A sound effect captioning system is now available for YouTube videos that can automatically detect music,sound and laughter in videos. YouTube already has had since 2009, automated captions. Now new features are introduced in surge of expanding the possibilities. These captions for sound effect in videos are brought to us through machine learning.Now millions of videos on YouTube are having sound effects and added captions : [APPLAUSE], [MUSIC], and [LAUGHTER].
These three captions are most frequent manually captioned sound effects, YouTube is initially improvements for its deaf and hard of hearing users. According to company captions like ringing, barking, and knocking are next in line, although it needs more deciphering as compare to simple laughter or music.
“While labeled ambient sound information is difficult to come by, we were able to generate a large enough dataset for training using weakly labeled data,” Google engineer Sourish Chaudhuri wrote in a blog post.
YouTube says it is similar to programming of detecting objects in images,but for object recognition they faced hurdles. For just those three sounds, the program is set by YouTube engineers in which they had to teach the program for detecting these sounds. They separate them temporarily after that inserted the recognized sound into the captions. Engineers are working to enhance the system thus the sound effects occurring at the same can also be recognized by system i.e Laughter and talking. Another challenge was to find a large enough data set to train the system that wasn’t already adequately labeled by manually inputting the data.
A question comes to ones’ mind is why these three effects applause, music, and laughter? Besides the reason of being the most frequently
manually adjusted labels in the close captioning system, all of these three have one meaning. A “ring,” YouTube explained, in offering an example, could be a ring from a doorbell, a phone, or an alarm, presenting a whole new challenge for the software.
According to YouTube, Daily over 15 million videos with automatic captioned are being viewed. Auto captions test results are concluded by YouTube that tells two thirds of users opinion is, these effect labels enhanced the overall experience.
The improved captions are now available on YouTube.