Melanie Baljko

Indirect text entry using one or two keys

This paper introduces a new descriptive model for indirect text composition facilities that is based on the notion of a containment hierarchy. This paper also demonstrates a novel, computer-aided technique for the design of indirect text selection interfaces -- one in which Huffman coding is used for the derivation of the containment hierarchy. This approach guarantees the derivation of optimal containment hierarchies, insofar as mean encoding length. This paper describes an empirical study of two two-key indirect text entry variants and compares them to one another and to the predictive model. The intended application of these techniques is the design of improved indirect text entry facilities for the users of AAC systems.

CanSpeak: a customizable speech interface for people with dysarthric speech

Current Automatic Speech Recognition (ASR) systems designed to recognize dysarthric speech require an investment in training that involves considerable effort and must be repeated if speech patterns change. We present CanSpeak, a customizable speech recognition interface that does not require automatic training and uses a list of keywords customized for each user. We conducted a preliminary user study with four subjects with dysarthric speech. Customizing the keyword lists doubled the accuracy rate of the system for two of the subjects whose parents and caregivers participated in the customizing task. For the other two subjects only small improvements were observed.

The aesthetics of emergence: Co-constructed interactions

In this article, we describe the aesthetics of emergence, which is our theoretical framework for an aesthetics of interaction and the underpinning of LoFi, an interactive A-life artwork that we are developing. We provide a survey of relevant concepts from the A-life and new media research communities, and we establish threads of commonalities with the HCI research community and especially the subset of that community that emphasizes aspects of user experience other than those that are characterized by performance-based measures. We describe and discuss several exemplar A-life artworks that are drawn from the last decade of jury selections of the annual Vida Art and Artificial Life Competition, conducted by Fundación Telefonica. We conclude with a discussion of issues that are common to the A-life and HCI research communities.

Do-It-Yourself (DIY) Assistive Technology: A Communication Board Case Study

Do-It-Yourself (DIY) and open design approaches allow for the development of customized, affordable assistive technologies. Freely shared designs and software components open doors for new ways to create and to share technology, representing an approach that has the potential to be more efficient, affordable, and effective than commercial approaches to Assistive Technology development and deployment. In this paper, we present a case study of how these methods have been used to develop a DIY, open-source Speech-Generating Device.

PhoVR: a virtual reality system to treat phobias

Phobias are a common type of disorder that affect a significant number of people, often in debilitating ways. Treating phobias is not always straightforward and can require significant effort from both the patient and the clinician. We propose a Virtual Reality Exposure Therapy (VRET) system for the treatment of phobias that makes use of affordable, consumer-level hardware and software components. The system allows the patient to follow the treatment in the comfort of his or her own home and allows the clinician to supervise and to direct the treatment from a different location via network.

Positional targets for lingual consonants defined using electromagnetic articulography

The study examined the positional targets for lingual consonants defined using a point-parameterized approach with Wave (NDI, Waterloo, ON, Canada). The overall goal was to determine which consonants had unique tongue positions with respect to other consonants. Nineteen talkers repeated vowel-consonant-vowel (VCV) syllables that included consonants /t, d, s, z, , k, g/ in symmetrical vowel contexts /i, u, a/, embedded in a carrier phrase. Target regions for each consonant, characterized in terms of x,y,z tongue positions at the point of maximum tongue elevation, were extracted. Distances and overlaps were computed between all consonant pairs and compared to the distances and overlaps of their contextual targets. Cognates and postalveolar homorganics were found to share the location of their target regions. On average, alveolar stops showed distinctively different target regions than alveolar fricatives, which in turn showed different target region locations than the postalveolar consonants. Across talker variability in target locations was partially explained by differences in habitual speaking rate and hard palate characteristics.

Huffman Base-4 Text Entry Glove (H4 TEG)

We designed and evaluated a Huffman base-4 Text Entry Glove (H4-TEG). H4-TEG uses pinches between the thumb and fingers on the users right hand. Characters and commands use base-4 Huffman codes for efficient input. In a longitudinal study, participants reached 14.0 wpm with error rates <;1%. In an added session without visual feedback, entry speed dropped only by 0.4 wpm. Yet another session was added that required entry of text with punctuation and other symbols. Entry speed dropped by 1.5 wpm.

The contrastive evaluation of unimodal and multimodal interfaces for voice otput communication aids

For computational Augmentative and Alternative Communication (AAC) aids, it has often been asserted that multimodal interfaces have benefits over unimodal ones. Several such benefits have been described informally, but, to date, few have actually been formalized or quantified. In this paper, some of the special considerations of this application domain are described. Next, the hypothesized benefits of semantically nonredundant multimodal input actions over unimodal input actions are described formally. The notion of information rate, already well established as a dependent variable in evaluations of AAC devices, is quantified in this paper, using the formalisms provided by Information Theory (as opposed to other, idiosyncratic approaches that have been employed previously). A comparative analysis was performed between interfaces that afford unimodal input actions and those that afford semantically nonredundant multimodal input actions. This analysis permitted generalized conclusions, which have been synthesized with those of another, recently-completed analysis in which unimodal and semantically redundant multimodal input actions were compared. A reinterpretation of Keates and Robinsons empirical data (1998) shows that their criticism of multimodal interfaces for AAC devices, in part, was unfounded.

The information-theoretic analysis of unimodal interfaces and their multimodal counterparts

That multimodal interfaces have benefits over unimodal ones has often been asserted. Several such benefits have been described informally, but, to date, few have actually been formalized or quantified. In this paper, the hypothesized benefits of semantically redundant multimodal input actions are described formally and are quantified using the formalisms provided by Information Theory. A reinterpretation of Keates and Robinsons empirical data (1998) shows that their criticism of multimodal interfaces was, in part, unfounded.

Sparkles of brilliance: incorporating cultural and social context in codesign of digital artworks

Digital media have great potential as tools for selfexpression and artistic exploration. We seek to enrich the discussion of challenges and benefits associated with using digital design methods and materials with children in developing countries through a case study. Our contributions to this discussion are based on our involvement in facilitating a twoday codesign workshop with 25 marginalized children in Oaxaca, Mexico. Together, we explored, designed and implemented digitally augmented paper artifacts based on traditional folk art from the childrens native region. We analyzed the artworks and observed the children during the workshop to inform our research. Lessons learned include the importance of establishing trust though local contacts, incorporating relevant cultural and social elements, planning concrete outcomes and using technology appropriately. We hope that this detailed case study may serve as an exemplar, by providing insights and inspiration for other designers, researchers, and developers when planning, carrying out, and studying workshops.