Adam J. Sporka

Non-speech input and speech recognition for real-time control of computer games

This paper reports a comparison of user performance (time and accuracy) when controlling a popular arcade game of Tetris using speech recognition or non-speech (humming) input techniques. The preliminary qualitative study with seven participants shows that users were able to control the game using both methods but required more training and feedback for the humming control. The revised interface, which implemented these requirements, was positively responded by users. The quantitative test with 12 other participants shows that humming excelled in both time and accuracy, especially over longer distances and advanced difficulty levels.

Whistling User Interface (U3I)

The paper describes the design, implementation and user evaluation of a system that allows a user to control a mouse pointer through whistling or humming. The pointer can be controlled in two ways: orthogonally (the pointer can only move with variable speed either horizontally or vertically at a time) and melodically (the pointer can move with fixed speed in any direction). The user study indicates that the users thought the orthogonal control was easier to operate than the melodic control. The orthogonal control was considered useful for controlling mouse movement while the melodic control was more useful for entertainment purposes. Humming was considered less tiring than whistling. This study makes several contributions to the field. First, it is perhaps the first published study investigating the use of whistling to operate a mouse pointer. Second, the system can be used as a low-cost alternative pointing device for people with motor disabilities.

A comparative study on distant free-hand pointing

In this paper we present a comparative study of free-hand pointing, an absolute remote pointing device. Unimanual and bimanual interaction were tested as well as the static reference system (spatial coordinates are fixed in the space in front of the TV) and novel body-aligned reference system (coordinates are bound to the current position of the user). We conducted a point-and-click experiment with 12 participants. We have identified the preferred interaction areas for left- and right-handed users in terms of hand preference and preferred spatial areas of the interaction. In bimanual interaction, the users relied more on dominant hand, switching hands only when necessary. Even though the remote pointing device was faster than the free-hand pointing, it was less accepted probably due to its low precision.

Longitudinal study of continuous non-speech operated mouse pointer

This paper reports a longitudinal study of a non-speech input-controlled continuous cursor control system: Whistling User Interface (U3I). This study combines quantitative (target acquisition tasks, subjective ratings and a simple reaction time test) and qualitative (interview) methods to arrive at a more nuanced understanding novice users. experience over time. The progress of training of ten participants has been observed. The study shows that the performance improved over time and plateaued on day four of the five days of the study.

Tangible newspaper for the visually impaired users

This paper outlines a novel interaction technique allowing the visually impaired users to examine the layout of complex paper documents (e.g. a newspaper page). The document is placed on a desk in the view of a camera placed above it. The tip of users index finger is tracked by means of algorithms of computer vision. As the user moves the finger over the document, the layout of its logical units (articles) is revealed by means of a simple sonification of their boundaries and the speech synthesis. In the paper, implementation of the test application is described and evaluated. The main advantage of our system is the direct mapping of the kinaesthetic experience to the layout of the physical document, enabling the user to employ any strategy to traverse the document. The prototype has been implemented using the ARToolKit library.

Comparison of two text entry methods on interactive TV

This paper describes a study with 18 participants on two text input methods for use with interactive television, The Numpad Typer (TNT) and TwiceTap. Both methods were designed for use with a common infra-red remote control. Each character is entered using two keystrokes. After one hour and forty minutes of practice, split into 5 sessions, the participants were able to type faster than 9 words per minute. While the performance of both methods was similar, the TwiceTap required a smaller number of keystrokes per character, was less prone to errors, and was found to be more comfortable by the participants. Over time, the use of frequent n-grams in TwiceTap was reinforced while the use of infrequent n-grams was suppressed.

Haptic and Spatial Audio Based Navigation of Visually Impaired Users in Virtual Environment Using Low Cost Devices

The use of haptic peripherals to mediate spatial information to visually impaired users is a problem which has recently been examined thoroughly, however the main issue of almost all current approaches is the use of custom made peripheral devices, the high cost of which renders their massive deployment infeasible. We have focused on using low-cost haptic devices to allow visually impaired users to navigate in and inspect a virtual environment. In this paper we describe our approach to navigation in virtual environments by using force feedback joystick and haptic mouse. We also employ the spatial sound to enhance the information perception. We discuss two different navigation modes of avatar in the virtual environment (joystick and mouse based) and several information mediation techniques. Numerous tests have also been performed. Results show that the efficiency and usability of our solution is comparable with tactile exploration of physical paper models of an environment.

Humsher: a predictive keyboard operated by humming

This paper presents Humsher -- a novel text entry method operated by the non-verbal vocal input, specifically the sound of humming. The method utilizes an adaptive language model for text prediction. Four different user interfaces are presented and compared. Three of them use dynamic layout in which n-grams of characters are presented to the user to choose from according to their probability in given context. The last interface utilizes static layout, in which the characters are displayed alphabetically and a modified binary search algorithm is used for an efficient selection of a character. All interfaces were compared and evaluated in a user study involving 17 able-bodied subjects. Case studies with four disabled people were also performed in order to validate the potential of the method for motor-impaired users. The average speed of the fastest interface was 14 characters per minute, while the fastest user reached 30 characters per minute. Disabled participants were able to type at 14 -- 22 characters per minute after seven sessions.

Text input for motor-impaired people

This paper provides an overview of 150 publications regarding text input for motor-impaired people and describes current state of the art. It focuses on common techniques of text entry including selection of keys, approaches to character layouts, use of language models, and interaction modalities. These aspects of text entry methods are further analyzed, and examples are given. The paper also focuses on an overview of reported evaluations by describing experiments, which can be conducted, to assess the performance of a text entry method. Following this overview, a summary of 61 text entry methods for motor-impaired people found in the related literature is presented, classifying those methods according to the aforementioned aspects and reported evaluation. This overview was assembled with the aim to provide a starting point to the new researchers in the field of accessible text entry. The text entry methods are also categorized according to the suitability for various conditions of the users.

Vocal interaction

Vocal interaction research has slowly been gaining popularity in the mainstream HCI, assistive technology, arts and game development communities. One main reason for the uptake of this interaction style is the potential of exploiting one of the most natural means of expression: human vocalizations, speech, and vocal gestures. This SIG meeting has three purposes: to communicate the results of the CHI 2007 workshop on vocal interaction to interested CHI attendees; to sketch a research agenda on the topic of the emerging interaction styles in the context of vocal interaction and its implications for the design of interactive systems; and to bring together the communities of researchers and practitioners who are addressing this topic.