Text Entry Rate Research Articles

Word Prediction System for Text Entry in Hindi

Word prediction is treated as an efficient technique to enhance text entry rate. Existing word prediction systems predict a word when a user correctly enters the initial few characters of the word. In fact, a word prediction system fails if the user makes errors in the initial input. Therefore, there is a need to develop a word prediction system that predicts desired words while coping with errors in initial entries. This requirement is more relevant in the case of text entry in Indian languages, which are involved with a large set of alphabets, words with complex characters and inflections, phonetically similar sets of characters, etc. In fact, text composition in Indian languages involves frequent spelling errors, which presents a challenge to develop an efficient word prediction system. In this article, we address this problem and propose a novel word prediction system. Our proposed approach has been tried with Hindi, the national language of India. Experiments with users substantiate 43.77% keystroke savings, 92.49% hit rate, and 95.82% of prediction utilization with the proposed word prediction system. Our system also reduces the spelling error by 89.75%.

Method for enhancing text entry rate with single-switch scanning.

Single-switch scanning is a technique used by some individuals for spoken and/or written communication. We developed a method for adjusting the settings in a single-switch scanning interface to increase a user's text entry rate (TER). We evaluated that method with nine individuals who use single-switch scanning to communicate. Text entry rates improved by an average of 120% (p = 0.003). All nine subjects increased their TER by at least 40%, and five of the nine increased their TER by over 100%. At baseline, TER averaged 1.42 words per minute (wpm), ranging from 0.28 to 2.92 wpm. With the revised settings, TER averaged 2.72 wpm and ranged from 1.12 to 6.51 wpm.

Analysis on User Errors in Virtual Keyboards

With the advancement of information and communication technology, the task of text composition is increasing exponentially. However, the text composition task in users' native languages remains an issue, particularly with QWERTY keyboard. As an alternative to this QWERTY keyboard, user interface designers advocate virtual keyboards. Nevertheless, designing an efficient and robust virtual keyboard becomes another issue. The traditional approach to measure the effectiveness of a virtual keyboard is the text entry rate. The user errors, which are very important, have been either grossly ignored or accomplished with ad-hoc user testing. In fact, user errors should be taken into account to evaluate a design along with text entry rate. This paper proposes an way to identify virtual keyboard design parameters which affect the user errors during text composition. Outcome of this research would be helpful to develop a computational model to predict user errors on the basis of virtual keyboard design parameters.

Text Entry by Gazing and Smiling

Face Interface is a wearable prototype that combines the use of voluntary gaze direction and facial activations, for pointing and selecting objects on a computer screen, respectively. The aim was to investigate the functionality of the prototype for entering text. First, three on-screen keyboard layout designs were developed and tested (n=10) to find a layout that would be more suitable for text entry with the prototype than traditional QWERTY layout. The task was to enter one word ten times with each of the layouts by pointing letters with gaze and select them by smiling. Subjective ratings showed that a layout with large keys on the edge and small keys near the center of the keyboard was rated as the most enjoyable, clearest, and most functional. Second, using this layout, the aim of the second experiment (n=12) was to compare entering text with Face Interface to entering text with mouse. The results showed that text entry rate for Face Interface was 20 characters per minute (cpm) and 27 cpm for the mouse. For Face Interface, keystrokes per character (KSPC) value was 1.1 and minimum string distance (MSD) error rate was 0.12. These values compare especially well with other similar techniques.

Bengali text input interface design for mobile devices

Text entry has become one of the most frequent activities performed using mobile devices such as PDAs. Virtual keyboards (VK), which allow text to be entered by tapping keys displayed on the screen, are among the predominant mode of text input for such devices. It is important to design VK layouts in a way such that the users can achieve high text entry speed with high accuracy. Several layouts, primarily in English and also in some other languages, have been proposed to achieve the twin objectives. However, no such work has been reported for Bengali, the second and fifth most popular language of India and the world, respectively. The existing methods cannot be applied directly to Bengali VK design due to the problem of accommodating the large Bengali alphabet (more than 60 characters) on a small display area. In order to resolve the resulting usability-performance trade-off, this paper proposes a two-level design. Five two-level VKs representing three design paradigms (alphabetic, frequency-based and adaptive) have been designed and compared in an empirical study. The study results show that for mobile devices, the two-level adaptive design is expected to give best performance in terms of text entry rate and accuracy. The layouts as well as the procedure and results of the study are discussed in this paper.

Text Entry via Character Stroke Disambiguation for an Adolescent With Severe Motor Impairment and Cortical Visual Impairment

ABSTRACT This study proposed a single-switch text entry system by hierarchical scanning of character strokes for an 11-year-old girl with severe physical disabilities and low vision. She could only perceive magnified straight line segments and chords presented against high-contrast, colored backgrounds. In a descriptive case study, the participant used the proposed system in the community for 8 months. Assessment included theoretical evaluation of text entry performance and empirical evaluation of the participant's proficiency. The proposed system had a lower error-free text entry rate but comparable proneness to user error as a real-world implementation of row-column virtual scanning keyboard with character frequency layout. The participant's proficiency, in terms of mean number of single-switch activations and time to type one character, showed statistically significant improvements as the case study progressed. The proposed system feasibly addressed the participant's typing needs, in a context where traditional row-column scanning and codeword-based text entry systems were not successful.

SAK

The design and evaluation of a scanning ambiguous keyboard (SAK) is presented. SAK combines the most demanding requirement of a scanning keyboard—input using one key or switch—with the most appealing feature of an ambiguous keyboard—one key press per letter. The optimal design requires just 1.713 scan steps per character for English text entry. In a provisional evaluation, 12 able-bodied participants each entered 5 blocks of text with the scanning interval decreasing from 1100 ms initially to 700 ms at the end. The average text entry rate in the 5 th block was 5.11 wpm with 99% accuracy. One participant performed an additional five blocks of trials and reached an average speed of 9.28 wpm on the 10 th block. Afterwards, the usefulness of the approach for persons with severe physical disabilities was shown in a case study with a software implementation of the idea explicitly adapted for that target community.

BlinkWrite: efficient text entry using eye blinks

In this paper, a new text entry system is proposed, implemented, and evaluated. BlinkWrite provides a communication gateway for cognitively able motor-impaired individuals who cannot use a traditional eye-tracking system. In contrast to most hands-free systems, BlinkWrite allows text to be entered and corrected using a single input modality: blinks. The system was implemented using a scanning ambiguous keyboard, a new form of scanning keyboard that allows English text to be entered in less than two scanning intervals per character. In a user study, 12 participants entered text using the system with three settings for scanning interval: 1,000, 850, and 700 ms. An average text entry rate of 4.8 wpm was observed with accuracy >97%. The highest average text entry rate was achieved with the scanning interval of 850 ms.

Text Entry in the E-Commerce Age: Two Proposals for the Severely Handicapped

People with severe motor disabilities have extreme access difficulties with all kinds of web services especially when they want not only to surf the web, but also write some text, e.g., to participate in an e-activity. Several problems arise when using traditional scanning systems, such as the low text entry rate, the time consuming task of learning the scan matrix layout, or simply, the poor visibility of the web page due to the large surface needed to display the complete scan matrix on the screen. We propose a reduced virtual keyboard based on scanning with only one switch as input device. The scan matrix consists of only three cells, so ambiguity is present due to the assignment of 26 characters to the three keys. Word-level and character-level disambiguation modes are explored using a mathematical model, and the text entry rates for an expert user were 15.9 and 10.3 words per minute respectively, using a scan period of 0.5 seconds. This keyboard could be embedded into a web page using a Java applet, JavaScript code or a Flash application, or be programmed as an independent application.

Toward automatic adjustment of keyboard settings for people with physical impairments

Purpose. We are developing a software system called IDA (Input Device Agent), whose goal is to optimally configure input devices for people with physical impairments. This study assessed IDA's ability to recommend three keyboard parameters in response to measurements of typing performance: repeat rate, repeat delay, and use of StickyKeys.Method. Twelve typists with physical impairments participated. The study employed a repeated measures design. Each participant typed six sentences in each of four keyboard conditions: default settings, IDA-recommended repeat settings, StickyKeys On, and a repeat of default settings.Results. Two participants had significant problems with inadvertent key repeats, when using the default repeat settings. For those two participants, use of the IDA-recommended repeat settings reduced the number of repeated characters by 96% and significantly improved text entry rate and typing accuracy. IDA recommended StickyKeys for six participants, each of whom had at least one problem related to modifying keys without StickyKeys. Use of StickyKeys for these individuals eliminated their modifier-related errors and significantly improved typing speed. IDA did not recommend StickyKeys for the six participants who demonstrated no need for it.Conclusions. The results indicate that IDA can provide useful assistance with repeat settings and StickyKeys.

Factors That Influence the Performance of Experienced Speech Recognition Users

Performance on automatic speech recognition (ASR) systems for users with physical disabilities varies widely between individuals. The goal of this study was to discover some key factors that account for that variation. Using data from 23 experienced ASR users with physical disabilities, the effect of 20 different independent variables on recognition accuracy and text entry rate with ASR was measured using bivariate and multivariate analyses. The results show that use of appropriate correction strategies had the strongest influence on user performance with ASR. The amount of time the user spent on his or her computer, the user's manual typing speed, and the speed with which the ASR system recognized speech were all positively associated with better performance. The amount or perceived adequacy of ASR training did not have a significant impact on performance for this user group.

Speech-Based Text Entry for Mobile Handheld Devices: An Analysis of Efficacy and Error Correction Techniques for Server-Based Solutions

As handheld devices become ubiquitous and the tasks performed become multipurpose in nature, efficient data entry techniques are necessary. This research evaluated several speech-based text entry solutions for handheld devices using server-based speech recognition. Because server-based solutions introduce network delays, an analysis of the relationship among network delays, number of recognition errors, how fast users can correct errors, and overall data entry rates was performed. The analysis and empirical results confirm the importance of minimizing recognition errors. This suggests that a server-based approach that makes more computing resources available may prove effective. Results from two empirical studies are presented. The first compares two error correction mechanisms: a multitap and soft keyboard solution. The second employs a longitudinal investigation of the effects of experience on text entry rates. Users attained an effective mean text entry rate as high as 25.3 words per min, which is higher than or comparable to data entry rates reported for other input techniques for handheld devices. The results of this research have implications for researchers and designers of automatic speech recognition systems and mobile devices.

Input Rates for a One-Handed Input Device (OHAI) for Chinese Text Entry

As computer technology has become ubiquitous in nature, designers must develop text-entry methods that can accommodate a variety of devices, cultures, and languages. This paper presents a study evaluating a One-HAnded Input (OHAI) device developed for mobile text-entry in Chinese. The device is a chorded keyboard system on which text is entered in Chinese using the pinyin system. Participants trained with the device for 10, 1-hour sessions. Their text-entry rates and their rate of input for individual chords were measured after each session. The Power Law of Practice was used to predict input rates after 100 hours of training. Predicted input rates approximate 16 characters per minute, approaching pinyin input rates on conventional keyboards. Input rates for individual chords were also measured in order that future iterations of the software may associate the most commonly used characters with the fastest-to-execute chords. The study also suggests several potential future improvements to the OHAI system, such as augmenting the software with an autocompletion system.

Usage, performance, and satisfaction outcomes for experienced users of automatic speech recognition

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.

An empirical investigation of the novice experience with soft keyboards

An experiment with 12 participants tested text entry rates on two sizes of soft keyboards with either a Qwerty layout or a layout presenting a randomized letter arrangement after each tap. The randomized layout simulated the novice experience by requiring users to visually scan the layout for each tap to find the intended letter. Rates for the Qwerty layouts were about 20 wpm with no significant difference between the large and small size. Rates for both sizes of the randomized layouts were very low, about 5.4 wpm. This is the expected walk-up text entry rate with a soft keyboard bearing an unfamiliar layout. This empirical result allows us to reject a previous model of novice interaction that used Fitts' law for stylus movement and the Hick-Hyman law for visual scan time.

Adaptive one-switch row-column scanning.

Row-column scanning is a very slow method of communication. Options for increasing text entry rate include 1) dynamically changing the configuration of the row-column matrix or 2) using rate-enhancement techniques like word prediction, but evidence suggests that increased cognitive load imposed by these methods on the user can result in little or no improvement in text generation rate. An alternative we are investigating is adapting a system's scan delay during run-time. Our goal is to allow a scanning system to adjust its parameters "on the fly" (as opposed to the current practice of setting parameters during clinical assessments). This paper describes the evolution of a one-switch row-column scanning system that adapts its scan rate based on measurements of user performance. Two experiments have been performed to explore the effects of automatically adapting scan delay on users' text entry rate. Our results indicate that automatic adaptation has the potential to enhance text-entry rate without increasing task complexity.

Text entry using soft keyboards

Text entry rates are explored for several variations of soft keyboards. We present a model to predict novice and expert entry rates and present an empirical test with 24 subjects. Six keyboards were examined: the Qwerty, ABC, Dvorak, Fitaly, JustType, and telephone. At 8-10 wpm, novice predictions are low for all layouts because the dominant factor is the visual scan time, rather than the movement time. Expert predictions are in the range of 22-56 wpm, although these were not tested empirically. In a quick, novice test with a representative phrase of text, subjects achieved rates of 20.2 wpm (Qwerty), 10.7 wpm (ABC), 8.5 wpm (Dvorak), 8.0 wpm (Fitaly), 7.0 wpm (JustType), and 8.0 wpm (telephone). The Qwerty rate of 20.2 wpm is consistent with observations in other studies. The relatively high rate for Qwerty suggests that there is skill transfer from users' familiarity with desktop computers to the stylus tapping task.

Theoretical upper and lower bounds on typing speed using a stylus and a soft keyboard

Abstract A theoretical model is presented to predict upper-and lower-bound text-entry rates using a stylus to tap on a soft QWERTY keyboard. The model is based on the Hick-Hyman law for choice reaction time, Fitts law for rapid aimed movements, and linguistic tables for the relative frequencies of letter-pairs, or digrams, in common English. The model's importance lies not only in the predictions provided, but in its characterization of text-entry tasks using keyboards. Whereas previous studies only use frequency probabilities of the 26 × 26 digrams in the Roman alphabet, our model accommodates the space har—the most common character in typing tasks. Using a very large linguistic table that decomposes digrams by position-within-words, we established start-of-word (space-letter) and end-of-word (letter-space) probabilities and worked from a 27 × 27 digram table. The model predicts a typing rate of 8.9wpm for novices unfamiliar with the QWERTY keyboard, and 30.1wpm for experts. Comparisons are drawn with empirical studies using a stylus and other forms of text entry.

Customised text entry devices for motor-impaired users

The standard QWERTY keyboard is the principal text entry device for word processing and computer-based communications. For many motor-impaired individuals, and in particular those without intelligible speech, the low text entry rates they can typically achieve is a major problem. For some, the QWERTY design is completely inappropriate. Alternative designs that can appreciably increase these rates would greatly enhance their ability to communicate. This paper considers and compares several approaches to the design of text entry devices for motor-impaired users. A general method for customising (i e, optimising) these designs is employed, and consideration is given to designs requiring significantly fewer input switches than the 26 or more keys required by QWERTY. Use is made of language statistics in the design procedure, and the increased availability of inexpensive, powerful computers is directly exploited.

Reduced Keyboard Designs Using Disambiguation

There are a number of important applications where the accuracy of typed copy is less important than other criteria, such as the speed of entry, ease of learning, reduced keyboard size, provision for innovative keyboard designs and work methods, etc. Some of these applications include communication devices for the motor handicapped and rough drafting. The applications in question still provide single finger typing as opposed to multifinger entries for chord keyboards. One approach to keyboard design for such applications involves using a multicharacter key set. Because there is more than one character on a key, the number of keys can be reduced to a point limited only by the required accuracy of the text produced which is itself limited by the ability of “disambiguation” algorithms to decode the ambiguous text strings. Reducing the number of keys increases text entry rates and reduces learning time. Experiments with keysets of 10, 12, 14, and 16 keys have produced keystroke rates of 3.3 to 1.7 characters per second and a 6% keying error while the disambiguation programs can produce an accuracy of 85 to 95%. Learning time in the experiments was about 9 to 12 minutes. The experiments demonstrate the feasibility of increasing text entry rates and freeing the keyboard from architectural constraints.