Research Projects »

With grant funding from the Small Business Innovation Research (SBIR) program, InvoTek’s current and future development plans include:

Training Caregivers to Help Persons with Alzheimer's Dress

People with dementia lose their abilities to perform activities of daily living when they do not use them. We are developing a new tool for teaching caregivers how to preserve functional ability during dressing. This tool includes a unique simulator that enables the caregiver to practice his or her dressing assistance skills.

Integrating Eye and Head Computer Access for People with Severe Disabilities

We are creating a new computer access method for people with quadriplegia so that they can use both head and eye movements to reduce the physical requirements for typing and moving the computer cursor.

Safe-Laser Keyboard

The objective of this system is to provide an alternate method to access assistive devices and computers for people who are unable to use their hands or voice. This solution will use an eye-safe laser to point at a laser-sensing surface that acts as a keyboard. As the user points the laser at the virtual keys on the laser-sensing surface, information is sent to the computer or other speech output device. The laser-sensing surface developed during this project can transform many non-conductive materials into a large-area photo sensor. We launched the first version of this product in July, 2011.

Play Talk

There is an urgent need for speech generating devices that meet the needs of young children with complex communication needs. This project responds to this need by developing innovative software that will:

(a) Appeal to young children by integrating play and communication;

(b) Be easy for young children to learn and use; and

(c) Be easy and fast for parents and professionals to program “on the fly” within interactions with their children to ensure that the children have access to the language that they require to communicate and learn.

Laser pointing in a safe context for people with disabilities LaserCam

This will be an important new communication method for people with disabilities who cannot speak. All current augmentative communication systems require a person to interact directly with the AAC device in order to generate messages. Direct interaction requires significant training in operating the device as well as frequent and precise setup for many users.

With LaserCam, users communicate by using an exceptionally eye-safe custom laser to select three-dimensional objects, photographs, and symbols in a predefined, laser-safe communication area. As envisioned, the system will permit a facilitator to design an access scheme, which will enable the user to progress seamlessly from low-tech, partner-interpreted pointing to high-tech, independent computer access.

Wii-see, a Wii-based Multimodal Access System for Assistive Devices

The access options for people with disabilities who rely on their hands to control an assistive device have not improved in many years. The proposed project creates a new input method for assistive devices in which the size, shape, and function of the access area are customizable to the needs and abilities of the user. To accomplish this we will use the remote control for the Nintendo Wii to track hand movements over an image palette and translate these movements into computer-control functions. This access method combines the advantages of low-tech and high-tech access techniques to create a new access method that we have named Wii-see.

Prosody Enhanced TTS for Dysarthric Speakers

This feasibility project investigates whether people with complex communication needs can control the prosody of a text-to-speech synthesizer within a unique speech-aware word prediction program. The research team will design a second-generation speech recognition system for dysarthric speakers that includes the ability to measure whether the speaker emphasizes a spoken word. Words that are emphasized by the speaker will then be emphasized by a text-to-speech synthesizer. We will incorporate this speech recognition technology into a “prosody aware” word prediction program so that people with dysarthria can use their speech, in combination with other techniques, to control the prosody of computer generated speech.

Gesture-enhanced Word Prediction for On-screen Keyboards

This project develops exceptionally efficient method for entering words into computers and other assistive devices. We accomplish this by designing an on-screen keyboard that uses gesture-enhanced word prediction techniques. The keyboard is gesture aware in the sense that it enables a person to enter words by moving the mouse cursor toward several letters in a word without requiring the person to select each on-screen letter by dwelling or clicking on it. The combination of word prediction and gesture recognition techniques may reduce the number of on-screen letters that the user must select by up to 75%.

Speech Supplemented Word Prediction

Commercial speech recognition software offers many people with physical limitations an important computer access method. While this access method is reasonably reliable for people with typical speech, people with motor speech disorders (dysarthria) are presently not able to use this technology reliably. The purpose of this research is to provide these people with a unique assistive-device access method that utilizes their speech. The software, named Supplemented Speech Recognition (SSR) for commercialization, enables people with dysarthria to use their speech capabilities to interact with personal computers, with an emphasis on assisted writing.

The central element of the SSR is custom speech-recognition software used in conjunction with word prediction.

The feasibility results for this project are exciting. The average keystroke savings achieved by people with dysarthria on typical sentences was 68%. Commercially available word prediction programs achieved no better than 47% keystroke savings on the same text.

SSR was released as a product in April, 2011.

RERC

InvoTek participates in the AAC-RERC, which conducts a comprehensive program of research, development, training, and dissemination activities that address the NIDRR priorities and seek to improve technologies for individuals who rely on augmentative and alternative communication (AAC) technologies. We research new technologies for people with minimal movement capabilities.