Annalu Waller - Academia.edu (original) (raw)

Papers by Annalu Waller

The advent of the microcomputer has provided the severely handicapped with the means to create te... more The advent of the microcomputer has provided the severely handicapped with the means to create text. Instead of using a keyboard, the disabled typist is able to scan and select linguistic items with an appropriate input switch. The resulting communication rate is, however, slow for writing and impractical for conversation. prohibitively A variety of techniques is used to improve this rate and range from 'static letter matrices to more sophisticated methods in which words and phrases are anticipated. Although many anticipatory methods claim to be linguis~ically based, most, if not all, depend solely on letter and word frequency statistics. 6 COMMUNICATION PROBLEMS Communication can be divided into expressive and receptive communication. Expressive communication refers to the formulation, encoding and sending of messages whereas receptive communication refers to the interception, decoding and understanding of messages. Impaired expressive communication indicates a difficulty in communication output (Creech, 1984). This may arise as a result of a motor disability affecting speech and/or physical movementse.g. cerebral palsy, amytrophic lateral scle~osis (ALS)or an inability to convert thoughts into words e.g. expressive aphasia. Writing is another form of expressive communication and can be impeded by motor, visual and mental disabilities. A loss of hearing, visual impairment, and the inability to understand language-e.g. receptive aphasia-can all lead to a receptive communication handicap. A communication problem may be due to sensory, psychological or physical (motor) impairments. 7 mental, Sensory Impairment An individual with a hearing impairment experiences difficulty in both receptive (hearing) and expressive (spoken) communication. A visually disabled person also has difficulty with both expressive and receptive forms of communication. The person with a hearing loss, however, has a conversational impairment whereas the visually disabled person cannot read or write. Various communication systems enable the deaf and the blind to overcome their communication problems. Unaided systems, e.g. sign language, provide conversation for the deaf (Vanderheiden & Lloyd, 1986), while braille provides an aided written communication system for the blind (Arditi & Gillman, 1986). Development of technology provides more and more sophisticated systems such as film subtitling, telecommunication devices and cochlear implants for the deaf (Damper et al, 1979; Hoyt, 1985; Loomis et al, 1983; Minneman, 1~84) and braille input-output (I/0) devices for the blind (Grossner et al, 1983; Fant, 1982; Stoffel, 1982). Mental Impairment The delay in the development of speech and motor control affects the communication of the mentally retarded individual. Gesture, sign and symbolic communication languages, are used to provide conversation for individuals with language and motor delays (Meyers, 1983). 8 Microcomputers can be used to provide a slow, repetitive medium for teaching, as well as providing a' means to simulate real-world situations, through the use of graphics and speech synthesis (Young, 1983). Psychological Impairment Communication handicaps can result from a psychological disability. Autism is one such disability in which communication can be severely impaired. Sign language and graphic communication boards are used to facilitate communication when the autistic individual is reluctant to engage in direct communication (Scrimshaw). The microcomputer has proved a motivating factor in breaking. down this barrier,by providing a non-threatening environment for social interaction (Papert, 1980). Physical Impairment Physical impairments often result in limited communication when the motor control of oral and limb function is impaired. Physical disfigurement, paralysis, spasticity and uncontrolled movements can impede spoken and/or written communication. Handicapping conditions caused by neurological damage (e.g. spinal cord injury, cerebral palsy, and cerebrovascular accidents (CVA stroke)), degenerative conditions (e.g. amytrophic lateral sclerosis and muscular dystrophy), and physical trauma (e.g. vocal• chord damage). All have devastating effects on communication. 9 which might include a number of the impairments mentioned above. This dissertation addresses those communication handicaps which result primarily Unless otherwise indicated, terms refer to physical disability. COMMUNICATION NEEDS from physical impairments. relating to disability will Communication is fundamental to interpersonal interaction and occurs in response to several communication needs (Vanderheiden, 1983; Vanderheiden & Lloyd, 1986). These needs can be summarized as follows: The communication of basic needs necessitates the transfer of essential information in a quick and easy and way which can be readily understood (MacDonald, 1980; McNaughton, 1985). Conversation also depends on a sufficiently fast rate of communication to facilitate functional interaction. Any restriction on the communication rate diminishes the quality of conversation (Vanderheiden, 1983). 10 Writing and messaging describe permanent forms of ' conununication. An ability to create text is essential for school work •and occupational requirements (Vanderheiden, 1983). The speed at which written text is produced, is not as crucial as in the communication of basic needs and conversation, as it does not primarily involve human interaction. However, it is still an important consideration as more rapid machine communication can contribute towards greater efficiency in ergonomic terms. Drawing allows for perceptual, psychological and recreational development by providing creative exploration, allowing expression of feelings and providing pictorial and graphic representation of facts and ideas (Papert, 1980; Weir et al., 1982). The emergence of the computer age has created new communication needs and opportunities. Electronic communication in the form of bulletin boards, data banks, information retrieval, electronic payments, and work opportunities (Pilgrim), all require some type of computer access-. Environmental control systems are to b~ found in any home, e.g. remote controls used to change television channels and to open electric garage doors. The availability of these systems has provided the severely disabled with the means to control their own environment for the first time (Boonzaier & Kleviansky,

The PhonicStick is a novel Augmentative and Alternative Communication joystick-like device which ... more The PhonicStick is a novel Augmentative and Alternative Communication joystick-like device which enables individuals with severe speech and physical disorders to access forty-two sounds (i.e. phonics) and blend the sounds together to create spoken words. The device aims to allow the users to select phonics and produce speech without the need for a visual interface. One of the problems with the current prototype of the PhonicStick is that the phonic entry is relatively slow and may involve many physical movements which will cause great difficulties for users with poor hand function. Therefore, in this research we are investigating whether natural language processing (NLP) technology can be utilized to facilitate the phonic retrieval and word creation processes. Our goal is to develop a set of phonic-based NLP acceleration methods, such as phonic disambiguation and phonic prediction, which will reduce the user effort required to select the target phonics and improve the speed of producing words. This paper will discuss the challenges of applying such methods to the PhonicStick and report on the current state of the development of the proposed techniques. The presentation will also include a live demonstration of the latest prototype of the PhonicStick.

ACM Transactions on Computer-Human Interaction

Current mechanisms for adopting and supporting high-tech augmentative and alternative communicati... more Current mechanisms for adopting and supporting high-tech augmentative and alternative communication (AAC) within special-education appear limited in their success, despite recognition of the potential benefits they represent for young emerging communicators. Prior research in this field has been restricted to discrete survey or interview methodologies. We present a five-month mixed-methods ethnographic study in a special-education school to explore the facilitators and barriers experienced by those using technology, with children who have little or no functional speech, to stimulate communication and language comprehension. Our analysis supports the outcomes of earlier studies, but also furnishes novel insights into the scale and urgency of addressing the problem—with implications for user-centred design within this community. We highlight infrastructure, policy, and recruitment deficits, and propose a two-fold solution: (i) an increase in engagement with this population through the...

Communication in its broadest sense enables people and things to ‘connect’. High tech augmentativ... more Communication in its broadest sense enables people and things to ‘connect’. High tech augmentative and alternative communication (AAC) technologies provide one perspective for supporting communication. Unfortunately, these technologies are largely under-utilised by children, suggesting a need to understand how they are used and not used in interpersonal communication. This paper reports on work that is part of a doctoral project that is investigating how digital technologies for communication might be designed in new ways. This paper reports on work that is examining how communication happens in a primary special school environment, involving children, adults and AAC. We consider design implications based on the findings of our qualitative video study.

Part 1: Special Thematic Sessions S9 through integration into existing international standards an... more Part 1: Special Thematic Sessions S9 through integration into existing international standards and supporting guidance. The Easy Reading Framework is providing a required implementation to validate the W3C techniques in a real world solution. Thus, the W3C guidelines are both distilling new project learnings and also informing the work. Conclusion: There is a growing awareness of cognitive accessibility user requirements and barriers along with the importance of addressing them at source. Thus, it's an opportune time to be part of the Easy Reading project and to enhance the W3C standards and resources. The Easy Reading project's personalized adaptation framework provides new understanding of user requirements and practical solutions, as well as being as useful Assistive Technology in its own right. There is now a useful introduction to requirements, enhanced standards, guidelines and techniques that commissioners, designers and developers can use to improve the experience of many. As a result, the experiences of people with cognitive and learning disabilities can be improved by application of these internationally recognized resources. The W3C operates an open consensus process so others are encouraged to collaborate to further improve cognitive accessibility.

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, 2020

Nonspeaking individuals with motor disabilities typically have very low communication rates. This... more Nonspeaking individuals with motor disabilities typically have very low communication rates. This paper proposes a design engineering approach for quantitatively exploring contextaware sentence retrieval as a promising complementary input interface, working in tandem with a word-prediction keyboard. We motivate the need for complementary design engineering methodology in the design of augmentative and alternative communication and explain how such methods can be used to gain additional design insights. We then study the theoretical performance envelopes of a context-aware sentence retrieval system, identifying potential keystroke savings as a function of the parameters of the subsystems, such as the accuracy of the underlying auto-complete word prediction algorithm and the accuracy of sensed context information under varying assumptions. We find that context-aware sentence retrieval has the potential to provide users with considerable improvements in keystroke savings under reasonable parameter assumptions of the underlying subsystems. This highlights how complementary design engineering methods can reveal additional insights into design for augmentative and alternative communication.

ACM Transactions on Computer-Human Interaction, 2018

This article examines the educational efficacy of a learning environment in which children diagno... more This article examines the educational efficacy of a learning environment in which children diagnosed with Autism Spectrum Conditions (ASC) engage in social interactions with an artificially intelligent (AI) virtual agent and where a human practitioner acts in support of the interactions. A multi-site intervention study in schools across the UK was conducted with 29 children with ASC and learning difficulties, aged 4--14 years old. For reasons related to data completeness and amount of exposure to the AI environment, data for 15 children was included in the analysis. The analysis revealed a significant increase in the proportion of social responses made by ASC children to human practitioners. The number of initiations made to human practitioners and to the virtual agent by the ASC children also increased numerically over the course of the sessions. However, due to large individual differences within the ASC group, this did not reach significance. Although no evidence of transfer to t...

Simulation & Gaming, 2019

Background. The ability to rapidly switch between tasks is important in a variety of contexts. Tr... more Background. The ability to rapidly switch between tasks is important in a variety of contexts. Training in task switching may be particularly valuable for children with intellectual disability (ID), specifically ID linked to genetic syndromes such as Prader-Willi syndrome (PWS). We have developed a cognitive training game for children with PWS and performed a pilot evaluation of the programme to inform future game development. Here, we describe and critically reflect on the development and pilot evaluation process. Methods. Several novel aspects of our approach are highlighted in this paper, including the involvement (in various roles) of children with a rare genetic syndrome (PWS) in the development and evaluation of the software (participatory design) and the development of a matched control, or placebo version of the game for use in the pilot evaluation. Results. Children with PWS were capable of contributing to the design and development of a cognitive training game in various r...

International Journal of Human-Computer Studies, 2016

This paper describes a Natural Language Generation system (NLG), How was School Today? that autom... more This paper describes a Natural Language Generation system (NLG), How was School Today? that automatically creates a personal narrative from sensor data and other media (photos and audio). It can be used by children with complex communication needs in schools to support interactive narrative about personal experiences. The robustness of story generation to missing data was identified as a key area for improvement in a feasibility study of the system at a first special needs school. This paper therefore suggests three possible methods for generating stories from unstructured data: clustering by voice recording, by location, or by time. Clustering based on voice recordings resulted in stories that were perceived as most easy to read, and to make most sense, by parents in a quantitative evaluation. This method was implemented in the live system, which was developed and evaluated iteratively at a second special needs school with children with different usage profiles. Open challenges and possibilities for nlg in augmented and alternative communication are also discussed.

Lecture Notes in Computer Science, 2013

This paper describes the design of an authoring tool, ISISS (Improving Social Interaction through... more This paper describes the design of an authoring tool, ISISS (Improving Social Interaction through Social Stories), for supporting practitioners using social stories to enhance social interaction in children with Autism Spectrum Conditions (ASC). The goals of the research are: 1) to determine practitioners' current procedures when working with social stories; 2) to discover how technology can better support such practitioners in the development and use of social stories that focus on improving children's social communication skills. An exploratory study was conducted with experienced practitioners, resulting in a number of design principles. Two low-functioning prototypes were developed, and explored in a second study. Further work is discussed.

Proceedings of the 12th European Workshop on Natural Language Generation - ENLG '09, 2009

Augmentative and Alternative Communication (AAC) systems are communication aids for people who ca... more Augmentative and Alternative Communication (AAC) systems are communication aids for people who cannot speak because of motor or cognitive impairments. We are developing AAC systems where users select information they wish to communicate, and this is expressed using an NLG system. We believe this model will work well in contexts where AAC users wish to go beyond simply making requests or answering questions, and have more complex communicative goals such as story-telling and social interaction.

Proceedings of the 14th international ACM SIGACCESS conference on Computers and accessibility, 2012

The high incidence of literacy deficits among people with severe speech impairments (SSI) has bee... more The high incidence of literacy deficits among people with severe speech impairments (SSI) has been well documented. Without literacy skills, people with SSI are unable to effectively use orthographic-based communication systems to generate novel linguistic items in spontaneous conversation. To address this problem, phoneme-based communication systems have been proposed which enable users to create spoken output from phoneme sequences. In this paper, we investigate whether prediction techniques can be employed to improve the usability of such systems. We have developed iSCAN, a phoneme-based predictive communication system, which offers phoneme prediction and phoneme-based word prediction. A pilot study with 16 able-bodied participants showed that our predictive methods led to a 108.4% increase in phoneme entry speed and a 79.0% reduction in phoneme error rate. The benefits of the predictive methods were also demonstrated in a case study with a cerebral palsied participant. Moreover, results of a comparative evaluation conducted with the same participant after 16 sessions using iSCAN indicated that our system outperformed an orthographic-based predictive communication device that the participant has used for over 4 years.

CHI '14 Extended Abstracts on Human Factors in Computing Systems, 2014

CHI is more than a conference, it is an international community of researchers and practitioners ... more CHI is more than a conference, it is an international community of researchers and practitioners who want to make a difference. Everything we do is focused on uncovering, critiquing and celebrating radically new ways for people and technology to evolve together. People in their everyday contexts, in diverse regions of the world, from very different backgrounds, with alternative outlooks on life drive this innovation. As you take part in the conference sessions we really hope you will experience how powerful this people-centred approach to technological transformation can be. CHI as a conference is now in its 32nd year and has grown to become the premier international forum on human-computer interaction, gathering us all to share innovative interactive insights that shape people's lives. CHI draws together a multidisciplinary community from around the globe. Our great strength is our ability to bring together students and experts, researchers and practitioners, scientists, designers and engineers, drawing from their rich perspectives to create new visions of human-computer interaction. This year's conference theme is One of a CHInd. We chose this nearly two years ago as we began planning for this event. It has helped us focus our efforts and we hope you will use it to keep your eyes open to the bigger picture amongst all the excitement, range of presentations and activities at the conference. CHI 2014 is One of CHInd because it is a celebration of the conference's one of a kind diversity; from the broad range of backgrounds of its attendees, to the diverse spectrum of communities and fields that the conference and its research have an impact on. CHI 2014 will take place at the Metro Toronto Convention Centre in Toronto, Canada, a city itself known for its one of a kind cultural diversity. But, CHI 2014 is more than a celebration of the diversity of our community and conference setting. We hope that this year's event, more than anything, reminds you that the "people", "participants", "users" or "humans" that you hear described throughout this week are actually uniquely wonderful individuals full of hopes, concerns, joys and frustrations. CHI is here to serve all of these one of a kinds. CHI 2014 features two outstanding keynote speakers: Booker prize winning author, Margaret Atwood; and, leading UX designer, Scott Jenson. New for CHI 2014, we have Provoke! Wisdom! Impact! plenary talks first thing each morning on Tuesday, Wednesday and Thursday. Come along, join the crowd and be energised by our speakers who will each bring in their experience of the Big Picture to inspire us. The talks will be short-twenty minutes-and then the rest of the day's programme will begin. We are also delighted to host a timely retrospective exhibition on wearable technology curated by Thad Starner and Clint Zeagler. CHI 2014 also includes two days of focused workshops and four days of technical content, including CHI's prestigious technical program, with 15 parallel sessions of rigorously reviewed research Papers, engaging Panels, Case Studies and Special Interest Groups (SIGs), an extensive Course program and invited talks from SIGCHI's award winners: Steve Whittaker, Gillian Grampton Smith and Richard Ladner. We also host student research, design, and game competitions, provocative alt.chi presentations and last-minute SIGs for discussing current topicsInteractivity hands-on demonstrations showcase the best of interactive technology. We also highlight over 241 Work-In-Progress posters: this year we have added some features to these sessions to better help you get the most out of the exciting, early stage work on show; do go along and engage with the authors about their work. Evening events include the CHI 2014 conference reception, Sponsors and University events, local performances and the Job Fair. We received over 3200 submissions and accepted nearly 1000 that will appear in the ACM Digital Library. To help you navigate through this immense program, there are a number of online and digital resources from the conference website to our mobile apps. You can also browse the videos, papers and extended abstracts on the CHI 2014 USB Key. But, CHI 2014 is about being in Toronto so perhaps the best way to select from and experience the event is by asking for pointers and chatting with your fellow attendees, our wonderful student volunteers, the information desk helpers or any of this year's committee. We are all here to make your experience as useful and enjoyable as possible. We are deeply indebted to our vast number of volunteers, without whom CHI 2014 would not be possible, including over 3800 reviewers, over 180 senior members of the program committee, nearly 100 members of the CHI 2014 conference committee and, of course, the more than 180 student volunteers. We thank you all! We are honored and excited by the opportunity to host CHI 2014 and wish you a productive and enjoyable stay in Toronto!

Topics in Language Disorders, 2006

Language Resources and Evaluation, 2008

As part of a project to construct an interactive program which would encourage children to play w... more As part of a project to construct an interactive program which would encourage children to play with language by building jokes, we developed a lexical database, starting from WordNet. To the existing information about part of speech, synonymy, hyponymy, etc., we have added phonetic representations and phonetic similarity ratings for pairs of words/phrases.

IEEE Intelligent Systems, 2006

It is well documented that people with severe speech and physical impairments (SSPI) often experi... more It is well documented that people with severe speech and physical impairments (SSPI) often experience literacy difficulties, which hinder them from effectively using orthographicbased AAC systems for communication. To address this problem, phoneme-based AAC systems have been proposed, which enable users to access a set of spoken phonemes and combine phonemes into speech output. In this paper we investigate how prediction techniques can be applied to improve user performance of such systems. We have developed a phoneme-based prediction system, which supports single phoneme prediction and phoneme-based word prediction using statistical language models generated using a crowdsourced AAC-like corpus. We incorporated our prediction system into a hypothetical 12-key reduced phoneme keyboard. A computational experiment showed that our prediction system led to 56.3% average keystroke savings. 4.2.1 Keystroke Savings Keystroke Savings (KS) is defined as the percentage of keystrokes that the user saves by using prediction methods compared to using the MULTITAP method: