Add to ORKGTo improve the performance of the telephone-line speaker identification system, we take in use three statistical ensemble methods: boosting [1], bagging [2] and combination of weak perceptrons (CWP) [3]. Our motivation lies in two aspects. Firstly, we are trying to find out whether those statistical ensemble methods can work when they are applied on this given real world problem, although they perform well in several other learning problems. Secondly, unlike previous researches on using statistical ensemble methods where no studies are conducted on mismatch conditions, in this paper, we are trying to make an investigation on our system where miscellaneous mismatch factors are involved. Meanwhile, we investigate the stability performance of ...
We address the question of whether and how boosting and bagging can be used for speech recognition....
Score-based fusion of multiple independent models for the purpose of identifying speakers is widely ...
Feature transformation plays an important role in robust speaker verification over telephone network...
Unlike previous comparative studies, we present an empirical evaluation on three typical statistical...
Statistical ensemble learning methods have turned to be effective way to improve accuracy of a learn...
This paper investigates a number of ensemble methods for improv-ing the performance of phoneme class...
We address the question of whether and how boosting and bagging can be used for speech recognition. ...
The speech spectra of a known group of ten speakers were used to identify a speaker arbitrarily sele...
This paper presents a technique using artificial neural networks (ANNs) for speaker identification t...
This paper presents an experimental study on the impact of telephone channels on the accuracy of aut...
Abstract—Two important components of a speaker identifica-tion system are the feature extraction and...
In this work we improve the performance of a speaker verification system by matching the feature vec...
In this paper, we propose a novel rank-based classifier combination scheme under uncertainty for spe...
Bibliography: leaves 95-104.Speech recognition systems all have one criterion in common; they perfor...
Abstract In this study, a speaker identification system is considered consisting of a feature extrac...
We address the question of whether and how boosting and bagging can be used for speech recognition....
Score-based fusion of multiple independent models for the purpose of identifying speakers is widely ...
Feature transformation plays an important role in robust speaker verification over telephone network...
Unlike previous comparative studies, we present an empirical evaluation on three typical statistical...
Statistical ensemble learning methods have turned to be effective way to improve accuracy of a learn...
This paper investigates a number of ensemble methods for improv-ing the performance of phoneme class...
We address the question of whether and how boosting and bagging can be used for speech recognition. ...
The speech spectra of a known group of ten speakers were used to identify a speaker arbitrarily sele...
This paper presents a technique using artificial neural networks (ANNs) for speaker identification t...
This paper presents an experimental study on the impact of telephone channels on the accuracy of aut...
Abstract—Two important components of a speaker identifica-tion system are the feature extraction and...
In this work we improve the performance of a speaker verification system by matching the feature vec...
In this paper, we propose a novel rank-based classifier combination scheme under uncertainty for spe...
Bibliography: leaves 95-104.Speech recognition systems all have one criterion in common; they perfor...
Abstract In this study, a speaker identification system is considered consisting of a feature extrac...
We address the question of whether and how boosting and bagging can be used for speech recognition....
Score-based fusion of multiple independent models for the purpose of identifying speakers is widely ...
Feature transformation plays an important role in robust speaker verification over telephone network...