The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Cet article décrit une méthode de formation d'un classificateur de modèles qui fonctionnera bien après avoir été adapté aux changements des conditions d'entrée. Considérant les méthodes d'adaptation basées sur la transformation des paramètres du classificateur, nous formulons le problème de l'optimisation des classificateurs et proposons une méthode pour les entraîner. Dans la méthode de formation proposée, le classificateur est formé pendant que l'adaptation est réalisée. La fonction objectif de la formation est donnée en fonction des performances de reconnaissance obtenues par le classificateur adapté. L'utilité de la méthode de formation proposée est démontrée par des expériences dans une tâche de reconnaissance de formes de voyelles japonaises en cinq classes avec adaptation du locuteur.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Naoto IWAHASHI, "Training Method for Pattern Classifier Based on the Performance after Adaptation" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 7, pp. 1560-1566, July 2000, doi: .
Abstract: This paper describes a method for training a pattern classifier that will perform well after it has been adapted to changes in input conditions. Considering the adaptation methods which are based on the transformation of classifier parameters, we formulate the problem of optimizing classifiers, and propose a method for training them. In the proposed training method, the classifier is trained while the adaptation is being carried out. The objective function for the training is given based on the recognition performance obtained by the adapted classifier. The utility of the proposed training method is demonstrated by experiments in a five-class Japanese vowel pattern recognition task with speaker adaptation.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_7_1560/_p
Copier
@ARTICLE{e83-d_7_1560,
author={Naoto IWAHASHI, },
journal={IEICE TRANSACTIONS on Information},
title={Training Method for Pattern Classifier Based on the Performance after Adaptation},
year={2000},
volume={E83-D},
number={7},
pages={1560-1566},
abstract={This paper describes a method for training a pattern classifier that will perform well after it has been adapted to changes in input conditions. Considering the adaptation methods which are based on the transformation of classifier parameters, we formulate the problem of optimizing classifiers, and propose a method for training them. In the proposed training method, the classifier is trained while the adaptation is being carried out. The objective function for the training is given based on the recognition performance obtained by the adapted classifier. The utility of the proposed training method is demonstrated by experiments in a five-class Japanese vowel pattern recognition task with speaker adaptation.},
keywords={},
doi={},
ISSN={},
month={July},}
Copier
TY - JOUR
TI - Training Method for Pattern Classifier Based on the Performance after Adaptation
T2 - IEICE TRANSACTIONS on Information
SP - 1560
EP - 1566
AU - Naoto IWAHASHI
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2000
AB - This paper describes a method for training a pattern classifier that will perform well after it has been adapted to changes in input conditions. Considering the adaptation methods which are based on the transformation of classifier parameters, we formulate the problem of optimizing classifiers, and propose a method for training them. In the proposed training method, the classifier is trained while the adaptation is being carried out. The objective function for the training is given based on the recognition performance obtained by the adapted classifier. The utility of the proposed training method is demonstrated by experiments in a five-class Japanese vowel pattern recognition task with speaker adaptation.
ER -