Different normalization methods are applied in recent Large Vocabulary Continuous Speech Recognition Systems (LVCSR) to reduce the influence of speaker variability on the acoustic models. In this paper we investigate the use of Vocal Tract Length Normalization (VTLN) and Speaker Adaptive Training (SAT) in Multi Layer Perceptron (MLP) feature extraction on an English task. We achieve significant...

Multilayer perceptrons (MLP) has been proven to be very successful in many applications including classification. The activation function is the source of the MLP power. Careful selection of the activation function has a huge impact on the network performance. This paper gives a quantitative comparison of the four most commonly used activation functions, including the Gaussian RBF network, over...

Occupying more than 70% of the concrete’s volume, aggregates play a vital role as the raw feed for construction materials; particularly in the production of concrete and concrete products. Often, the characteristics such as shape, size and surface texture of aggregates significantly affect the quality of the construction materials produced. This article discusses a novel method for automatic cl...

The present paper deals with the continuous work of extending multi-dimensional limiting process (MLP), which has been quite successfully proposed on twoand three-dimensional structured grids, onto the unstructured grids. The basic idea of the present limiting strategy is to control the distribution of both cell-centered and cell-vertex physical properties to mimic a multi-dimensional nature of...

Ensemble of classifiers is one of the most researched methods in pattern classification in recency. It’s a well-known fact that multiple phases for evaluation provides more accuracy. In this paper we proposed a multistage classifier approach where we are applying three supervised classifiers for the classification in pattern recognition. Three Classifiers are Multilayer Perceptron (MLP), K-Near...

Abstract the co-articulation is one of the main reasons that makes the speech recognition difficult. However, the traditional Hidden Markov Models(HMM) can not model the co-articulation, because they depend on the first-order assumption. In this paper, for modeling the co-articulation, we propose a more perfect HMM than traditional first order HMM on the basis of our previous works and they giv...

Mapping knowledge structures is a key task in Knowledge Discovery in Databases (KDD). In order to display the thematic organization of knowledge, we compare and evaluate two different cartography approaches: principal components analysis (PCA) and a multilayer perceptron (MLP) in "self-association" mode. This kind of MLP can be used to perform a PCA when the activation function is set to the id...

This paper describes a very efficient Parallel Phone Recognizers followed by Language Modeling (PPRLM) system in terms of both performance and processing speed. The system uses context-independent phone recognizers trained on MLP features concatenated with the conventional PLP and pitch features. MLP features have several interesting properties that make them suitable for speech processing, in ...

We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLP). The acoustic features are based on frame-level phone posterior probabilities, obtained by merging two different MLP estimators, one based on PLP-Tandem features, the other based on hidden activation TRAPs (HATs) featu...