srinivas Parthasarathy
Document Year:
2017
Cite

Document Files

Parthasarathy_2017_2-poster.pdf

(10)

Subscribe

[1] Srinivas Parthasarathy, Chunlei Zhang, John H.L. Hansen, Carlos Busso, "A study of speaker verification performance with expressive speech", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5416. Accessed: Jun. 06, 2020.
@article{5416-20,
url = {http://sigport.org/5416},
author = {Srinivas Parthasarathy; Chunlei Zhang; John H.L. Hansen; Carlos Busso },
publisher = {IEEE SigPort},
title = {A study of speaker verification performance with expressive speech},
year = {2020} }
TY - EJOUR
T1 - A study of speaker verification performance with expressive speech
AU - Srinivas Parthasarathy; Chunlei Zhang; John H.L. Hansen; Carlos Busso
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5416
ER -
Srinivas Parthasarathy, Chunlei Zhang, John H.L. Hansen, Carlos Busso. (2020). A study of speaker verification performance with expressive speech. IEEE SigPort. http://sigport.org/5416
Srinivas Parthasarathy, Chunlei Zhang, John H.L. Hansen, Carlos Busso, 2020. A study of speaker verification performance with expressive speech. Available at: http://sigport.org/5416.
Srinivas Parthasarathy, Chunlei Zhang, John H.L. Hansen, Carlos Busso. (2020). "A study of speaker verification performance with expressive speech." Web.
1. Srinivas Parthasarathy, Chunlei Zhang, John H.L. Hansen, Carlos Busso. A study of speaker verification performance with expressive speech [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5416