This paper proposes simultaneous decoding using multiple utterances to derive one or more allophonic transcriptions for each word. Three possible simultaneous decoding algorithms, namely the N-best-based algorithm, the forward-backward-based algorithm and the word-network-based algorithm, are outlined. The proposed word-network-based algorithm can incrementally decode a transcription from any number of training utterances. Speech recognition experiments for both known and unknown word vocabularies show up to 16% reduction in word error rate when simultaneously decoded allophonic transcriptions are added to the recognition dictionaries. This result holds even for dictionaries originally transcribed by expert phoneticians.

This paper presents an artificial neural network (ANN) for speaker-independent isolated word speech recognition. The network consists of three subnets in concatenation. The static information within one frame of speech signal is processed in the probabilistic mapping subnet that converts an input vector of acoustic features into a probability vector whose components are estimated probabilities of the feature vector belonging to the phonetic classes that constitute the words in the vocabulary. The dynamics capturing subnet computes the first-order cross correlation between the components of the probability vectors to serve as the discriminative feature derived from the interframe temporal information of the speech signal. These dynamic features are passed for decision-making to the classification subnet, which is a multilayer perceptron (MLP). The architecture of these three subnets are described, and the associated adaptive learning algorithms are derived. The recognition results for a subset of the DARPA TIMIT speech database are reported. The correct recognition rate of the proposed ANN system is 95.5%, whereas that of the best of continuous hidden Markov model (HMM)-based systems is only 91.0%.>

A static model (SM) in the form of a single vector is proposed to represent the temporal properties of a sequence of speech feature vectors. In contrast to a hidden Markov model which captures the conditional probabilities of state transitions of consecutive observations x/sup to //sub t/ and x/sup to //sub t+1/ over time, an SM captures their average joint probabilities of belonging to a pair of phonetic classes omega /sub i/ and omega /sub j/ without any Markovian assumption. SM is tested with isolated words derived from the TIMIT database as well as artificially created words. The vocabulary is a subset of TIMIT consisting of 21 words derived from the two 'sa' sentences spoken by 420 speakers. The artificial vocabulary of 10 words is designed to study the limitations of SM. Experimental results indicate that apart from a rather mild limitation of SM in handling a certain type of vocabulary, SM actually performs better than baselined continuous hidden Markov models (CHMM) in terms of recognition rate as far as isolated word recognition is concerned, and it takes only 60% of the time needed by CHMM in recognition.>

Based on the assumption that most probability densities in real life can be approximated by a mixture of Gaussian densities, we propose here a three-layer adaptive network with each neuron in the lower hidden layer representing a Gaussian basis function (covariance matrix equal to [Formula: see text] where I is a unit matrix) to estimate various probability densities and serve as a Bayes classifier. The width of the basis function [Formula: see text] may be the same for all neurons in this layer or it may vary from one neuron to another. This paper investigates the effectiveness of the network for both cases and presents a localized learning algorithm to adjust the network parameters. The network was trained with artificial data derived from known mixtures of memoryless Gaussian sources as well as exponential and Gamma densities. The performance of the network as a pattern density estimator was measured in terms of the relative difference between the target probability density function (p.d.f.) which generates the training and testing data and the network output representing the estimation. Samples from two mixtures corresponding to two classes were used to test the network capability as a classifier by comparing its error rate against that of a Bayes classifier. Both one- and two-dimensional cases were explored. The successfulness of the network depended on how well the target p.d.f.’s were represented by the training samples, the number of hidden neurons employed in the network and how thoroughly the network was trained. It was also found that allowing each basis function to have an independent width had a predominant effect on the network performance.