No abstract

No abstract

This paper focuses on user performance with word predic-Absstract-This study analyzes user performance of text entry tasks with word prediction by applying modeling techniques developed in the field of human-computer interaction. Fourteen subjects transcribed text with and without a word prediction feature for seven test sessions. Eight subjects were able-bodied and used mouthstick typing, while six subjects had high-level spinal cord injuries and used their usual method of keyboard access. Use of word prediction decreased text generation rate for the spinal cord injured subjects and only modestly enhanced it for the able-bodied subjects. This suggests that the cognitive cost of using word prediction had a major impact on the performance of these subjects. Performance was analyzed in more detail by deriving subjects' times for keypress and list search actions during word prediction use. All subjects had slower keypress times during word prediction use as compared to letters-only typing, and spinal cord injured subjects had much slower list search times than able-bodied subjects. These parameter values were used in a two-parameter model to simulate subjects' word entry times during word prediction use, with an average model error of 16%. These simulation results are an encouraging first step toward demonstrating the ability of analytical models to represent user performance with word prediction. I. BACKGROUNDOMPUTER-BASED augmentative and alternative com-C munication (AAC) systems provide people who have severe disabilities with the opportunity to communicate independently in the areas of speech, writing, and computer applications. A major goal in the design and prescription of these systems is to provide the user with the fastest means of communication possible. A variety of techniques designed to enhance user performance are currently used in AAC systems, including word abbreviations [ 11, [2], message encoding [3], [4], and word prediction [5], [6]. There continues to be a need for greater understanding of the efficacy of these systems.A primary aim in most rate enhancement approaches is to reduce the motor requirements placed on the user. This is clearly an important goal, since the vast majority of users have severe physical impairments. However, a frequent consequence of reducing motor requirements is to increase the cognitive and perceptual loads on the user 141, [7], [SI. The net balance of this trade-off determines whether the user's overall performance will be enhanced or inhibited with a system [9].

This study examines how the cognitive and perceptual loads introduced by a word prediction feature impact learning and performance. Two groups of able-bodied subjects transcribed text using two row-column scanning systems for 10 consecutive trials each. The two systems differed only in that one system had a word prediction feature. Subject groups differed in their order of system use. The results show that, under the conditions of this study, the word prediction system was not substantially more difficult to learn, but it did not yield a statistically significant improvement in text generation rate. This suggests that the cost of using this word prediction system balanced the benefit of the keystroke savings achieved by these subjects. The relationship between keystroke savings, cost in item selection rate, and improvement in text generation rate is explored in order to provide insight into this outcome.

This paper presents a variety of outcomes data from 24 experienced users of automatic speech recognition (ASR) as a means of computer access. To assess usage and satisfaction, we conducted an in-person survey interview. For those participants who had a choice of computer input methods, 48% reported using ASR for 25% or less of their computer tasks, while 37% used ASR for more than half of their computer tasks. Users' overall satisfaction with ASR was somewhat above neutral (averaging 63 out of 100), and the most important role for ASR was as a means of reducing upper-limb pain and fatigue. To measure user performance, we asked users to perform a series of word processing and operating system tasks with their ASR systems. For 18 of these users, performance without speech was also measured. The time for nontext tasks was significantly slower with speech (p < 0.05). The average rate for entering text was no different with or without speech. Text entry rate with speech varied widely, from 3 to 32 words per minute, as did recognition accuracy, from 72% to 94%. Users who had the best performance tended to be those who employed the best correction strategies while using ASR.