A new class of A* algorithms for Viterbi phonetic decoding subject to lexical constraints is presented. This type of algorithm can be made to run substantially faster than the Viterbi algorithm in an isolated word recognizer having a vocabulary of 1600 words. In addition, multiple recognition hypotheses can be generated on demand and the search can be constrained in respect conditions on phone durations in such a way that computational requirements are substantially reduced. Results are presented on a 60000-word recognition task.>

The authors have assessed the possibility of modeling phone trajectories to accomplish speech recognition. This approach has been considered as one of the ways to model context-dependency in speech recognition based on the acoustic variability of phones in the current database. A hybrid segmental learning vector quantization/hidden Markov model (SLVQ/HMM) system has been developed and evaluated on a telephone speech database. The authors have obtained 85.27% correct phrase recognition with SLVQ alone. By combining the likelihoods issued by SLVQ and by HMM, the authors have obtained 94.5% correct phrase recognition, a small improvement over that obtained with HMM alone.>

Minimum duration constraints and energy thresholds for phonemes were used to increase the recognition accuracy of an 86000-word speaker-trained isolated word recognizer. Minimum duration constraints force the phoneme models to map to acoustic segments longer than the duration minima for the phonemes. Such constraints result in significant lowering of likelihoods of many incorrect word choices, improving the accuracy of acoustic recognition and recognition with the language model. The phoneme models were also improved by correcting the segmentation of the phonemes in the training set. During training, the boundaries between phonemes are not marked accurately. Energy is used to correct these boundaries. Application of an energy threshold improves the segment boundaries between stops and sonorants (vowels, liquids, and glides), between fricatives and sonorants, between affricates and sonorants. and between breath noise and sonorants. On two speakers, the overall reduction in errors using minimum durations and energy thresholds is from 27.3% to 23.1% for acoustic recognition and from 14.3% to 8.8% with the language model.>

The authors present a new class of A* algorithms for Viterbi phonetic decoding subject to lexical constraints. They show that this type of algorithm can be made to run substantially faster than the Viterbi algorithm in an isolated word recognizer having a vocabulary of 1600 words and that it runs very quickly on a 60000-word recognition task. In addition, multiple recognition hypotheses can be generated on demand and the search can be constrained to respect conditions on phone durations in such a way that computational requirements are substantially reduced.>

We present a new stochastic model for the energy and duration of phone segments which takes account of the speech rate, the loudness of the signal and the effects of stress and pre-pausal lengthening and we show how the block Viterbi decoding algorithm can be used to integrate it with phone-based HMM speech recognizers. The model has been implemented on an isolated-word data-base and a preliminary experiment gives a modest improvement in word recognition accuracy.

Recent results obtained with a hidden Markov model (HMM)-based acoustic recognizer using a virtually unlimited vocabulary (86000 words) to perform speaker-dependent isolated-word recognition are described. The task domain of this recognizer is quite general, consisting of paragraphs read from various newspapers, books, and magazines. The results of a comparative acoustic recognition study using various types of HMMs and various amounts of training data (from 700 to about 4000 words) are presented. The models explored include context-dependent allophonic HMMs (including generalized diphone and triphone models with unimodal Gaussian output densities) and context-independent phonemic HMMs (using either unimodal or mixture densities). Experimental results indicate that phonemic HMMs with many components in the mixture output densities provide the highest acoustic recognition accuracy. The acoustic recognition accuracy for a total of about 7000 test words spoken by four male and five female speakers is 82%. Recognition accuracy after application of the language model increases to 92%.>

The problem of using a small amount of speech data to adapt a set of Gaussian HMMs (hidden Markov models) that have been trained on one speaker to recognize the speech of another is considered. The authors experimented with a phoneme-dependent spectral mapping for adapting the mean vectors of the multivariate Gaussian distributions (a method analogous to the confusion matrix method that has been used to adapt discrete HMMs), and a heuristic for estimating covariance matrices from small amounts of data. The best results were obtained by training the mean vectors individually from the adaptation data and using the heuristic to estimate distinct covariance matrices for each phoneme.>

A novel type of hidden Markov model (HMM) has been developed to account explicitly for the context-dependent vowel acoustic transitions in consonant-vowel and vowel consonant phonetic environments. The major difference between this type of HMM and the standard Gaussian HMM is that the Gaussian mean vectors associated with the vowel HMM states, which are intended to model the vowel acoustic transitions, are set to be linearly interpolated values between those of the vowel steady state and those of the assumed locus for the adjacent consonant. The locus vectors, one for each consonant except for /h/, are trained together with all other HMM parameters using the Baum-Welch algorithm. The training procedure is fully automatic and converges to a local maximum. The model is incorporated in a phonetically based 75000-word vocabulary speech recognizer and provides a modest improvement in recognition rate over the standard approach.>

The acoustic recognizer of the INRS-Telecommunications 60000-word-vocabulary isolated-word recognition system is discussed. The task of the acoustic recognizer is to generate a list of word hypotheses and their likelihoods based on the acoustic data for each input word. Two sets of experiments are reported in which such knowledge is incorporated into the hidden Markov models (HMMs) used during recognition. In the first set, vowel duration properties are used in the HMMs. In the second set, word-initial and word-final stop consonants are modeled as a sequence of context-dependent subphonemes. The performance of the recognizer is significantly improved by appropriate utilization of the context-dependent vowel-duration information and the context-dependent microsegmental properties of stop consonants. >

Relative performance is compared for three different language models applied to the linguistic decoding part of a 75000-word speech recognizer. These models are the trigram model, the tri-POS model (POS stands for parts of speech), and a smoothed trigram model with tied distributions for words three or more syllables long. The full trigram model gives the best performance but is most expensive in terms of data and storage requirements. The smoothed trigram and tri-POS models yield equivalent performance. For general text entry tasks, use of the tri-POS model is suggested since it is less sensitive to variations in the discourse domains. For applications specific to individual discourse domains, trigram models trained on data obtained from the target domain are recommended.>

This paper proposes a new way of using vector quantization for improving recognition performance for a 60,000 word vocabulary speaker-trained isolated word recognizer using a phonemic Markov model approach to speech recognition. We show that we can effectively increase the codebook size by dividing the feature vector into two vectors of lower dimensionality, and then quantizing and training each vector separately. For a small codebook size, integration of the results of the two parameter vectors provides significant improvement in recognition performance as compared to the quantizing and training of the entire feature set together. Even for a codebook size as small as 64, the results obtained when using the new quantization procedure are quite close to those obtained when using Gaussian distribution of the parameter vectors.

This paper addresses the problem of recognizing hand-segmented vowel phonemes in isolated words pronounced by different speakers. Overcoming variation in the spectral properties of similar vowels produced by different speakers (vowel normalization) is a subproblem in the goal of large vocabulary, speaker-independent speech recognition. Two normalization techniques are compared in a series of recognition experiments on the 15 oral and nasal French vowel phonemes.

This study compares the recognition rates attainable with the aid of two different methods of generating reference templates from training words and two different decision rules. The test enviroment consists of isolated words from a small vocabulary spoken by a large number of speakers over the public telephone system. Experiments performed show that the use of individual word templates for references together with the k-nearest neighbor decision procedure substantially improves the performance in isolated word recognition. We attempted to minimize the computations involved in the k-nearest neighbor decision procedure by assuming that the dynamic time-warp distance was a metric, which would allow use of a 1-nearest neighbor decision rule with appropriately relabeled reference data. Results indicate that this step leads to an error rate exceeding that obtainable with the 1-nearest neighbor rule on the original nonrelabeled data.

An exploratory implementation of a syllable-based recognizer is described. Continuous speech is first divided into syllabic units, and the units are then matched against syllable templates using a dynamic programming algorithm. A hierarchical transition network is used to limit the syllable search to possible continuations of the current partial sentence hypotheses. Competing hypotheses are pruned by a 'beam search'. Experiments are reported on automatic recognition of English sentences with a 70-word vocabulary and restricted syntax produced by one male speaker. 85% of the sentences were correctly recognized. Comparable results were obtained for a similar task in French using a female speaker. The method is computationally efficient: real-time performance on dedicated hardware should be obtainable without difficulty. A method of scaling the distance measures used in the syllable matching is described. This scaling takes into account variability in syllable production, both as a function of position within the syllable and as a function of the various spectral parameters being used.