Google has only gone and added speech recognition to YouTube in the hopes that automatic subtitles will be produced for those deaf or hearing-impaired among us. While it's a brave gesture, a big step to helping those with disadvantages access content otherwise inaccessible, will it really work? I've had plenty of experience testing out various speech recognition technologies and all of them failed. The only program which has ever come close to understanding what I spoke into the microphone is Crazy Talk.
Mike Cohen, a Google engineer, said this:
I have been working on speech technology for 25 years. There have been steady improvements and this is the culmination of lots of work over years and years. We have had to work on a wide variety of problems like accent variation, background noise, the variation in language, in pronunciation.
The subtitles will appear as YouTube captions, a feature which has been around for quite a while. Google's own blog reads:
'In addition to automatic captions, we’re also launching automatic caption timing, or auto-timing, to make it significantly easier to create captions manually. With auto-timing, you no longer need to have special expertise to create your own captions in YouTube. All you need to do is create a simple text file with all the words in the video and we’ll use Google’s ASR technology to figure out when the words are spoken and create captions for your video'.
See the full article here.
0 comments:
Post a Comment