This paper reports recent efforts to apply the speaker-independent SPHINX-H system to the DARPA Wall Street Journal continuous speech recognition task. In SPHINX-H, we incorporated additional dynamic and speaker-normalized features, replaced discrete models with sex-dependent semi-continuous hidden Markov models, augmented within-word triphones with between-word triphones, and extended generali...

We propose an online learning algorithm for large margin training of continuous density hidden Markov models. The online algorithm updates the model parameters incrementally after the decoding of each training utterance. For large margin training, the algorithm attempts to separate the log-likelihoods of correct and incorrect transcriptions by an amount proportional to their Hamming distance. W...

to low error rates occurs faster and yields (in the average) better models. If the mean vectors of the multivariate Gaussian density functions are placed according to the clusters organized by SOMs, only a couple of iterations of maximum likelihood estimation is required to set suitable values to the other CDHMM parameters. The LVQ was used to get more discrim-inative clustering but it seems th...

This paper presents the results of the comparison of continuous and discrete density Hidden Markov Models (HMMs) used for cursive handwriting recognition. For comparison, a subset of a large vocabulary (1000 word), writer-independent online handwriting recognition system for word and sentence recognition was used, which was developed at Duisburg University. This system has some unique features ...

We extend our previously proposed quasi-Bayes adaptive learning framework to cope with the correlated continuous density hidden Markov models (HMM’s) with Gaussian mixture state observation densities in which all mean vectors are assumed to be correlated and have a joint prior distribution. A successive approximation algorithm is proposed to implement the correlated mean vectors’ updating. As a...

This work presents an Offline Cursive Word Recognition System dealing with single writer samples. The system is based on a continuous density Hiddden Markov Model trained using either the raw data, or data transformed using Principal Component Analysis or Independent Component Analysis. Both techniques significantly improved the recognition rate of the system. Preprocessing, normalization and f...

In this paper, we propose a new approach to online adaptation of continuous density hidden Markov model (CDHMM) based on speaker space model evolution. The speaker space model which characterizes the a priori knowledge of the training speakers is effectively described in terms of the latent variable model such as the factor analysis (FA) or probabilistic principal component analysis (PPCA). The...

An algorithm is described for modelling and recognising temporal structures of visual activities. The method is based on (1) learning prior probabilistic knowledge using Hidden Markov Models, (2) automatic temporal clustering of hidden Markov states based on Expectation Maximisation and (3) using observation augmented conditional density distributions to reduce the number of samples required fo...