Please ensure Javascript is enabled for purposes of website accessibility For Real-Time Captioning Exec. Joe Duarte, Accessibility Requires High-Tech and Low-Tech Approaches
top of page

For Real-Time Captioning Exec. Joe Duarte, Accessibility Requires High-Tech and Low-Tech Approaches

Updated: Feb 14

Guest blogger Joe Duarte, Co-CEO of mobile phone captioning app InnoCaption, reflects on his experiences growing up with a hearing loss, overcoming professional obstacles and playing a pivotal role in the advancement of technology that has expanded communication access for people who are deaf or hard of hearing.


Joe Duarte, Co-CEO of InnoCaption
Joe Duarte, Co-CEO, InnoCaption

By Joe Duarte, Co-CEO, InnoCaption


So much has changed over the years for those of us with hearing loss, in terms of attitudes and acceptance as well as technologies that provide more options than ever. The array of devices (including wearables and cochlear implants), software and services can be dizzying, especially for parents of deaf children or people who have recently experienced sudden hearing loss.

The essential need for accessible communications continues to challenge us as a society, and what works for some of us—whether it’s a technology solution or a workaround—may not be the right solution for others. That’s okay—my story isn’t the same as anyone else’s, although there are certainly common obstacles and triumphs that many of us have encountered.


Early Experiences Shape Expectations


As a child in Portugal in the late 1950s, my deafness was misdiagnosed repeatedly. After finally finding a doctor who understood the reality of the situation, my mother was told that the resources needed to support me just weren’t available to us locally. He recommended we fly to the U.S. to visit CHC (then called the New York League for the Hard of Hearing).


At four years old, I received my first hearing aids from CHC while my mother, an elementary school teacher, was provided with six months of training from the organization on how to continue my therapy when we returned to Portugal. This combination of family involvement, community and medical support and technology gave me an opportunity to expand my world.


I came back to America for high school, even though I didn’t yet speak English, adding another barrier to communicating with those around me. Eventually, I went to college, initially part-time, to give me a chance to get more comfortable with English and then full-time to finally earn a degree in biomedical electronics engineering. This brought me to IBM, where I worked on, of all things, sonar systems for submarines. Even though I was not directly involved in its development, I had an opportunity to try IBM’s automated speech recognition (ASR) system on test phone calls; in the 80s, this technology was still in its infancy.


Navigating the Business World


At IBM, I obviously couldn’t use the phone, and while I’d been given a TTY, co-workers and clients didn’t always have the patience for it. Even in-person meetings could be challenging, and, as project lead, I needed to understand everyone’s input. So, I would rely on someone to take notes; sometimes, a low-tech approach is as effective as a device or piece of software.


Later, I started my own firm, Duartek, to design custom audio-visual systems that could make conference rooms and auditoriums more accessible for people with hearing loss. Yet, I still had to navigate the telephone. I took to putting calls on speakerphone and asking my secretary to mouth to me what the other person was saying, then I would speak my replies. Again, a low-tech approach was the answer. But, technology would also play a major role supporting communication for me.


Technology as an Enabler


Joe Duarte, TDI Convention, 2015
TDI Convention, Austin, 2011

People choose different approaches to communications, depending on need, situation and culture. Signing, for example, can be a huge help with social interactions. Technology can also help those who want it, and the capabilities are improving daily.

Hearing aids, for instance, have gotten smaller and more tunable for individual needs, while Cochlear implants (CIs) have advanced significantly over the years. While they may not be for everyone, they can make a number of communications channels more accessible. My wife and I both have CIs, and the ability to listen to the radio or hear most of a conversation is freeing. But, as those with CIs know, it takes significant training to make sense of the new sounds they generate, so it isn’t an instant solution, especially, if you have long-term deafness.


Real-time captioning has been an essential approach for understanding everything, from TV shows and movies to conference speakers and classroom instructors; more recently telephones and, now due to the pandemic, video conferences also support real-time captions. Of course, when it comes to the telephone, TTYs are still helpful to many, but they introduce a time lag to conversations and don’t work as well in a more mobile society.


InnoCaption is Game-Changing Technology


Captioning cell phone conversations empowers users to communicate on their terms. When I first saw the InnoCaption app demonstrated at a conference in 2013, I immediately knew it was a game changer and offered to help the company in any way I could. Now, I’m proud to be part of the leadership team, serving as Co-CEO.


InnoCaption—which is part of the telecommunications relay system supported by FCC funding—can caption phone conversations using ASR. But the best experience comes from a network of stenographers who can transcribe conversations in real time.


While ASR technologies keep improving, they still have a tough time with accents, background noise and poor connection quality. A human stenographer can better deal with these challenges, while also adding details such as multiple speakers, ambient sounds and tone of voice.


Going forward, I believe artificial intelligence will eventually lead to great improvements in ASR. Today, for example, there are a handful of phone apps that can caption in-person conversations. For the foreseeable future, though, human-powered real-time captioning will be key to providing an effective and powerful platform for communication and collaboration that simply didn’t exist before.


56 views0 comments
bottom of page