![]() ![]() To achieve this goal, we studied the reaching of targets with 1 dimension. The objective is to propose a modeling of motor performances (and eventually perceptual performances) of our study population to predict the time necessary to move and to research targets. This study have a double issue (theoretical and technological interest): the understanding of the motor deficiencies and the design of systems (such as virtual keyboards) based on interaction techniques of pointing. Thus, to understand and describe the motor deficiencies, we need to study the motor activity by applying the psychomotor law. On the contrary, other studies show the benefits of optimizing the layout of the keys for the text input, under conditions of mobility for the OPTI and Metropolis keyboard and in office situation for the GAG keyboard. This reduction of speed is also observed during text input activity by disabled people with the UKO ambiguous keyboard. The studies on able-bodies showed that the text input is faster with physical AZERTY keyboard (75 Words Per Minute) than with virtual AZERTY keyboard with pointing (25 Words Per Minute). Systems can additionally be categorised as those that are speaker dependent or independent and those that deal with limited vocabularies as opposed to those that try to recognise the whole of the specified language. The majority have been developed for the English language although there are several speech engines that have been developed for other languages (Peissner, 2002). There are several commercially available voice recognition systems such as Dragon Naturally speaking (Nuance, 2006) and IBM ViaVoice (IBM, 2006). The creation of speaker-independent, speech-enabled interface systems for mobile applications, are thus likely to be of increasing benefit to users. Voice is a natural interface that the majority of people are capable of using without any technical training. There are many reasons for this new focus but according to (Holmes, 2001), one of the main reasons is the recent introduction of reasonably effective speaker independent speech recognition technologies. Examples are use by the police (Cohen, 2005) and by medical staff (Baumgart, 2005) and (Moffett, 2003). there are limits on its accuracy, and strategies that can improve performance are discussed Introduction In recent years, the use of speech and natural language interface technologies have shown great promise for significantly improving the usability of many mobile computer based applications. there are limits on its accuracy, and strategies that can improve performance are discussed. At present there are limits on its accuracy, and strategies that can improve performance are discussed. As a first step, an application has been built to recognise code words for the letters of the Arabic alphabet and it has been evaluated on 30 Arabic speakers. Although it is recognised that speech engines that are designed specifically for Arabic would have better recognition rates, using this approach would enable mixed language systems to be built, which is a typical requirement for medical applications in the Arabic world where much of the technical lan-guage is English but names of patients and other information is in Arabic. This paper reports on research that is designed to evaluate the use of commercially available, English based speech engines, to recognise limited Arabic vocabularies. The results of these studies suggest that it would be worthwhile to develop a working voice-spelling system for PDAs in the future. This paper describes several User-Centered Design studies conducted to develop a voice-spelling alphabet for PDAs that overcomes these problems, including: (1) the development of a model of user performance to assess the potential of voice spelling as an alternate input method for PDAs, (2) Web-based surveys for determining the words that people tend to associate with the letters of the alphabet, (3) accuracy experiments used to tune the final voice-spelling alphabet, and (4) the development of a graphical user interface for displaying code words as a prompt when voice spelling is used. ![]() ![]() Voice-spelling problems include the high acoustic confusability between certain letters of the alphabet and the difficulty of memorizing code words for the letters of the alphabet. PDAs do not yet have the power to support full speech dictation, but they do have sufficient power to support voice spelling. The best current solutions to the problem are small soft keyboards and constrained handwriting recognizers. A persistent problem with personal digital assistants (PDAs) is the difficulty of entering data into the devices. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |