Creating and Augmenting Keyboards for Extended Reality with the K eyboard A ugmentation T oolkit

This article discusses the Keyboard Augmentation Toolkit (KAT), which supports the creation of virtual keyboards that can be used both for standalone input (e.g., for mid-air text entry) and to augment physically tracked keyboards/surfaces in mixed reality. In a user study, we firstly examine the impact and pitfalls of visualising shortcuts on a tracked physical keyboard, exploring the utility of virtual per-keycap displays. Supported by this and other recent developments in XR keyboard research, we then describe the design, development, and evaluation-by-demonstration of KAT. KAT simplifies the creation of virtual keyboards (optionally bound to a tracked physical keyboard) that support enhanced display —2D/3D per-key content that conforms to the virtual key bounds; enhanced interactivity —supporting extensible per-key states such as tap, dwell, touch, swipe; flexible keyboard mappings that can encapsulate groups of interaction and display elements, e.g., enabling application-dependent interactions; and flexible layouts —allowing the virtual keyboard to merge with and augment a physical keyboard, or switch to an alternate layout (e.g., mid-air) based on need. Through these features, KAT will assist researchers in the prototyping, creation and replication of XR keyboard experiences, fundamentally altering the keyboard’s form and function.

Exploring a Bilingual Next Word Predictor for a Federated Learning Mobile Application

We explore a bilingual next-word predictor (NWP) under federated optimization for a mobile application. A character-based LSTM is server-trained on English and Dutch texts from a custom parallel corpora. This is used as the target performance. We simulate a federated learning environment to assess the feasibility of distributed training for the same model. The popular Federated Averaging (FedAvg) algorithm is used as the aggregation method. We show that the federated LSTM achieves decent performance, yet it is still sub-optimal. We suggest possible next steps to bridge this performance gap. Furthermore, we explore the effects of language imbalance varying the ratio of English and Dutch training texts (or clients). We show the model upholds performance (of the balanced case) up and until a 80/20 imbalance before decaying rapidly. Lastly, we describe the implementation of local client training, word prediction and client-server communication in a custom virtual keyboard for Android platforms. Additionally, homomorphic encryption is applied to provide with secure aggregation guarding the user from malicious servers.

Exploring a Bilingual Next Word Predictor for a Federated Learning Mobile Application

We explore a bilingual next-word predictor (NWP) under federated optimization for a mobile application. A character-based LSTM is server-trained on English and Dutch texts from a custom parallel corpora. This is used as the target performance. We simulate a federated learning environment to assess the feasibility of distributed training for the same model. The popular Federated Averaging (FedAvg) algorithm is used as the aggregation method. We show that the federated LSTM achieves decent performance, yet it is still sub-optimal. We suggest possible next steps to bridge this performance gap. Furthermore, we explore the effects of language imbalance varying the ratio of English and Dutch training texts (or clients). We show the model upholds performance (of the balanced case) up and until a 80/20 imbalance before decaying rapidly. Lastly, we describe the implementation of local client training, word prediction and client-server communication in a custom virtual keyboard for Android platforms. Additionally, homomorphic encryption is applied to provide with secure aggregation guarding the user from malicious servers.

Romanian Slavonic in Unicode: problems and solutions

Editors of Slavonic and Slavonic–Romanian text can make use of a large variety of tools (fonts, physical and virtual keyboard layouts, word processors, operating systems) for transcribing and digitizing these texts in a uniform manner. The uniformity of the transcripts is based on Unicode standardization. Our study aims at explaining the place of Slavonic in Unicode and at briefly describing the most accessible tools. To this end, we shall describe the working tools from a historical and functional perspective and then provide examples in which those tools can be or have already been used to obtain a more accurate transcript. The user can choose from the existing methods and tools according to his/her purposes, needs and means. A better understanding of technical data can reduce the working time, improve transcription, accelerate learning times and generally make an editor’s work much easier.

Eye gaze controlled adaptive virtual keyboard for users with SSMI

BACKGROUND: Users with Severe Speech and Motor Impairment (SSMI) often use a communication chart through their eye gaze or limited hand movement and care takers interpret their communication intent. There is already significant research conducted to automate this communication through electronic means. Developing electronic user interface and interaction techniques for users with SSMI poses significant challenges as research on their ocular parameters found that such users suffer from Nystagmus and Strabismus limiting number of elements in a computer screen. This paper presents an optimized eye gaze controlled virtual keyboard for English language with an adaptive dwell time feature for users with SSMI. OBJECTIVE: Present an optimized eye gaze controlled English virtual keyboard that follows both static and dynamic adaptation process. The virtual keyboard can automatically adapt to reduce eye gaze movement distance and dwell time for selection and help users with SSMI type better without any intervention of an assistant. METHODS: Before designing the virtual keyboard, we undertook a pilot study to optimize screen region which would be most comfortable for SSMI users to operate. We then proposed an optimized two-level English virtual keyboard layout through Genetic algorithm using static adaptation process; followed by dynamic adaptation process which tracks users’ interaction and reduces dwell time based on a Markov model-based algorithm. Further, we integrated the virtual keyboard for a web-based interactive dashboard that visualizes real-time Covid data. RESULTS: Using our proposed virtual keyboard layout for English language, the average task completion time for users with SSMI was 39.44 seconds in adaptive condition and 29.52 seconds in non-adaptive condition. Overall typing speed was 16.9 lpm (letters per minute) for able-bodied users and 6.6 lpm for users with SSMI without using any word completion or prediction features. A case study with an elderly participant with SSMI found a typing speed of 2.70 wpm (words per minute) and 14.88 lpm (letters per minute) after 6 months of practice. CONCLUSIONS: With the proposed layout for English virtual keyboard, the adaptive system increased typing speed statistically significantly for able bodied users than a non-adaptive version while for 6 users with SSMI, task completion time reduced by 8.8% in adaptive version than nonadaptive one. Additionally, the proposed layout was successfully integrated to a web-based interactive visualization dashboard thereby making it accessible for users with SSMI.

Operating Virtual Keyboard and Mouse Using Hand Gestures

This project promotes an approach for the Human Computer Interaction (HCI) where cursor movement can be controlled using a real-time camera, it is an alternative to the current methods including manual input of buttons or changing the positions of a physical computer mouse. Instead, it utilizes a camera and computer vision technology to control various mouse events and is capable of performing every task that the physical computer mouse can. The Virtual Mouse color recognition program will constantly acquiring real-time images where the images will undergone a series of filtration and conversion. Whenever the process is complete, the program will apply the image processing technique to obtain the coordinates of the targeted colors position from the converted frames. After that, it will proceed to compare the existing colors within the frames with a list of color combinations, where different combinations consists of different mouse functions. If the current colors combination found a match, the program will execute the mouse function, which will be translated into an actual mouse function to the users' machine.