publication . Conference object . 2012

Discriminative classifiers for phonotactic language recognition with iVectors

Mehdi Soufifar; Sandro Cumani; Lukas Burget; Jan Cernocky;
  • Published: 07 Sep 2012
  • Publisher: IEEE
Abstract
Phonotactic models based on bags of n-grams representations and discriminative classifiers are a popular approach to the language recognition problem. However, the large size of n-gram count vectors brings about some difficulties in discriminative classifiers. The subspace Multinomial model was recently proposed to effectively represent information contained in the n-grams using low-dimensional iVectors. The availability of a low-dimensional feature vector allows investigating different post-processing techniques and different classifiers to improve recognition performance. In this work, we analyze a set of discriminative classifiers based on Support Vector Machines and Logistic Regression and we propose an iVector post-processing technique which allows to improve recognition performance. The proposed systems are evaluated on the NIST LRE 2009 task.
Persistent Identifiers
Subjects
ACM Computing Classification System: ComputingMethodologies_PATTERNRECOGNITION
free text keywords: Set (abstract data type), Artificial intelligence, business.industry, business, NIST, Speech recognition, Pattern recognition, Training set, Feature vector, Computer science, Support vector machine, Random subspace method, Feature extraction, Discriminative model, Subspace topology
Download from
null
https://doi.org/10.1109/icassp...
Conference object . 2012
Providers: Crossref
Any information missing or wrong?Report an Issue