What is meta? ×
Meta Stack Exchange is where users like you discuss bugs, features, and support issues that affect the software powering all 131 Stack Exchange communities.

Jeff/Joel and the rest of the StackOverflow Community,

Would you be interested in a community podcast transcription service that utilizes the power of your site's tribe/users/community. It would all be driven by a ridiculously simple-to-use UI and API. The goal would be for your users to stay on your site, but hit a little button/link on the side of the page that says something along the lines of "Contribute 10 seconds of your time to help transcribe Podcast #65" (or whatever you want it to say... it's an API, you have the power!!)


Feature Notes:

It would allow a user to transcribe a 1 to 3 second clip. In the end, it would auto-stitch each "transcriptlet" into the final transcript, then post it. The main goal is an unbelievable simple to use interface that takes the user 15 seconds or less to transcribe a 1 to 3 second clip. If 1,800 (of your 1 mil users) transcribe 2 seconds then your 60 minute podcast is transcribed (potentially in an insanely short period of time).

There will of course be options: like must have 3 (or X) copies/matches of each "transcriptlet" ~roughly match before it is "auto-approved/stitched". And many more, I am not going to get into all of the details here...

Other features: Point-base sub-system, achievement sub-system, ...


Questions for Joel, Jeff and the community:

Anyways, what I wanted to know is, would you guys be interested in a using a service like this. I need a good beta site to try this out on. You could empower your community and get your podcasts transcribed. And be part of building a (another) great service.

And of course, I want to know: Do you think other sites with podcasts and a community would pay for something like this. I am talking like $5, $10 or $15/hr for transcription (rather than the $200+/hr that some people charge). There will also be a free service (X minutes/month or whatever) too, but the premium service would cost a very small amount. Or possibly it will be ad supported. But I know I just listened to you guys talk about the dissapointment with Google AdSense... Anyways, it's starting out as free for sure (during beta). And most likely free for you guys always :) Because I want StackOverFlow to be transcribed (I will pay the $5 per podcast :)


What inspired this project:

  • The end of every single one of your podcasts (wiki comments)
  • The fact that I would like to search and replay segments of the podcast for someone, but can never remember which is which, due to the lack of podcast transcribing
  • I like your idea of the wiki, but that requires people to listen to the mp3 with a player, keep track of timing and stop/replay/pause the track, and update the wiki properly. It is a bit time consuming.
  • After listening to "Tribes" by Seth Godin, it really made me think that this would work no problem with a community like yours.
  • It would be a fun little app/service/site to write with my development team.
  • We would be solving a problem that exists for a lot of podcast/communities. (Hanselminutes, twit, ...) Anyone with a Tribe really.
  • And yes, money. Money is good side-effect of providing an elegant solution to a problem.


Current Project Status:

I had my first meeting with the development team, we have initial database design, very rough Balsamiq Mockups, FogBugz Wiki/Tasks created and a bunch of other planning done. They asked me:

"Well how do you know Jeff and Joel would even want to use something like this if we spent the 6 to 8 weeks (ok 4-6 months) to developed it?"

I said, I don't know, but I have very strong feelings that they would. So that is why I am asking. It would be GREAT if one of you or both of you could respond.

We can make this happen. I am ready to pull the trigger, we might do it anyways. But if I saw a reply from you guys that said "Heck yes we would use that". Then it would be a no-brainer for us to make it happen. If you said "You are a frikin' IDIOT"", then maybe I might back-off and think of another idea


Quick background:

I own/run a small development company in Grand Rapids, MI. We have run and successfully delivered many software products from the very big to the very small. We can rock it out.


Thanks!

Thanks for your time. I apologize for the very long message and the loose grammar. It happens when I get excited about something.

share|improve this question
6  
If you need a tool to estimate the project's time sixtoeightweeks.com –  Ólafur Waage Sep 1 '09 at 0:29
1  
Dude, who made that site? Did you? That rocks! I just listened to the podcast where they talked about that :) –  mschmidt42 Sep 1 '09 at 0:48
1  
I made the site. And thanks :) –  Ólafur Waage Sep 1 '09 at 0:54

2 Answers 2

I'm not going to be in either of the camps (of Heck yes and you're an idiot).

I do think this is a pretty large service for something quite simple. But it's something that hasn't been tested.

When I first read this I thought immediately of reCaptcha and how they are crowd sourcing bad data from OCR's. Which when you think of at first as an impossible and crazy idea.

There are ofcourse many factors to include. Like duplicate translations. What if a person just enters garbage. How do you tag such garbage. Who and how do you handle garbage data. etc etc.

Will the idea of needing X amounts of duplicates work. How can you match them (different punctuation styles, spelling errors etc).

share|improve this answer
    
Yeah, we have a lot of ideas laid out for a lot of that. The "Site Owner" admins will have lots of options on how to verify/auto-approve the transcriptlets. Options like: ignore punctuation, whitespace, capitalization and more. And to weed out the garbage data, we will have a minimum match requirement. So if someone puts in "asdf". but 3 other people put in ~roughly~ "then he said this" and the site admin had the minimum match set to 3 per transcriptlet, then the "asdf" would be thrown out. And if a particular user started having a patter of that, then we would deal with them accordingly. –  mschmidt42 Sep 1 '09 at 0:46
    
But yeah, there are a lot of things going on in the project (design-wise). We have an initial layout and proof-of-concept for the audio analysis/splitter portion. And we are working on some algorithms for the "auto-transcriptlet-stitching system": which attempts to deal with situations where the audio splitter broken inside of a word (happens 10% of the time or so). But we also have a final "manual stitching GUI" that will allow site admins and/or power users (users reaching a certain threshold of approved transcriptlets and low down-votes) to clean things up in an east to use UI. –  mschmidt42 Sep 1 '09 at 0:52

Sure, I'd certainly use that, but it's not easy and surprisingly expensive to do well.

I think a bunch of people have built similar things using Amazon Mechanical Turk.

Transcription services certainly exist; I've looked into this before. We tried using them to get transcriptions of a bunch of video interviews. Basically, the cheaper transcriptions were so bad that they were literally unusable even for our simple intended purpose of just being able to quickly scan through interview footage picking out the good stuff. It is amazing how poor a job people do on technical jargon, industry buzzwords, names, etc., when they don't know the domain. There are very expensive technical transcription services, usually with specialties like legal and medical, that do a better job, but they're not really affordable.

share|improve this answer
    
EXISTING SERVICE ISSUE: I did a lot of research on existing services, and yes, they are very expensive. Like I said, we could go the free route, small fee route, and/or targeted ads. Our goal is to target sites that have a tribe willing to contribute 10 seconds of their time. I've also looked into the "automated transcription software"... absolutely terrible. I am convinced we need humans to do the job (at least for the next 5 years minimum). The software side of things that we write will be there just to manage all of the "micro-jobs" that the community is doing and then put them together. –  mschmidt42 Sep 2 '09 at 0:34
1  
JARGON ISSUE: That's the great thing about letting YOUR community transcribe it using our easy-to-use interface/api. They know your voice, Jeff's voice. They know the jargon. They know TCP/IP is not "tepee". And this is true with each Tribe/Community. They all have their own speakers and jargon. Your people know you so the transcriptions are easier for them. Most likely, they already listen to the podcast in full once. I already have a proof-of-concept of the audio-splitter. I have Podcast #65 busted out into hundreds of 1 to 2 second clips. it is pretty nice for the first 3 hours into it. –  mschmidt42 Sep 2 '09 at 0:35
    
sounds like you've thought about it a lot... so, to answer your original question, yeah, we'd definitely use it for the podcast. –  Joel Spolsky Sep 2 '09 at 0:38
    
excellent. Thanks for your time and the response. You rock. Go FogCreek!!! –  mschmidt42 Sep 2 '09 at 1:21
    
Thanks for the note about "Amazon Mechanical Turk". I am going to research that a bit. Looks similar, not exactly the same, but I'm glad I know that it exists. Thanks. –  mschmidt42 Sep 2 '09 at 11:44

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .