We present a multi-network Time-Delay Neural Network (TDNN)based connectionist architecture that allows us to perform multispeaker phoneme discrimination (/b,d,gh at the speaker-dependent recognition rate of 98.4%. The overall network gates the phonemic decisions of modules trained on individual speakers to form its over-all classification decision. By dynamically adapting to the input speech a...

This paper describes a study of the use of four different neural network techniques for automatic speech recognition (ASR) using two common, real-world application databases. The neural network techniques investigated were the Multi-Layer Perceptron (MLP), the Multi-Output-Layer Perceptron (MOLP), which is an improved version of the MLP , the Time-Delay Neural Network (TDNN) and the Kohohnen Se...

Shared memory multiprocessors require reconfigurable interconnection networks (INs) for scalability. These INs are reconfigured by an IN control unit. However, these INs are often plagued by undesirable reconfiguration time that is primarily due to control latency, the amount of time delay that the control unit takes to decide on a desired new IN configuration. To reduce control latency, a trai...

This paper presents the design of a neural-based acoustic control used for the equalization of the response of a sound reproduction system. The system usually can be modeled as a composite system of a loudspeaker and an acoustic signal-transmission channel. Generally, an acoustic signal radiated inside a room is linearly distorted by wall reflections. However, in a loudspeaker, the nonlinearity...

A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that often attributable speaker differences. Speaker adaptation techniques play a vital role mismatch. Model-based approaches require sufficient amounts of target ensure robustness. When amount level limited, prone overfitting poor generalization. To address issue, this paper proposes full B...

In this paper, we analyze the performance of Time Delay Neural Networks (TDNN) and Hidden Markov Models (HMM) for Electroencephalogram (EEG) signal classification. The specific focus of this study is Brain-Computer Interfacing (BCI), where near-real time detection of mental commands during a multi-channel EEG recording is desired. We argue that HMM and TDNN should be preferred over the rigid, o...

A novel prediction scheme is proposed for real-time MPEG video to predict the burst and long-range dependent traffic. The trend and periodic characteristics of MPEG video traffic are fully captured by a proposed stochastic state-space dynamic model. Then a recursive filtering algorithm is proposed to estimate traffic for long-range prediction. Simulation results based on real MPEG traffic data ...

Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then converted into speech. This paper describes a system that uses a time-delay neural network (TDNN) to perform this phonetic-to-acoustic mapping, with another neural n...

Automatic computer recognition of arbitrary handwritten characters remains as one of the more elusive targets for computer researchers. Methods incorporating knowledge of time-sequencing of data point inputs have achieved some success, but are not generally applicable to real-world applications where such time-dependency information is often not available. Using a simple algorithm for synthesiz...