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...

Leakage current is a key factor in IC power consumption even in the active operating mode. We investigate the simultaneous optimization of gate size and threshold voltage to reduce leakage power. We assume a standard-cell-based design flow where the available cell sizes and threshold voltages (V t 's) are given, and model the optimization as a mixed-integer linear programming (MLP) problem. In ...

MLP based front-ends have shown significant complementary properties to conventional spectral features. As part of the DARPA GALE program, different MLP features were developed for Mandarin ASR. In this paper, all the proposed frontends are compared in systematic manner and we extensively investigate the scalability of these features in terms of the amount of training data (from 100 hours to 16...

We studied adipocytes from 8-week-old control rat offspring (CON) or rat offspring subjected to maternal low (8%) protein (MLP) feeding during pregnancy/lactation, a procedure predisposing to obesity. Acute exposure to isoproterenol or adenosine enhanced PDK4 and PPARγ mRNA gene expression in CON and MLP adipocytes. Enhanced adipocyte Pdk4 expression correlated with increased PPARγ expression. ...

This study aims to develop a generalized framework of an SOM called a modular network SOM (mnSOM). The mnSOM has an array structure consisting of functional modules that are trainable neural networks, e.g., multi-layer perceptrons (MLPs), instead of the vector units of the conventional SOM. In the case of MLP-modules, an mnSOM learns a group of systems or functions in terms of the input-output ...

In this paprr, we dvscribe d recurrent neural network based, isolated word speech recognizer. 'The recognizer uses 2 MLP's. A f i s t , static MLP is used for classification of frames in phonemes. Next, a time compression step is applied. The resulting pseudo-segments are then used as inputs for a second, dynamic MLP that integrates the information over time to decide the current word. We apply...

In this paper, an experimental evaluation of the neurofuzzy models NEFCLASS and FuNN is conducted in real world pattern recognition applications. The models are investigated with respect to classification performance and the number of rules generated and compared to the traditional MLP network trained with backpropagation. The models NEFCLASS and FuNN are examined in benchmarking problems from ...

We have proposed the glial network which was inspired from the feature of brain. In the glial network, glias generate independent oscillations and these oscillations propagated neurons and other glias. We confirmed that the glial network improved the learning performance of the Multi-Layer Perceptron (MLP) In this article, we investigate the MLP with the impulse glial network. The glias have on...

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...