Factors that Affect i-Vectors Based Language Identification Systems

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The performance of a language identification (LID) system that uses i-vectors as features depends on several parameters, such as algorithm parameters and data parameters. In this study, an analysis of performance of a language identification system is considered, for which we focused only on data parameters in the “Back End” of the system, analyzing the influence of the amount of data and the speaker variability in the training phases of the UBM and the total variability Matrix T. Also, the Multiclass logistic regression (MLR) classifiers were analyzed, by balancing the classes of the database to train the classifiers on each language. These tests have been carried out in the Kalaka-3 database; we have used the average detection cost function (Cavg) to evaluate the performance. It is shown experimentally that in the training phase of the UBM, speaker variability is more important than a large amount of data. In the training phase of the total variability matrix T a better performance was obtained when a larger number of audios were used. And finally, balancing classes on each language to train the MLR classifiers allowed us to get a better performance only in certain languages. Using all of these proposed variations, we got a Cavg improvement of 37% in a standard language identification system.

Original languageEnglish
Title of host publicationSmart Technologies, Systems and Applications - 1st International Conference, SmartTech-IC 2019, Proceedings
EditorsFabián R. Narváez, Diego F. Vallejo, Paulina A. Morillo, Julio R. Proaño
PublisherSpringer
Pages154-164
Number of pages11
ISBN (Print)9783030467845
DOIs
StatePublished - 1 Jan 2020
Event1st International Conference on Smart Technologies, Systems and Applications, SmartTech-IC 2019 - Quito, Ecuador
Duration: 2 Dec 20194 Dec 2019

Publication series

NameCommunications in Computer and Information Science
Volume1154 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference1st International Conference on Smart Technologies, Systems and Applications, SmartTech-IC 2019
Country/TerritoryEcuador
CityQuito
Period2/12/194/12/19

Keywords

  • Data
  • i-Vector
  • Language identification

Fingerprint

Dive into the research topics of 'Factors that Affect i-Vectors Based Language Identification Systems'. Together they form a unique fingerprint.

Cite this