Topics
MarkovElection
Speech 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 Maximum Likelihood training. Experimental results in speaker independent digit recognition show an important increase of r...
Colloque avec actes et comité de lecture. internationale.International audienceState-of-the-art auto...
In the past decades, statistics-based hidden Markov models (HMMs) have become the predominant approa...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
Speech dynamic feature 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 ...
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...
This work consists on designing a continuous speech recognition system using pattern recognition tec...
The authors describe the acoustic processor of a Spanish continuous speech recognition system based ...
Nesta dissertação é realizado um estudo teórico e a implementação em software de um sistema de recon...
In this paper we address the problem of phoneme recognition in continuous speech using a two stage p...
We study the problem of parameter estimation in continuous density hidden Markov models (CD-HMMs) fo...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
Abstract-Speech recognition is formulated as a problem of maximum likelihood decoding. This formulat...
This paper gives an overview of the principles of a system for phoneme based, large vocabulary, cont...
Colloque avec actes et comité de lecture. internationale.International audienceState-of-the-art auto...
In the past decades, statistics-based hidden Markov models (HMMs) have become the predominant approa...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
Speech dynamic feature 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 ...
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...
This work consists on designing a continuous speech recognition system using pattern recognition tec...
The authors describe the acoustic processor of a Spanish continuous speech recognition system based ...
Nesta dissertação é realizado um estudo teórico e a implementação em software de um sistema de recon...
In this paper we address the problem of phoneme recognition in continuous speech using a two stage p...
We study the problem of parameter estimation in continuous density hidden Markov models (CD-HMMs) fo...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
Abstract-Speech recognition is formulated as a problem of maximum likelihood decoding. This formulat...
This paper gives an overview of the principles of a system for phoneme based, large vocabulary, cont...
Colloque avec actes et comité de lecture. internationale.International audienceState-of-the-art auto...
In the past decades, statistics-based hidden Markov models (HMMs) have become the predominant approa...
Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully ...
Add to ORKG