We report on investigations, conducted at the 2006 JHU Summer Workshop, of the use of articulatory features in automatic speech recognition. We explore the use of articulatory features for both observation and pronunciation modeling, and for both audio-only and audio-visual speech recognition. In the area of observation modeling, we use the outputs of a set of multilayer perceptron articulatory feature classifiers (1) directly, in an extension of hybrid HMM/ANN models, and (2) as part of the observation vector in a standard Gaussian mixture-based model, an extension of the now popular “tandem ” approach. In the area of pronunciation modeling, we explore models consisting of multiple hidden streams of states, each corresponding to a differen...
Abstract. Generally speech recognition systems make use of acoustic features as a representation of ...
Phonological studies suggest that the typical subword units such as phones or phonemes used in autom...
Artificial neural networks (ANN) have proven to be well suited to the task of articulatory feature (...
We report on investigations, conducted at the 2006 Johns HopkinsWorkshop, into the use of articulato...
We study the problem of automatic visual speech recognition (VSR) using dynamic Bayesian network (DB...
We describe a dynamic Bayesian network for articulatory feature recognition. The model is intended t...
This paper describes the use of dynamic Bayesian networks for the task of articulatory feature recog...
In this paper we investigate the use of articulatory data for speech recognition. Recordings of the ...
This thesis elaborates the use of speech production knowledge in the form of articulatory phonetic f...
The ultimate goal of our research is to develop a computational model of human speech recognition th...
The ultimate goal of our research is to develop a computational model of human speech recognition th...
The ultimate goal of our research is to develop a computational model of human speech recognition th...
Abstract Most of the current state-of-the-art speech recognition systems are based on speech signal ...
The paradigm of phone-based hidden Markov models has dominated automatic speech recognition since th...
Current technology for automatic speech recognition (ASR) uses hidden Markov models (HMMs) that reco...
Abstract. Generally speech recognition systems make use of acoustic features as a representation of ...
Phonological studies suggest that the typical subword units such as phones or phonemes used in autom...
Artificial neural networks (ANN) have proven to be well suited to the task of articulatory feature (...
We report on investigations, conducted at the 2006 Johns HopkinsWorkshop, into the use of articulato...
We study the problem of automatic visual speech recognition (VSR) using dynamic Bayesian network (DB...
We describe a dynamic Bayesian network for articulatory feature recognition. The model is intended t...
This paper describes the use of dynamic Bayesian networks for the task of articulatory feature recog...
In this paper we investigate the use of articulatory data for speech recognition. Recordings of the ...
This thesis elaborates the use of speech production knowledge in the form of articulatory phonetic f...
The ultimate goal of our research is to develop a computational model of human speech recognition th...
The ultimate goal of our research is to develop a computational model of human speech recognition th...
The ultimate goal of our research is to develop a computational model of human speech recognition th...
Abstract Most of the current state-of-the-art speech recognition systems are based on speech signal ...
The paradigm of phone-based hidden Markov models has dominated automatic speech recognition since th...
Current technology for automatic speech recognition (ASR) uses hidden Markov models (HMMs) that reco...
Abstract. Generally speech recognition systems make use of acoustic features as a representation of ...
Phonological studies suggest that the typical subword units such as phones or phonemes used in autom...
Artificial neural networks (ANN) have proven to be well suited to the task of articulatory feature (...