D. Jeffery Higginbotham

Techniques for augmenting scanning communication

Scanning communication systems provide a unique set of opportunities for the application of augmentative communication technologies. Possibilities include optimization of the row-column matrix, dynamic rearrangement of the matrix, addition of character or word lists, and combinations of these techniques. A series of descriptive experiments were performed to establish the switch savings performance of 14 different scanning configurations. A common software platform and a strictly regimented testing procedure were employed to ensure the reliability and consistency of the data, facilitating comparisons between the different paradigms. Within each configuration, a systematic analysis of the relevant parameters was performed. The best character prediction method provided an average switch savings of 40.5% over a baseline row-column configuration, while the best word prediction technique provided an average savings of only 38.8%. Both of these configurations used seven-element prediction lists, which did not pr...

Evaluation of keystroke savings across five assistive communication technologies

This investigation assessed the written keystroke savings of five available assistive communication technologies (ACTs): E Z Keys, Predictive Linguistic Program, Words Strategy, Write 100, and a generic encoding technique. Each ACT was used to type 20 written expository texts composed by nondisabled individuals from four grade levels (4th, 8th, 12th, and college). Evaluation of keystroke savings revealed significant between-ACT differences in keystroke savings across devices for all typed text, typed text contained in an ACTs lexicon and spelled text, as well as differences in the vocabulary coverage of each ACT. Between-grade differences in keystroke savings were not generally noted. Results are discussed in regard to the utility of keystroke savings for clinical evaluation and communication device development.

Use of nondisabled subjects in AAC research: Confessions of a research infidel

Research within augmentative and alternative communication (AAC) frequently involves the use of augmentative systems users as subjects. This article will make an argument for using nondisabled communicators as subjects in AAC research.

Subject Selection in AAC Research: Decision Points

In this concluding paper related to subject selection in augmentative and alternative communication (AAC) research, four issues previously discussed are brought together: the representativeness/homogeneity of subjects, methodological design, external validity, and research economics. In light of these particular issues, a set of heuristics for making appropriate subject choices is provided.

Discourse comprehension of synthetic speech delivered at normal and slow presentation rates

The purpose of this investigation was to determine the effects of the quality and speech presentation rate (SPR) of synthetic speech and textual characteristics (length, complexity, genre) on a listeners ability to summarize paragraph-length texts. Forty able-bodied students and staff members were individually tested over a 3-day period, listening to eight texts produced by one of two synthesizers (DECtalk, Echo+) at a normal SPR or with 10-second intervals of silence interspersed between individual words. Using a discourse summarization taxonomy developed for this study, subjects listening to DECtalk speech produced more accurate summaries than did ECHO speech listeners, and synthetic speech presented at a slow rate was summarized more accurately than synthetic speech presented at a normal SPR. Additionally, a significant three-way interaction effect was noted for voice × SPR × text complexity. Echo listeners performed more poorly at normal versus slow SPRs regardless of text complexity level. However, ...

The effect of context priming and task type on augmentative communication performance.

Augmentative and Alternative Communication (AAC) devices include special purpose electronic devices that generate speech output and are used by individuals to augment or replace vocal communication. Word prediction, including context specific prediction, has been proposed to help overcome barriers to the use of these devices (e.g., slow communication rates and limited access to situation-related vocabulary), but has not been tested in terms of effects during actual task performance. In this study, we compared AAC device use, task performance, and user perceptions across three tasks, in conditions where the AAC device used either was, or was not, primed with task specific vocabularies. The participants in this study were adults with normal physical, cognitive, and communication abilities. Context priming had a marginally significant effect on AAC device use as measured by keystroke savings; however, these advantages did not translate into higher level measures of rate, task performance, or user perceptions. In contrast, there were various statistically significant process and performance differences across task type. Additionally, results for two different emulations of human performance showed significant keystroke savings across context conditions. However, these effects were mitigated in actual performance and did not translate into keystroke savings. This indicates to AAC device designers and users that keystroke-based measures of device use may not be predictive of high level performance.

An AAC Application Using Speaking Partner Speech Recognition to Automatically Produce Contextually Relevant Utterances: Objective Results

The purpose of this study was to evaluate the efficacy of a computer program, Converser, which uses the speech recognition of the speaking partner to predict contextually appropriate utterances and to store relevant noun phrases. The dyads (which consisted of a program user and a speaking partner) tested Converser in two communication tasks: a conversation and an interview. Two conditions were applied: A simple communication aid with an alphabet layout without Converser (alpha-only condition), and an identical aid with Converser (alpha-converser condition). Objective measurements were made concerning the program users rate and Converser usage. The results showed that the alpha-converser condition generated a faster communication rate than the alpha-only condition. Also, the program users utilized the stored noun phrases in their productions more than the full utterances. Converser allowed for periodic instances of a fast rate of speech, which appeared to have a positive impact on communication.

AAC performance and usability issues: the effect of AAC technology on the communicative process.

In this article, Clarks theory of language use is applied to the study of conversations of augmented speakers and their addressees. Discussion focuses on how shared meaning—called common ground—is achieved, the process of grounding utterances under real-time constraints, and how the media characteristics of devices affect the grounding process. A joint action analysis of grounding will be applied to examples of word-board and Voice Output Communication Aid (VOCA)-mediated conversations to show how participants organize their talk around specific media constraints to conduct their conversations and solve communication problems. The authors argue that this model of device-mediated communication performance, or some variety of it, has the potential to reconcile many of the individual research findings in this field within a single explanatory framework. If successful, this approach could be used to evaluate future research with an empirically-based model of communication performance.

The Application of Natural Language Processing to Augmentative and Alternative Communication

ABSTRACT Significant progress has been made in the application of natural language processing (NLP) to augmentative and alternative communication (AAC), particularly in the areas of interface design and word prediction. This article will survey the current state-of-the-science of NLP in AAC and discuss its future applications for the development of next generation of AAC technology.

The effect of the communication output method on augmented interaction

The experiment compared the ability of a Comprehension Model versus an Interaction Model to account for the communication performance of augmented communicators. Five dyads consisting of adults without disabilities, with one participant in each dyad randomly assigned to use an augmentative communication device, engaged in ten direction-giving tasks in which the augmented communicator used either a Word Method (i.e., spoken words only) or a Mixed Method (i.e., mix of spoken words and letters) speech output. Results indicated an overall completion time and communication rate advantage for the Mixed Method output in most communication tasks, supporting the Interaction Model of augmented communication. The role of communication co-construction in augmented interaction and the implications of the Interaction Model for future communication device design are discussed.