Computational simulations of mediated face-to-face multimodal communication
Bibliographic record
Abstract
Individuals who have little or no functional speech due to underlying physical disorder may instead use a computational device, called a Voice Output Communication Aid (VOCA), to produce synthesized speech. We describe a previously-unidentified set of tradeoffs that face the designers of Augmentative and Alternative Communication (AAC) systems, of which VOCAs are one possible component. On the one hand, the mode of synthesized speech that is afforded by a VOCA can be used to produce communicative actions that are more likely to be successfully interpreted than those produced using other modes, especially by unfamiliar communication partners—a benefit that can justify the often-sizeable effort that must be expended by individuals in order to use their VOCAs. On the other hand, the use of this so-called aided mode can conflict with the simultaneous use of the other, unaided modes, such as facial expression, eye gaze, vocalization, and gesture—a negative effect on the interlocutor's ability to produce multimodal communicative actions. These actions can be equally or even more effective than unimodal ones produced using synthesized speech alone, while also requiring less effort. The use of multimodal interfaces for VOCAs was first proposed by Shein et al. [1990]; prototypes have since been developed by Treviranus et al. [1991], Smith et al. [1996], and Keates and Robinson [1998]. We describe and formalize a previously-unidentified mechanism whereby a repertoire of modes of articulation affords a repertoire of mode strategies. The mechanism developed here accounts for the effects of conflict among the modes in a repertoire—a situation in which two or more modes rely on common underlying communicative effectors, as is the case with synthesized speech and gesture. We instantiated the mechanism computationally and used it to simulate the consequences of unimodal and multimodal VOCA interfaces on a simulated communicator's repertoire of mode strategies. We show that, for the unimodal interfaces, empirical and anecdotal evidence agree with the simulation results. We also show, through the simulations, that the mechanism of mode conflict can have serious consequences for the utility of multimodal VOCA interfaces and thus the bottleneck-reduction hypothesis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".