Inclusive Logo
2071 Adam Clayton Powell Jr. Blvd., 2 New York, NY 10027 United States
Phone: (347) 927-5770    Email:

Understanding The Limitations Of Automated Captioning For The ASL Community

Automated captioning is a feature that has been around for a while, but has recently hit the spotlight with many meetings and events shifting to virtual platforms. Automated captioning is done by voice recognition software and machine learning algorithms. It’s all the rage right now.

But is it worth the excitement? Many people think automated captioning makes their videos accessible for Deaf and hard of hearing viewers. Unfortunately, because automated captioning is not done by humans who can understand the subject of the video, people’s accents, background noise, and grammar and punctuation, automated captioning is not an ideal solution.

It should come as no surprise that automated captioning is typically free. This is probably one of the factors that people look at when researching options for their videos. Does opting for the free, easier or quickest way to add captioning benefit viewers who need the captioning? Suffice to say, it does not. As ICS’ in-house captioning professional explains:

“Automated captioning does not provide true accessibility because most of the time the captions are of such poor quality that content is not accurately communicated. Poor audio quality, background noise, mispronunciations, accents etc. all contribute to inaccurate auto-captions. Automated captions should only be a starting point. Only when a human puts in the time to edit those captions does it become accurate.”

Automated captioning does have some beneficial use. For example, when adding captions to a video already created, a captioning professional may use the automatically generated captions as a baseline, then take the time to go back and review the captioning, making corrections where needed. Having the captions done live by a transcriber or having a professional add captions after the video is created is the best way to go.

Voice recognition software is not designed to filter out background noises or overlapping conversations, while transcribers are able to acknowledge more than one person talking and interpret the background conversations to the best of their ability. On top of that, transcribers are experts with grammar and punctuation and can ensure the captioning is accurately typed so we, the viewers, can fully understand the videos without having to try and figure out where one sentence begins and ends.

According to the University of Minnesota Duluth, “YouTube automatic captions typically provide about 60-70% accuracy, which means that 1 in 3 words can be wrong.” On the other hand, the accuracy rate for live captioning by humans is much higher – between 96 and 99%! To learn more about real-time captioning check out this article:

After a brief review of automated captioning and live captioning, it is safe to say that live captioning or professional post-translation services for videos already created, provide more complete and equal access for the Deaf and hard of hearing community. If you are curious and want to learn more about automated and live captioning, don’t hesitate to reach out to Inclusive Communication Services at (917) 960-3804 or by email at

Leave a Reply

Your email address will not be published. Required fields are marked *

Try the Inclusive Experience

10% off your first service request


Inclusive Impact

Need a professional sign language interpreter, caption provider, or media translator?

Making ADA accommodations simple and inclusive!

We are here to help you!