November 19, 2009

YouTube Audio Transcription

YouTube added a feature that generates video captions. "We've combined Google's automatic speech recognition (ASR) technology with the YouTube caption system to offer automatic captions, or auto-caps for short. Auto-caps use the same voice recognition algorithms in Google Voice to automatically generate captions for video."

The feature only works for English and it's been enabled for a small number of channels that usually feature talks and interviews: UC Berkeley, Stanford, MIT, Yale, UCLA, Duke,UCTV, Columbia, PBS, National Geographic.


Another new feature is auto-timing, which lets you upload the transcription of a video and it automatically generates the time codes. "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."

Since Google's speech recognition technology is not perfect, it would be useful to generate the captions and then to manually edit them to correct the mistakes.

Automatic captions make YouTube videos more accessible: you can watch videos with the sound off and you can translate the captions into another language using Google Translate.
at

24 comments:

  1. AnonymousNovember 19, 2009 at 6:35 PM

    I think this is great, but I wish they would go further.

    Yesterday, I wanted a reasonably accurate (google voice like) transcript from the Diane Rehm Show. The DR Show charges $19 for a transcript -- I'm not sure why.

    I'd like to see Google offer services to websites like the DR Show where they can get a not perfect, google voice like transcript of their show made to accompany their mp3.

    ReplyDelete
    Replies
    1. SwBratcherMarch 17, 2012 at 5:01 PM

      You don't want a google voice transcription, as it's awful. I once used phonetag and their transcription rocks compared to google voice's engine. Once google buys phonetag it'll be better.

      Delete
  2. lifted trucksNovember 19, 2009 at 10:19 PM

    That's amazing, now by using this, there may be no frustration to think over for the great caption... its awesome...things goes so easy and without fear.. its great..!!1

    ReplyDelete
  3. son_of_malcomNovember 20, 2009 at 1:00 AM

    What would be really great is to be able to download the captions file seperately, once the timings have been automatically applied. Also, do auto-timing captions have an option to translate them or is it just the automatic speech-text ones that do?

    ReplyDelete
  4. YoliNovember 20, 2009 at 4:53 AM

    This is truly beneficial for deaf or people who are hearing-impaired and the language translation option is also great for the international community. But it seems to have no SEO value. Or does it ?

    ReplyDelete
  5. UnknownNovember 20, 2009 at 4:20 PM

    Great! Now youtube is international!

    ReplyDelete
  6. MuzonNovember 20, 2009 at 10:48 PM

    I always loved Google that they think of users and do only useful services.

    ReplyDelete
  7. sportisotNovember 21, 2009 at 4:39 PM

    I like YouTube so much...

    ReplyDelete
  8. Roshan JoshiNovember 22, 2009 at 2:15 AM

    very nice. hopefully they would come up with other languages soon as well.

    ReplyDelete
  9. Umang AminNovember 25, 2009 at 11:30 PM

    I like it that's Really nice future ...But that text Include in Google Search ranking ?

    ReplyDelete
  10. web development irelandNovember 29, 2009 at 7:34 AM

    nice feature, especially the translation bit..

    ReplyDelete
  11. seo resumeNovember 29, 2009 at 12:04 PM

    There is no doubt that YouTube Video rock and its best.

    ReplyDelete
  12. chiffmonkeyMarch 7, 2010 at 3:41 AM

    It's absolutely awful.

    It seems to be completely deaf as to what people are actually saying and offers WAY off the mark captions.

    ReplyDelete
  13. JBApril 13, 2010 at 8:47 AM

    LOL even though most of it doesnt make sense its great entertainment- once on a Blendtec video it came up as 'Don't Breathe Air'

    ReplyDelete
  14. Richard DaddApril 26, 2010 at 4:38 AM

    "Not perfect" is a bit of an understatement.

    And when you say "The feature only works for English" surely what you in fact mean is: "the feature doesn't fail quite so spectactularly if you speak English in a clear American accent."

    Any actual English people may as well be speaking Portuguese in my experience.

    Let's be honest, it shouldn't be released from Beta status until it works better. At present its main function is as a comedy generator.

    See how it hilariously renders classic works of literature:

    http://www.youtube.com/watch?v=syFXOH3t4CY

    ReplyDelete
  15. CandidJune 1, 2011 at 8:04 AM

    Transcribing your audios is now easy with Secure Transcription, email to support@securetranscription.com or dial 18664108787 to our toll free number.

    ReplyDelete
  16. AnonymousDecember 25, 2011 at 12:59 AM

    So far I've used Google Trascribe Audio on two music videos on YouTube, and the results have been amazingly laughable. Nothing in either video translation resulted in a rational thought. Using it made me dumber. I award Google no points, and may God have mercy on its soul.

    ReplyDelete
  17. Carey SuanteJanuary 29, 2012 at 2:18 AM

    You can't really rely on Google softwares to transcribe your videos.

    It's wise to check out a transcription service provider like www.transcriptionpro.net, which makes outsourcing videos for transcription easy and secure with their online transcription software.

    ReplyDelete
  18. rodoFebruary 2, 2012 at 5:51 AM

    yes that is nice functionality, one day it will work perfectly

    ReplyDelete
  19. ElevatelocalMarch 6, 2012 at 8:09 AM

    Is there a tool that accurately does this?

    ReplyDelete
  20. AnonymousJune 27, 2012 at 1:02 PM

    THis is great! Thanks to both companies for their attention to accessibility issues. This is a great step in the right direction.

    Thanks again.

    ReplyDelete
  21. Audio TranscriptionOctober 10, 2012 at 10:31 PM

    Google's voice recognition technology is not still matured to produce accurate transcription for non-American accents, or with people speaking quickly or multiple speakers audio files. If you have more than one voice it is almost impossible to get a good transcript.Better go for a manual transcription services.

    ReplyDelete
  22. expect perfectionApril 1, 2016 at 9:42 AM

    Automatic speech recognition (ASR) technology is very cool. I Think it is very helpful Audio transcription technology if YouTube caption system to offer all those thinks.

    ReplyDelete
  23. Cory TreffilettiJanuary 22, 2018 at 11:27 AM

    The Voicera tool is now available to transcribe meetings and calls and costs less than Google or other transcription services, plus offers note taking through an AI. Try that out if you have a moment at www.voicera.com

    ReplyDelete

Note: Only a member of this blog may post a comment.