Today, Thursday, May 19, 2022, marks the 11th annual Global Accessibility Awareness Day (GAAD), a day with the purpose of getting everyone talking, thinking and learning about digital access and inclusion to enhance the lives of the more than One Billion people living around the world with disabilities. GAAD’s overall goal is to disrupt the culture of technology and digital product development to include accessibility as a core requirement, rather than address it as an afterthought.
In light of this day, AppTek is particularly proud of our collaboration with Gallaudet University on the creation of GoVoBo, the universal automatic captioning and translation application for deaf and hard of hearing (DHH) users around the globe. The application was developed by and for the DHH community. GoVoBo will be on stage this evening at the Verizon Forward for Good Accelerator program in New York. GoVoBo was one of seven products chosen from over 170 applicants to be part of this accessibility accelerator program.
GoVoBo was created to fulfill an immediate need to welcome all DHH users around the world into the conversation. As the Covid-19 pandemic drove the fast adoption of web-based meeting platforms, the DHH community found that many of the platforms did accessibility poorly, and many not at all. For these individuals, there was a feeling of reduction of personal autonomy and exclusion from being full members of the community.
With a relentless focus on the deaf and hard of hearing community, the GoVoBo application now brings users universal access to digital communications and information platforms, with an intuitive interface and always available captions and translation designed to offer 24/7 equal access to any conversation or broadcast media.
One of the most important components to offering more inclusion lies in the accuracy of the supporting AI models. AppTek developed its 4D for HLT (Human Language Technology) approach to offer more accurate transcriptions and translations across 80+ languages and hundreds of dialects with a particular focus on bias reduction to ensure every voice can be heard around the world. The multi-faceted 4D approach is performed through the “slicing and dicing” of multiple languages/dialects, domains, demographics, and audio channels to ensure the highest accuracy for all speakers inside the conversation with features such as speaker diarization and identification built in to further improve the readability of captions and allow DHH users to better follow the conversation.
As we continue to look forward to future innovations inside the GoVoBo application roadmap, we are exploring new ways to further bridge the divide between deaf and hearing users. One such initiative is to capture deaf accented speech for speakers with a hearing aid or cochlear implant. Another initiative is to capture “more than words” inside a conversation, such as identifying and visualizing speaking characteristics which help DHH users better identify a speaker’s age or gender, the prosody/emotion of a speaker’s voice, inflections that identify, for example, anger or sarcasm, that may otherwise be missing from the context of the conversation, the presentation of non-speech sounds, and more.
Additionally, beyond the many facets of captioning, AppTek’s technologies continue to expand the horizon of accessibility applications. Today, we are building neural speech synthesis technology designed to speak emergency alerts, weather warnings and school closings for the blind. We are also working on innovations in computer vision for sign language-to-text recognition as seen here and audio descriptions of people and images on-screen to further enable communications.
As usability expert Steve Krug once said “The one argument for accessibility that doesn’t get made nearly often enough is how extraordinarily better it makes some people’s lives. How many opportunities do we have to dramatically improve people’s lives just by doing our job a little better?”
Every step forward in making the lives of an individual better is a step in the right direction.
AppTek is a global leader in artificial intelligence (AI) and machine learning (ML) technologies for automatic speech recognition (ASR), neural machine translation (NMT), natural language processing/understanding (NLP/U) and text-to-speech (TTS) technologies. The AppTek platform delivers industry-leading solutions for organizations across a breadth of global markets such as media and entertainment, call centers, government, enterprise business, and more. Built by scientists and research engineers who are recognized among the best in the world, AppTek’s solutions cover a wide array of languages/ dialects, channels, domains and demographics.