In the paper a method of optimal selection of utterances used as command entry-words for voice controlled application is presented. Voice controlled programs seem to be particularly useful in the area of medical informatics, where a physician interacts with a program by voice while operating the medical device or being involved in examinations requiring manual activities. The proposed method selects command words from sets of proposals defined for each command so as to minimize the overall probability of incorrect command recognition. First the entry-word dissimilarity matrix is calculated. The word dissimilarities are evaluated using HMM models consisting of appropriately trained acoustic models of the phonemes constituting words. The trained HMM is used as the sample utterance generator for the word. The artificially created utterance samples are then recognized by speech recognizers created for pairs of words. The estimation of correct recognition probability is used as the word dissimilarity measure. The word dissimilarities are then used to determine the average assessment of words selections that can be used as commands. Selection is created by choosing single word from sets of candidates defined for each command. Finally, suboptimal selection is found by using genetic algorithm. Experiments carried out prove that suboptimal selection of command entry-words can observably increase the accuracy of spoken commands recognition in many cases.
The paper presents an attempt to automatic speech recognition of Polish spoken medical texts. The attempt resulted in experimental system that can be used as a tool for practical applications. The system uses a typical recognition method based on Hidden Markov Model and domain-specific language model. Implemented software made it possible to conduct many experiments aimed on evaluation of the assumed approach usefulness. Obtained experiment results are presented and analyzed. The system architecture and the way in which it can be integrated with hospital information systems is also exposed.
Governments across the world are launching ambitious and expensive initiatives related to health care information systems and information systems strategies that use IT as the basis for improving the health care of patients. Computer-based hospital information systems (HISs) are expensive, e.g. a typical HIS for a large hospital is estimated to cost some $50m, i.e. 140m PLN [21]. In contrast, the benefits that result from an information system - in health care or in other business sectors - have rarely been measured [9]. The National Health Service in the UK has embarked on a huge initiative, namely The National Programme for IT in the NHS (NPfIT), costing some £12.4 billion (70bn PLN) over 10 years to 2013-2014. Hospital information systems have evolved over the last three decades. Has this evolution allowed us to gain knowledge of, and understand, the problems and obstacles of HISs and their implementation? Have we a corresponding knowledge of how to achieve success and minimise failure in HIS implementations? In this context, this paper examines the NPfIT, the problems it has experienced and the successes it has achieved, in order to extract lessons from these experiences that might benefit future information and communication technology (ICT) implementations in health care.
In the paper the concept, main design problems, applied solutions and some implementation details of a hospital information system based on handheld computers are presented. Increasing power and low prices of handheld computers make it very convenient tool for mobile information systems in medicine and health care. Permanent availability of patients data to nursing personnel and physicians at the patient’s bed make medical decision making easier, more accurate, reduces the risk of mistakes, eliminates unnecessary paper works and provides more up-to-date information. The purpose of the system being described here is to utilize all these advantages of mobile computing at the relatively low costs of hardware and software.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.