Speech Technology Magazine

 

YouTube Expands Video Transcription Option for All

Businesses can benefit from an expanded audience base.
By Leonard Klie - Posted May 3, 2010
Page1 of 1
Bookmark and Share

Back in November, YouTube added a feature that generates captions and transcripts for videos uploaded to its servers. At the time, the feature had been enabled for only a small number of universities, as well as channels like PBS and National Geographic—media outlets that traditionally air a lot of talks and interviews.

As of early March, YouTube began rolling out the robo-transcription option across its entire Web site, enabling its use by businesses and consumers alike.

YouTube, which is owned by Google, uses Google’s automatic speech recognition (ASR), speech-to-text, and voice search technologies, together with its own captioning system, to generate audio transcripts of the videos. People who post videos to YouTube can download the autogenerated transcript, make any necessary corrections, and upload the transcripts along with the video. People with existing content already posted to YouTube can select a “request processing” option to add captions to their video tracks.

For businesses that frequently post content, such as training videos, product demonstrations, company meetings and seminars, and video tours, the transcription option strengthens an already powerful and free marketing tool. With as much as 74 percent of American consumers visiting YouTube at least once every two weeks, the video-hosting service is a huge marketing tool for millions of businesses. Companies like Home Depot use the service to display how-to videos for the do-it-yourself home handyman, and the Girl Scouts use it for selling cookies. Electric Tour Co., which offers tours of San Francisco and Sausalito, Calif., and Charles Smith Pottery, which is based in Mobile, Ala., have also posted videos to YouTube. Though neither has used the transcription service yet, both told Speech Technology it was something they would look into.

Chris Dale, a Google spokesman, says businesses can benefit greatly from the service by expanding their audiences.

Google was quick to point out that the transcription option is limited right now in that it works only for videos with audio in English and for videos that have very clear audio tracks. “But it will get better over time,” Dale says.

Google also plans to expand the feature to include more languages, the company said in a blog post. Additionally, users can now generate the transcript and then run it through Google’s automated translation engine “to generate the text in as many as 50 languages,” according to Dale. 

Google expects to have as many as 10 billion video clips captioned by the end of the year. The company further said one of the ultimate goals for the transcription option is to make YouTube more accessible to the hearing-impaired and those learning English as a second language.

Beyond that, video transcription has lots of uses online. It makes video content searchable, helps in search engine optimization, and could even be used to generate targeted advertising. “The captioning makes searching for material on YouTube simpler and more efficient,” Dale says.

Page1 of 1