A generalization of the minimum classification error (MCE) training method for speech recognition and detection
نویسنده
چکیده
منابع مشابه
Improved performance and generalization of minimum classification error training for continuous speech recognition
Discriminative training of hidden Markov models (HMMs) using segmental minimum classi cation error (MCE) training has been shown to work extremely well for certain speech recognition applications. It is, however, somewhat prone to overspecialization. This study investigates various techniques which improve performance and generalization of the MCE algorithm. Improvements of up to 7% in relative...
متن کاملLarge-margin minimum classification error training: A theoretical risk minimization perspective
Large-margin discriminative training of hidden Markov models has received significant attention recently. A natural and interesting question is whether the existing discriminative training algorithms can be extended directly to embed the concept of margin. In this paper, we give this question an affirmative answer by showing that the sigmoid bias in the conventional minimum classification error...
متن کاملLarge-Margin Gaussian Mixture Modeling for Automatic Speech Recognition
Discriminative training for acoustic models has been widely studied to improve the performance of automatic speech recognition systems. To enhance the generalization ability of discriminatively trained models, a large-margin training framework has recently been proposed. This work investigates large-margin training in detail, integrates the training with more flexible classifier structures such...
متن کاملA minimum classification error based distance measure for template based speech recognition
In this paper we investigate the minimum classification error (MCE) criterion for the training of distance measures for template based speech recognition. These MCE-based distance measures are illustrated with example experiments on the Wall Street Journal 5k benchmark for continuous speech recognition.
متن کاملGeneralization of the minimum classification error (MCE) training based on maximizing generalized posterior probability (GPP)
In this paper, we generalize the training error definitions for minimum classification error (MCE) training and investigate their impact on recognition performance. Starting the conventional MCE method, we discuss with three issues in regard to training error definition, which may affect the recognizer performance and need to be extensively studied. We focus our discussions on the first two asp...
متن کامل