The technology will also release YouTube videos to a wider foreign market and make them more searchable, which will make it easier for Google to profit from them.
While the technology can include captions only on English-language speech, Google is giving users the choice of using its automatic translation system to understand the captions in 51 languages. That could widen the appeal of YouTube videos to millions of other people who do not speak English but could use the captioning technology to read subtitles in their native language.
The speech identification technology that Google uses to turn speech into text is not new; Google presently uses it to transcribe voice mail messages for users of its Google Voice service. But Ken Harrenstien, a deaf engineer who helped develop the automatic captioning system, said the technology had never been practical on such a large scale.
YouTube already has numerous hundred thousand videos that have closed captions, which normally come from broadcast networks that include them in their programs. Some other online video sites like Hulu and AOL also have some professionally produced videos with closed captioning.
But Mr. Harrenstien said an immense majority of clips on YouTube did not have captions and the new Google technology would create them automatically. YouTube is primarily applying the captioning technology only to a few channels, most of them specializing in educational content. They comprise channels from universities like Stanford, Yale, Duke, Columbia and the Massachusetts Institute of Technology, PBS and National Geographic, and Google itself — its corporate videos will be captioned. The company plans to steadily expand the number of channels that work with the automatic captioning technology.
Google also introduced a associated service to give anyone who uploads a video to YouTube the option of uploading as well a text file of the words spoken in the video. Google will change the text file into captions, automatically matching the spoken words with the files.
The technology, which Google calls “auto-timing,” will make it simple for anyone to add captions to their videos. It will be accessible to YouTube users worldwide, and Google said it would be mainly useful for videographers who shoot from a script, since they already have a file of the text spoken in the video.
In addition to serving people who are deaf or do not speak English, the captions will make it easier for anyone to search text inside videos and find specific snippets within a video.
Google announced the innovative features on Thursday at an event in Washington. The company said they would be accessible by the end of the week.
0 comments:
Post a Comment