This paper presents a speech recognition system which incorporates predictive neural networks. The neural networks are used to predict observation vectors of speech. The prediction error vectors are modeled on the state level by Gaussian densities, which provide the local similarity measure for the Viterbi algorithm during recognition. The system is evaluated on a continuous speech phoneme reco...

This paper describes a morphological analysis method of continuous spoken Korean to solve the integration problem of speech recognition and natural language processing. The method centers on a Viterbi search-based morphological analysis on top of speech signal processing and MLP-based phone recognition. The main contribution of this paper is to introduce a Viterbi search-based morphological ana...

| In this paper we report a series of tests carried out on our hybrid HMM/ANN systems which aims at combining Neural Networks theory and Hidden Markov Models (HMMs) for speech recognition of a continuous speech French database: BREF-80. As this database is not manually labelled , we describe a new method based on the temporal alignment of the speech signal on a high quality synthetic speech pat...

Abstract. In this paper, we focus on a novel NN/HMM architecture for continuous speech recognition. The architecture incorporates a neural feature extraction to gain more discriminative feature vectors for the underlying HMM system. The feature extraction can be chosen either linear or non-linear and can incorporate recurrent connections. With this hybrid system, that is an extension of a state...

This paper presents an approach for the automatic speech recognition using syllabic units. Its segmentation is based on using the ShortTerm Total Energy Function (STTEF) and the Energy Function of the High Frequency (ERO parameter) higher than 3,5 KHz of the speech signal. Training for the classification of the syllables is based on ten related Spanish language rules for syllable splitting. Rec...