This report focuses on a hybrid approach, including stochastic and connectionist methods , for continuous speech recognition. Hidden Markov Models (HMMs) are a popular stochastic approach used for continuous speech, well suited to cope with the high variability found in natural utterances. On the other hand, artiicial neural networks (NNs) have shown high classiication power for short speech ut...

The carbonation tower is a key reactor to manufacturing synthetic soda ash using the Solvay process. Because of the complexity of the reaction in the tower, it is difficult to control such a nonlinear large-time-delay system with normal measurement instrumentation. To solve this problem, a time-delay neural network (TDNN) is used in the soft measurement model in this paper. A special back-propa...

Phonological feature space has been proposed to represent acoustic models for automatic speech recognition (ASR) tasks. The most successful methods to detect articulatory gestures from the speech signal are based on Time Delay Neural Networks (TDNN). Stochastic Finite-State Automata have been effectively used in many speech-input natural language tasks. They are versatile models with well estab...

This paper concerns dynamic neural networks for signal processing: architectural issues are considered but the paper focuses on learning algorithms that work on-line. Locally recurrent neural networks, namely MLP with IIR synapses and generalization of Local Feedback MultiLayered Networks (LF MLN), are compared to more traditional neural networks, i.e. static MLP with input and/or output buffer...

A new tightly coupled speech and natural language integration model is presented for a TDNN-based continuous possibly large vocabulary speech recognition system for Korean. Unlike popular n-best techniques developed for integrating mainly HMM-based speech recognition and natural language processing in a word level, which is obviously inadequate for morphologically complex agglutinative language...

Three networks are compared for low false alarm stock trend predictions. Short-term trends, particularly attractive for neural network analysis, can be used profitably in scenarios such as option trading, but only with significant risk. Therefore, we focus on limiting false alarms, which improves the risk/reward ratio by preventing losses. To predict stock trends, we exploit time delay, recurre...

This paper presents a speech intelligibility model based on automatic recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and performance measure that estimates the word error rate these probabilities. does not require clean reference nor labels during testing as ASR decoding step, which finds most likely sequence of words given posterior probabilities, is omitted...

We study the Focused Gamma Network and its special case TDNN for speech recognition from a signal representation point of view and show that these structures extract the features of the signals input to them in the form of Taylor's series approximation performed in the frequency domain.

A new scheme to represent phonological changes during continuous speech recognition is suggested. A phonological tag coupled with its morphological tag is designed to represent the conditions of Korean phonological changes. A pairwise language model of these morphological and phonological tags is implemented in Korean speech recognition system. Performance of the model is verified through the T...

The focused gamma network is proposed as one of the possible implementations of the gamma neural model. The focused gamma network is compared with the focused backpropagation network and TDNN for a time series prediction problem, and with ADALINE in a system identification problem.