Add to ORKGSpeech dynamic feature are routinely used in current speech recognition systems in combination with short-term (static) spectral features. The aim of this paper is to propose a method to automatically estimate the optimum ponderation of static and dynamic features in a speech recognition system. The recognition system considered in this paper is based on Continuous-Density Hidden Markov Modelling (CDHMM), widely used in speech recognition. Our approach consists basically in 1) adding two new parameters for each state of each model that weight both kinds of speech features, and 2) estimating those parameters by means of a discriminative training algorithm that minimizes the recognition error using the recently proposed Generalized Probabilis...
In this work, motivated by large margin classifiers in machine learning, we propose a novel method t...
International audienceLVCSR systems are usually based on continuous density HMMs, which are typicall...
In the paper a method of speeding up the response of a CDHMM based speech recognition system is intr...
Speech dynamic feature are routinely used in current speech recognition systems in combination with ...
Speech dynamic features, which provide smoothed estimates of the derivatives of the spectral paramet...
Speech dynamic features are routinely used in current speech recognition systems in combination with...
Speech dynamic feature are routinely used in current speech recognition systems in combination with ...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
We study the problem of parameter estimation in continuous density hidden Markov models (CD-HMMs) fo...
In this work, a framework for efficient discriminative training and modeling is developed and implem...
Abstract—Today’s speech recognition systems are based on hidden Markov models (HMMs) with Gaussian m...
Abstract. In this paper, we introduce a fast estimate algorithm for dis-criminant training of semi-c...
Speech Recognition is becoming more important in our daily life. Many applications are starting to u...
In this book, we introduce the background and mainstream methods of probabilistic modeling and discr...
In this work, motivated by large margin classifiers in machine learning, we propose a novel method t...
International audienceLVCSR systems are usually based on continuous density HMMs, which are typicall...
In the paper a method of speeding up the response of a CDHMM based speech recognition system is intr...
Speech dynamic feature are routinely used in current speech recognition systems in combination with ...
Speech dynamic features, which provide smoothed estimates of the derivatives of the spectral paramet...
Speech dynamic features are routinely used in current speech recognition systems in combination with...
Speech dynamic feature are routinely used in current speech recognition systems in combination with ...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
We study the problem of parameter estimation in continuous density hidden Markov models (CD-HMMs) fo...
In this work, a framework for efficient discriminative training and modeling is developed and implem...
Abstract—Today’s speech recognition systems are based on hidden Markov models (HMMs) with Gaussian m...
Abstract. In this paper, we introduce a fast estimate algorithm for dis-criminant training of semi-c...
Speech Recognition is becoming more important in our daily life. Many applications are starting to u...
In this book, we introduce the background and mainstream methods of probabilistic modeling and discr...
In this work, motivated by large margin classifiers in machine learning, we propose a novel method t...
International audienceLVCSR systems are usually based on continuous density HMMs, which are typicall...
In the paper a method of speeding up the response of a CDHMM based speech recognition system is intr...