Non-intrusive Metrics Research Articles

Collaborative System Usability in Spaceflight Analog Environments through Remote Observations

The conventional design cycle in human–computer interaction faces significant challenges when applied to users in isolated settings, such as astronauts in extreme environments. Challenges include obtaining user feedback and effectively tracking human–software/human–human dynamics during system interactions. This study addresses these issues by exploring the potential of remote conversation analysis to validate the usability of collaborative technology, supplemented with a traditional post hoc survey approach. Specifically, we evaluate an integrated timeline software tool used in NASA’s Human Exploration Research Analog. Our findings indicate that voice recordings, which focus on the topical content of intra-crew speech, can serve as non-intrusive metrics for essential dynamics in human–machine interactions. The results emphasize the collaborative nature of the self-scheduling process and suggest that tracking conversations may serve as a viable proxy for assessing workload in remote environments.

On the Cost of Detection Response Task Performance on Cognitive Load.

This study investigates the cost of detection response task performance on cognitive load. Measuring system operator's cognitive load is a foremost challenge in human factors and ergonomics. The detection response task is a standardized measure of cognitive load. It is hypothesized that, given its simple reaction time structure, it has no cost on cognitive load. We set out to test this hypothesis by utilizing pupil diameter as an alternative metric of cognitive load. Twenty-eight volunteers completed one of four experimental tasks with increasing levels of cognitive demand (control, 0-back, 1-back, and 2-back) with or without concurrent DRT performance. Pupil diameter was selected as nonintrusive metric of cognitive load. Self-reported workload was also recorded. A significant main effect of DRT presence was found for pupil diameter and self-reported workload. Larger pupil diameter was found when the n-back task was performed concurrently with the DRT, compared to no-DRT conditions. Consistent results were found for mental workload ratings and n-back performance. Results indicate that DRT performance produced an added cost on cognitive load. The magnitude of the change in pupil diameter was comparable to that observed when transitioning from a condition of low task load to one where the 2-back was performed. The significant increase in cognitive load accompanying DRT performance was also reflected in higher self-reported workload. DRT is a valuable tool to measure operator's cognitive load. However, these results advise caution when discounting it as cost-free metric with no added burden on operator's cognitive resources.

Phase‐aware subspace decomposition for single channel speech separation

Single channel speech separation (SCSS) is often required as post-processing in several applications that facilitate automatic human-to-human or human-to-machine communication in challenging acoustic environments such as voice command for smart homes or robotics. The proposed SCSS system, that the authors call phase-aware subspace decomposition (PASD), relies on subspace decomposition for speech separation followed by a phase-aware mask for final subspace recovery. In fact, the proposed approach decomposes the mixture into a sparse and low-rank subspace in the frequency domain by rank minimising that relies on iterative decomposition using adaptive thresholding in each iteration to achieve soft estimation and considers phase-information for reconstruction. Separation results are reported in terms of both intrusive and non-intrusive metrics using realistic recordings corrupted with real-life noises. As speech separation systems are expected to have maximal interference rejection without speech distortion, we also evaluate the proposed system by recognising speech from a target speaker in the presence of either concurrent speech or noise. Recognition results show that separated signals are of high intelligibility so that they can be exploited by other automatic applications. The extensive evaluation under different test scenarios proves that PASD consistently improves the quality of the separated signals, compared to other benchmark approaches.

Enriched communication across the lifespan

Speech is a hugely efficient means of communication: a reduced capacity in listening or speaking creates a significant barrier to social inclusion at all points through the lifespan, in education, work and at home. Hearing devices and speech synthesis can help address this reduced capacity but their use imposes greater listener effort. The goal of the EU-funded ENRICH project is to modify or augment speech with additional information to make it easier to process. Enrichment reduces listening burden by minimising cognitive load, while maintaining or improving intelligibility. ENRICH investigates the relationship between cognitive effort and natural and synthetic speech. Non-intrusive metrics for listening effort will be developed and used to design modification techniques which result in low-burden speech. The value of various enrichment approaches will be evaluated with individuals and cohorts with typically sub-optimal communication ability, such as children, hearingor speech-impaired adults, non-native listeners and individuals engaged in simultaneous tasks.

Driver drowsiness detection based on non-intrusive metrics considering individual specifics

ObjectivesDrowsy driving is a serious highway safety problem. If drivers could be warned before they became too drowsy to drive safely, some drowsiness-related crashes could be prevented. The presentation of timely warnings, however, depends on reliable detection. To date, the effectiveness of drowsiness detection methods has been limited by their failure to consider individual differences. The present study sought to develop a drowsiness detection model that accommodates the varying individual effects of drowsiness on driving performance. MethodsNineteen driving behavior variables and four eye feature variables were measured as participants drove a fixed road course in a high fidelity motion-based driving simulator after having worked an 8-h night shift. During the test, participants were asked to report their drowsiness level using the Karolinska Sleepiness Scale at the midpoint of each of the six rounds through the road course. A multilevel ordered logit (MOL) model, an ordered logit model, and an artificial neural network model were used to determine drowsiness. ResultsThe MOL had the highest drowsiness detection accuracy, which shows that consideration of individual differences improves the models’ ability to detect drowsiness. According to the results, percentage of eyelid closure, average pupil diameter, standard deviation of lateral position and steering wheel reversals was the most important of the 23 variables. ConclusionThe consideration of individual differences on a drowsiness detection model would increase the accuracy of the model's detection accuracy.