A new voice assistant that improves internet browsing for people with visual impairments has been developed by researchers at the University of Waterloo in Ontario, Canada.
The tool, dubbed Voice Exploration, Retriveal and Search (VERSE), was created in collaboration with Microsoft and researchers at the University of Washington to merge the best elements of existing voice assistants. The result, the researchers claim, is that VERSE is able to make free-form web searchers easier than competing systems.
University of Waterloo PhD student Alexandra Vtyurina said: “Virtual assistants are convenient and accessible but lack the ability to deeply engage with content, such as read beyond the first few sentences of an article, list alternative search results and suggestions. In contrast, screen readers allow for deep engagement with accessible content, and provide fine-grained navigation and control, but at the cost of reduced walk-up-and-use convenience.
“Our prototype, VERSE, adds screen reader-like capabilities to virtual assistants, and allows other devices, such as smartwatches, to serve as input accelerators to smart speakers.”
Through VERSE, users can make commands such as ‘next’, ‘previous’, ‘go back’ or ‘go forward’ to operate a machine. The tool is paired with an app which runs on a smartphone or smartwatch which can serve as an input accelerator. For example, rotating the crown on a smartwatch can advance VERSE to the next search result, section or paragraph of a webpage.
The data used to develop the technology was collected from 53 visually impaired patients, more than half of whom reported using a voice assistant multiple times a day on a range of devices like smart speakers, phones and TVs.
Vtyurina said: “At the outset, VERSE resembles other virtual assistants, as the tool allows people to ask a question and have it answered verbally with a word, phrase or passage. VERSE is differentiated by what happens next.”