Andrew C. Morris

Learn More
We address the theoretical and practical issues involved in ASR when some of the observation data for the target signal is masked by other signals. Techniques discussed range from simple missing data imputation to Bayesian optimal classification. We have developed the Bayesian approach because this allows prior knowledge to be incorporated naturally into(More)
In this paper, we develop di€erent mathematical models in the framework of the multi-stream paradigm for noise robust automatic speech recognition (ASR), and discuss their close relationship with human speech perception. Largely inspired by Fletcher's ``product-of-errors'' rule (PoE rule) in psychoacoustics, multi-band ASR aims for robustness to data(More)
In this report we investigate and compare di erent subband based Automatic Speech Recognition ASR approaches including an original approach referred to as the full combination approach based on an estimate of the noise weighted sum of posterior probabilities for all possible subband combinations We show that the proposed estimate is a good approximation of(More)
1. Introduction Possible application of the missing data techniques to the problem of robust speech recognition was my area of interest in the last six months. In the following sections, some of the problems of robustness in speech recognition, proposed techniques for dealing with and missing data approach will be described. Ways for extension of missing(More)
Current technology for automatic speech recognition (ASR) uses hidden Markov models (HMMs) that recognize spoken speech using the acoustic signal. However, no use is made of the causes of the acoustic signal: the articulators. We present here a dynamic Bayesian network (DBN) model that utilizes an additional variable for representing the state of the(More)
OBJECTIVES Ventilator-associated pneumonia is the most common intensive care unit-acquired infection. Although there is widespread consensus that evidenced-based interventions reduce the risk of ventilator-associated pneumonia, controversy has surrounded the importance of implementing them as a "bundle" of care. This study aimed to determine the effects of(More)
The word error rate (WER), commonly used in ASR assessment, measures the cost of restoring the output word sequence to the original input sequence. However, for most CSR applications apart from dictation machines a more meaningful performance measure would be given by the proportion of information communicated. In this article we introduce two new absolute(More)
The activity of a yeast recombinase, FLP, on specific target DNA sequences, FRT, has been demonstrated in embryos of the vector mosquito, Aedes aegypti. In a series of experiments, plasmids containing the FLP recombinase under control of a heterologous heat-shock gene promoter were co-injected with target plasmids containing FRT sites into preblastoderm(More)
The performance of most ASR systems degrades rapidly with data mismatch relative to the data used in training. Under many realistic noise conditions a significant proportion of the spectral representation of a speech signal, which is highly redundant, remains uncorrupted. In the “missing feature” approach to this problem mismatching data is simply ignored,(More)