Around the world, there are many people with hearing impairments. This doesn't mean that they are necessarily deaf -- they may instead have severe hearing loss. Someone in my family, for instance, has to wear hearing aids. For these people, captioning on videos (text displayed on screen) can be a necessity, making it possible to enjoy a TV show or movie. Heck, it can be used by people without hearing issues too; they may need to mute their TV as to not wake family members.
Nowadays, captioning extends to internet videos too, including the very popular YouTube. In fact, today, Google announces that it has exceeded 1 billion captioned videos! While this is certainly an amazing accomplishment, the service's automatic speech recognition can sometimes be very wrong -- even comically so.
"Google first launched video captions back in 2006. Three years later these efforts were taken to a whole new level with automated captions on YouTube. This was a big leap forward to help us keep up with YouTube’s growing scale. Fast forward to today, and the number of videos with automatic captions now exceeds a staggering 1 billion. Moreover, people watch video with automatic captions more than 15 million times per day," says Liat Kaver, Product Manager, Google.
Kaver also says, "A major goal for the team has been improving the accuracy of automatic captions -- something that is not easy to do for a platform of YouTube’s size and diversity of content. Key to the success of this endeavor was improving our speech recognition, machine learning algorithms, and expanding our training data. All together, those technological efforts have resulted in a 50 percent leap in accuracy for automatic captions in English, which is getting us closer and closer to human transcription error rates."
In other words, Google's automated captioning is getting better, but it is still not on the same level as human transcribing. Quite frankly, computers may never be able to perfect the captioning, but the search giant deserves kudos for continually improving.
As an example of just how wrong the captioning can be, famous YouTube vlogger Jenna Ezarik recently released a very funny video highlighting it. As per the top image, she and her sister do not normally talk about retired NBA star Shaquille O'Neal!
What has your experience been with captioning on YouTube? Tell me in the comments.