This paper reports our recent progress on using multilingual data for improving speech-to-text (STT) systems that can be easily delivered. We continued the work BBN conducted on the use of multilingual data for improving Babel evaluation systems, but focused on training time-delay neural network (TDNN) based chain models. As done for the Babel evaluations, we used multilingual data in two ways:...

A neural network based technique is introduced which hides the control latency of reconfigurable interconnection networks (INs) in shared memory multiprocessors. Such INs require complex control mechanisms to reconfigure the IN on demand, in order to satisfy processor-memory accesses. Hiding the control latency seen by each access improves multiprocessor performance significantly. The new techn...

This paper presents results regarding the application of Time-Delay Neural Networks (TDNNs), up to now mainly used in speech recognition, for control tasks. A set of examples taken from a model-based robot controller is used to validate the suitability of the TDNN and to show its superiority to standard multilayer perceptrons. Afterwards, a new algorithm is presented that shows how the inherent...

This paper discusses the performance comparison of an artificial neural network (ANN) model and a memory polynomial (MP) model for modeling the dynamic nonlinear input-output characteristics of power amplifier (PA) with memory. The ANN model was based on time delay neural network (TDNN) and the memory polynomial model was developed using analytical polynomial function. Both models were develope...

| This paper presents the Time Delay Radial Basis Function Network (TDRBF) for recognition of pho-nemes. The TDRBF combines features from Time Delay Neural Networks (TDNN) and Radial Basis Functions (RBF). The ability to detect acoustic features and their temporal relationship independent of position in time is inherited from TDNN. The use of RBFs leads to shorter training times and less parame...

A b s t r a c t . This paper presents a time-delayed neural network (TDNN) model that has the capability of learning and predicting the dynamic behavior of nonlinear elements that compose a wireless communication system. This model could help speeding up system deployment by reducing modeling time. This paper presents results of effective application of the TDNN model to an amplifier, part of a...

In this paper, a new Behavioral model that has the capability to learn and predict the dynamic behavior of nonlinear PAs, based on a Time-Delayed Neural Network (TDNN), is proposed. The Neural Network model can be trained with input/output device measurements or simulations, and a very good accuracy can be obtained in the device characterization easily and rapidly. These properties make this ki...

This paper compares the accuracy of three hybrid intelligent systems in forecasting ten international stock market indices; namely the CAC40, DAX, FTSE, Hang Seng, KOSPI, NASDAQ, NIKKEI, S&P500, Taiwan stock market price index, and the Canadian TSE. In particular, genetic algorithms (GA) are used to optimize the topology and parameters of the adaptive time delay neural networks (ATNN) and the t...

This paper presents an approach using a mixture of connectionist experts for the identification of complex Arabic phonetic features such as the emphasis, the gemination and the relevant duration of vowels. These experts are typically time delay neural networks using a version of autoregressive backpropagation algorithm (AR-TDNN). A serial and parallel architectures of AR-TDNN have been implemen...

This paper introduces a stacked architecture that uses a time delay neural network (TDNN) to model long-term patterns for spoken language identification. The first component of the architecture is a feed-forward neural network with a bottleneck layer that is trained to classify context-dependent phone states (senones). The second component is a TDNN that takes the output of the bottleneck, conc...