We present Soundoku, a sound-based puzzle game designed for sighted people. The goal of this game is to determine if it is possible to transform a popular puzzle game like Blendoku into a sound-based puzzle, without making it a musical game, and to obtain a fun, interesting and eventually instructive game. Initial evaluations of our game by players between the ages of 17 and 26 indicate that the game is considered fun if not addictive. These results pave the way for the creation of a game using procedural generation of sound puzzles.

The purpose of this prototype is to demonstrate a use of puff input for text entry. The entry method is based on hierarchical scanninglike selection of characters located in a static table organized according too the letter frequency. The cursor is moved in a way similar to operating a claw crane machine with two buttons. To move the cursor to the target position the user needs to produce two puffs, the first selects the column, and the second selects the row. With a brief training the method is capable of entry rate of 5 WPM.

The purpose of this prototype is to demonstrate the feasibility of text entry via detection of the surface myoelectric signals on user's body. Our system is capable to detect the movement of two fingers and the entire palm. The detector produces discrete signals as well as continuous quantifications of the exerted force. Two mappings of the signals on text entry were implemented, Scanning LetterWise and 2-FOCL, in two modes, discrete and continuous.

In an initial user study, three motor-impaired musicians---a composer with a degenerative motor neuron disease, a guitarist who suffered a stroke, and a first-year college student with impaired finger movement---identified prospective areas of research in assistive technology. Participants in the study made use of a range of technologies to adapt conventional software to their needs, and identified practical limitations and challenges in those adaptations, including suggestions for novel and intuitive interfaces, optimized control-surface layouts, and repurposing opportunities in text-input techniques.

The study presented in this paper is aimed at identifying text editing actions that are routinely performed by the users when composing a text document and that are not directly supported by common word processors. The results of this study will help a design of a novel word processing interface controlled by device with a limited number of input signals, operated by people with certain motor disabilities.

Nonverbal vocal interaction (NVVI) is an input modality by means of which users control the computer by producing sounds other than speech. Previous research in this field has focused mainly on studying isolated instances of NVVI (such as mouse cursor control in computer games) and their performance. This paper presents a study with 36 elderly users in which basic NVVI vocal gestures (commands) were ranked by their perceived fatigue, satisfaction, and efficiency. The results of this study inspired a set of NVVI gesture design guidelines that are also presented in this paper.

This paper presents Humsher -- a novel text entry method operated by the non-verbal vocal input, specifically the sound of humming. The method utilizes an adaptive language model for text prediction. Four different user interfaces are presented and compared. Three of them use dynamic layout in which n-grams of characters are presented to the user to choose from according to their probability in given context. The last interface utilizes static layout, in which the characters are displayed alphabetically and a modified binary search algorithm is used for an efficient selection of a character. All interfaces were compared and evaluated in a user study involving 17 able-bodied subjects. Case studies with four disabled people were also performed in order to validate the potential of the method for motor-impaired users. The average speed of the fastest interface was 14 characters per minute, while the fastest user reached 30 characters per minute. Disabled participants were able to type at 14 -- 22 characters per minute after seven sessions.

This paper introduces a text entry application for users with physical disabilities who cannot utilize a manual keyboard. The system allows the user to enter text hands-free, with the help of "Non-verbal Vocal Input" (e.g., humming or whistling). To keep the number of input sounds small, an ambiguous keyboard is used. As the user makes a sequence of sounds, each representing a subset of the alphabet, the program searches for matches in a dictionary. As a model for the system, the scanning-based application QANTI was redesigned and adapted to accept the alternative input signals. The usability of the software was investigated in an international longitudinal study done at locations in the Czech Republic, Germany, and the United States. Eight test users were recruited from the target community. The users differed in the level of speech impairment. Three users did not complete the study due to the severity of their impairment. By the end of the experiment, the users were able to enter text at rates between 10 and 15 characters per minute.

We are interested in understanding human personality and its manifestations in human interactions. The automatic analysis of such personality traits in natural conversation is quite complex due to the user-profiled corpora acquisition, annotation task and multidimensional modeling. While in the experimental psychology research this topic has been addressed extensively, speech and language scientists have recently engaged in limited experiments. In this paper we describe an automated system for speaker-independent personality prediction in the context of human-human spoken conversations. The evaluation of such system is carried out on the PersIA human-human spoken dialog corpus annotated with user self-assessments of the Big-Five personality traits. The personality predictor has been trained on paralinguistic features and its evaluation on five personality traits shows encouraging results for the conscientiousness and extroversion labels. Index Terms: Automated personality prediction from speech, human–human dialog analysis.

This paper reports a comparison of user performance (time and accuracy) when controlling a popular arcade game of Tetris using speech recognition or non-speech (humming) input techniques. The preliminary qualitative study with seven participants shows that users were able to control the game using both methods but required more training and feedback for the humming control. The revised interface, which implemented these requirements, was positively responded by users. The quantitative test with 12 other participants shows that humming excelled in both time and accuracy, especially over longer distances and advanced difficulty levels.