Learn More
The results of our research presented in this paper is twofold. First, an estimation of global posteriors is formalized in the framework of hybrid HMM/ANN systems. It is shown that hybrid HMM/ANN systems, in which the ANN part estimates local posteriors, can be used to modelize global model posteriors. This for-malization provides us with a clear theory in(More)
In this paper, we propose a new acoustic confidence measure of ASR hypothesis and compare it to approaches proposed in the literature. This approach takes into account prior information on the acoustic model performance specific to each phoneme. The new method is tested on two types of recognition errors: the out-of-vocabulary words and the errors due to(More)
Major progress is being recorded regularly on both the technology and exploitation of automatic speech recognition (ASR) and spoken language systems. However, there are still technological barriers to flexible solutions and user satisfaction under some circumstances. This is related to several factors, such as the sensitivity to the environment (background(More)
In this paper, we focus on the modeling of coarticulation and pronunciation variation in Automatic Speech Recognition systems (ASR). Most ASR systems explicitly describe these production phenomena through context-dependent phoneme models and multiple pronunciation lexicons. Here, we explore the potential benefit of using feature spaces covering longer time(More)
In this paper, we discuss the use of artificial room reverberation to increase the performance of automatic speech recognition (ASR) systems in reverberant enclosures. Our approach consists in training acoustic models on artificially reverberated speech material. In order to obtain the desired reverberated speech training database, we propose to use a(More)
The results of our research presented in this paper are twofold. First, an estimation of global posteriors is formalized in the framework of hybrid HMMMANN systems. It is shown that hybrid HMMMANN systems , in which the ANN part estimates local posteriors , can be used to modelize global model posteriors. This formalization provides us with a clear theory(More)
In this paper, hybrid HMM/ANN systems are used to model context dependent phones. In order to reduce the number of parameters as well as to better catch the dynamics of the phonetic segments, we combine (context dependent) diphone models with context independent phone models. Transitions from phone to phone are modeled as generalized context dependent(More)