The Art and Science of Real-Time Captioning: Ensuring Accessibility for Millions
Explore the intricate world of real-time captioning, where skilled professionals ensure accurate and timely captions for millions, enhancing accessibility and connectivity.
File
VITAC How Captions Work
Added on 10/01/2024
Speakers
add Add new speaker

Speaker 1: TV is fast. In an effort to keep the viewers attention, programs quickly cut from scene to scene, commentator to commentator, person to person, with dialogue flying a mile a minute.

Speaker 2: It's a wonder that anyone is able to keep up and understand everything that's being said.

Speaker 1: Now imagine translating that audio into text, in real time, for an audience of more than 50 million Americans in the deaf and hard of hearing community, as well as those who choose to watch content without sound. People who rely on that text for their news, entertainment, and other critical information to keep them connected and informed about the world around them. This is the job of a highly skilled set of professionals, real-time captioners. Accurate live captions can only be generated in two ways, by a steno captioner or a voice writer. Professional typists average upwards of 80 words per minute, nowhere near the 180 to 250 words per minute spoken on an average television program. And computer generated captions, like those touted by various artificial intelligence systems, simply are no match for the human experience of the spoken word. Steno captioners use stenotype machines to caption. These machines are simplified keyboard devices that include just 22 keys with no letters, shift keys, or space bars. The keys of the steno machine represent syllables. Captioners write words phonetically based on the sounds they hear, entering them one syllable at a time by simultaneously pressing keys. It's a little like playing the chords on a piano. A steno captioner develops their own shortcuts for commonly used words and phrases, building a dictionary of terms, technical jargon, and proper names with corresponding keystrokes. Captioning an event like the Olympics may require thousands of specialized entries, such as athletes' names and sports terms, and all of these special entries must be entered manually. With the fast-paced nature of television and speeds exceeding 225 words per minute, it's nearly impossible to caption 100% verbatim. And while most on-screen errors are due to technical concerns, captioners are human, and even at 99% accuracy, mistakes do happen. Voice writers use an entirely different tool to create captions. Their voice. Voice writers listen to audio and re-speak what they hear into a highly customized and configured voice recognition system.

Speaker 2: Investigating PIRC. The lava is from Hawaii's Kilauea volcano, comma, which erupted in... Because the engine is trained on a specific voice, errors like those seen on an automated

Speaker 1: engines don't usually occur. Yo, PIRC ain't even care no more. PIRC is just like, I'm off this. Yo, call Zordon, tell him to get us an Uber. Yo, let's kill that old lady that made a holloway. But just like steno captioning, voice writing is not flawless. When the engine doesn't recognize a word, or the captioner wixes her murds, it reaches for the most likely and often incorrect option. As he gobbled the cakes on his plate, comma, the greedy ape said that, as he ate, comma,

Speaker 2: To better ensure high accuracy rates, voice captioners also develop dictionaries in their software that recognize the words they most often use and need ahead of time.

Speaker 1: Amir Bashti. In both steno and voice, the secret to the most accurate captions is the same. Updating dictionaries, reviewing files, and most importantly, practice. At Vitek, we hire only the most experienced voice captioners. All across the nation, our captioning teams work 24-7 in providing timely and accurate captions to millions. Our captioners also are supported by our 24-7 systems and broadcast technology professionals to ensure we are providing the most reliable service for our customers and clients. As media continues to evolve, the world of caption content continues to expand. And we are committed to making the world a better place. As media continues to evolve, the world of caption content continues to expand. And Vitek sees a future where captions and accessible content are the standard. Accessibility for life is not just our motto, it's our mission.

ai AI Insights
Summary

Generate a brief summary highlighting the main points of the transcript.

Generate
Title

Generate a concise and relevant title for the transcript based on the main themes and content discussed.

Generate
Keywords

Identify and highlight the key words or phrases most relevant to the content of the transcript.

Generate
Enter your query
Sentiments

Analyze the emotional tone of the transcript to determine whether the sentiment is positive, negative, or neutral.

Generate
Quizzes

Create interactive quizzes based on the content of the transcript to test comprehension or engage users.

Generate
{{ secondsToHumanTime(time) }}
Back
Forward
{{ Math.round(speed * 100) / 100 }}x
{{ secondsToHumanTime(duration) }}
close
New speaker
Add speaker
close
Edit speaker
Save changes
close
Share Transcript