Automatic captioning system on YouTube now identifies sound effects

While limited, YouTube is venturing out of just automatically captioning what’s being spoken. Google’s technology is now able to caption three specific sounds: [LAUGHTER], [APPLAUSE], and [MUSIC]. YouTube concentrated on these three first because these are exactly the sounds most video producers manually caption in their clips. These three are considered to be “relatively unambiguous” as compared to the sounds lie [RING], which as Google engineer Sourish Chauduri points out, can refer to the ringing of a bell, alarm, or phone. If you’re curious about how the company managed to do so with its tech. You can read more about it in detail in this link. You can see it in action in the video embedded above. Just make sure to click the CC button to see the sound effect captioning system at work.