Real-time captions presented through AR glasses hold great promise for enhancing accessibility for Deaf and Hard of Hearing (DHH) individuals. However, conventional approaches often overlook the diversity of user preferences and perceptual characteristics. In this study, we explore how spatial personalization—adjustments in display method, position, and depth—can improve the user experience of AR captions.We conducted two experiments. Experiment 1 focused on 2D position personalization, revealing that user-controlled positioning enhanced visibility and comfort, though comprehension gains were modest. Experiment 2 introduced a novel concept, Simulated Depth Personalization, which emulates different viewing distances despite a fixed AR focal plane (4 m). This revealed clear individual differences: participants varied in whether their preferences aligned more with the presentation method (e.g., monocular vs. binocular) or viewing distance.Our findings emphasize that effective AR captioning is not one-size-fits-all but must flexibly adapt to individual spatial preferences. We argue for incorporating spatial personalization as a core design principle for accessible AR systems.

Auditory directionality remains challenging for d/Deaf and hard of hearing (DHH) people. We evaluated a shoulder-mounted tactile system that vibrates bilaterally to signal sound direction and urgency in multi-person meetings. Eight DHH participants watched subtitled VR meetings with and without the device, pressing a trigger when their name or an alarm appeared and selecting the speaker afterward. The device increased reaction count for name calls and shortened reaction time for both name and alarm alerts (all p < 0.05), while speaker identification accuracy stayed high and unchanged. Post-experiment surveys confirmed strong demand for directional cues (p < 0.01) and alarm sound alerts (p < 0.05). Reflective Thematic Analysis of open-ended responses highlighted (i) the need to customize target sounds, (ii) meeting-focused use cases, and (iii) requests for refined vibration patterns and lighter design. These findings demonstrate the system’s value for timely notifications and emphasize directional feedback and customizability as critical to practical adoption.

Japanese Sign Language (JSL) and Manually Coded Japanese (MCJ) are the two main forms of sign language used in Japan. The former differs significantly from spoken Japanese, while the latter closely aligns with spoken syntax. Pidgin Sign Japanese (PSJ) is an intermediate form that heavily relies on nonmanual signals such as facial expressions and head movements for grammatical nuances. Current sign language recognition (SLR) systems predominantly focus on MCJ, neglecting the challenging properties of PSJ. This paper proposes an annotation assistance tool designed to automate the annotation of non-manual and spatial elements in PSJ. Our tool significantly reduces the manual effort required for annotation by using state-of-the-art methods for tracking human pose, hand, and face landmarks, along with recognizing facial action units (FAUs). Validation on a preliminary dataset of 30 videos containing over 90 instances of nonmanual elements demonstrated a $\mathbf{4 0 \%}$ reduction in annotation time, highlighting our proposal’s efficiency and effectiveness in handling the complexities of PSJ.

We have conducted a series of experiment to investigate the potential of music communication based on emotion for hearing-impaired people and people with hearing abilities. The purpose of the experiments is to design a performance assistance system to enable hearing-impaired people to enjoy taking part in a music ensemble. In this paper, we describe an experiment on recognizing emotion in two media: moving images of a professional percussionist giving an improvised performance and the sounds extracted from the performance. The experiment was designed to investigate whether the image of a performance is important in recognizing emotion in the performance. The result showed that there was no significant difference in recognition of emotion between the two media. Our results were consistent with those of previous experiments: (1) there was no significant difference in recognizing emotion between hearing-impaired people and people with hearing abilities, and (2) ldquofearrdquo was the least recognized of the four emotions.

We conducted an experiment to determine the abilities of hearing-impaired and normal-hearing people to recognize intended emotions conveyed in four types of stimuli: a drum performance, a drum performance accompanied by a drawing expressing the same intended emotion, and a drum performance accompanied by one of two types of motion pictures. The recognition rate was the highest for a drum performance accompanied by a drawing even though participants in both groups found it difficult to identify the intended emotion because they felt the two stimuli sometimes conveyed different emotions. Visual stimuli were especially effective for performances whose intended emotions were not clear by themselves. The difference in ability to recognize intended emotions between the hearing-impaired and normal-hearing participants was insignificant. The results of this and a series of experiments will enable us to better understand the similarities and differences between how people with different hearing abilities encode and decode emotions in and from sound and visual media. We should then be able to develop a system that will enable hearing-impaired and normal-hearing people to play music together.

With the purpose of building a performance assistant system with visual cues for hearing-impaired people and people with normal hearing abilities to play music together, we need to better understand how hearing-impaired people express and understand music with visual assistance. We have conducted a series of experiments to determine how hearing-impaired people understand an emotion in a drum performance from its intended emotion. These experiments showed that communication based on emotion through musical performance is possible. Therefore we need to know the practical applications for a visual interface. In this paper, we describe an experiment that determines how hearing-impaired people understand an emotion in small simple drawings from its intended emotion. The results suggest that there are similarities in recognizing emotions between hearing-impaired people and people with normal hearing abilities.

A novel method is described for automatically modeling virtual cities that change over time. Cellular automata are used to lay out the buildings, and a genetic algorithm is used to produce the time series of changes. The cellular automata are given one of several states: vacant, four kinds of buildings and two kinds of roads. The sequence of applied rules needed to generate the series of changes is determined using a genetic algorithm.

This paper proposes a novel method that enables automatic modeling of virtual cities. The method makes use of L-systems to generate road networks and the genetic algorithm (GA) to generate building layouts. The road networks are composed of two types of roads-linear flow systems which are generated by using the Tree L-system and cellular networks which are generated by using the Map L-system. A generation procedure for road networks and building layouts is described. Some experimental results of generated road networks and virtual cities are also shown.