Add to ORKGBoosting is a general method for training an ensemble of classifiers with a view to improving performance relative to that of a single classifier. While the original AdaBoost algorithm has been defined for classification tasks, the current work examines its applicability to sequence learning problems, focusing on speech recognition. We apply boosting at the phoneme model level and recombine ex-pert decisions using multi-stream techniques. 1
Abstract The highest recognition performance is still achieved when training a recognition system wi...
This paper investigates two important issues in constructing and combining ensembles of acoustic mo...
In the following article we discuss the practical and theoretical aspects of the SphinxTrain procedu...
Boosting is a general method for training an ensemble of classifiers with a view to improving perfor...
Boosting is a general method for training an ensemble of classifiers with a view to improving perfor...
We address the question of whether and how boosting and bagging can be used for speech recognition. ...
We address the question of whether and how boosting and bagging can be used for speech recognition....
We apply boosting techniques to the problem of word error rate minimisation in speech recognition. T...
Boosting approaches are based on the idea that high-quality learning algorithms can be formed by rep...
In this study we propose two methods to improve HMM speech recognition performance. The first method...
The performance of automatic speech recognition (ASR) system can be significantly enhanced with addi...
We apply boosting techniques to the problem of word error rate minimisation in speech recognition. ...
In this paper, a novel approach for speaker recognition is proposed. The system makes use of adaptiv...
We describe the use of discriminative criteria to optimize Boosting based ensembles. Boosting algori...
Artificial neural networks (ANNs) have been used to classify phonetic features in speech. The featur...
Abstract The highest recognition performance is still achieved when training a recognition system wi...
This paper investigates two important issues in constructing and combining ensembles of acoustic mo...
In the following article we discuss the practical and theoretical aspects of the SphinxTrain procedu...
Boosting is a general method for training an ensemble of classifiers with a view to improving perfor...
Boosting is a general method for training an ensemble of classifiers with a view to improving perfor...
We address the question of whether and how boosting and bagging can be used for speech recognition. ...
We address the question of whether and how boosting and bagging can be used for speech recognition....
We apply boosting techniques to the problem of word error rate minimisation in speech recognition. T...
Boosting approaches are based on the idea that high-quality learning algorithms can be formed by rep...
In this study we propose two methods to improve HMM speech recognition performance. The first method...
The performance of automatic speech recognition (ASR) system can be significantly enhanced with addi...
We apply boosting techniques to the problem of word error rate minimisation in speech recognition. ...
In this paper, a novel approach for speaker recognition is proposed. The system makes use of adaptiv...
We describe the use of discriminative criteria to optimize Boosting based ensembles. Boosting algori...
Artificial neural networks (ANNs) have been used to classify phonetic features in speech. The featur...
Abstract The highest recognition performance is still achieved when training a recognition system wi...
This paper investigates two important issues in constructing and combining ensembles of acoustic mo...
In the following article we discuss the practical and theoretical aspects of the SphinxTrain procedu...