Yes, this seems to be a perennial question for AIR-L. And the answer has thus far remained the same: automatic transcription just isn't there yet. If you see some of the transcriptions offered by YouTube, you'll know why. If you are only looking for automatic tagging of keywords, there are tools and services available to do this, with the better ones getting quite expensive, but for accurate transcriptions, humans are still needed. I haven't used Mechanical Turk for transcription, but I'd be interested to know if anyone on the list has... For reference: http://www.cs.cmu.edu/~mrmarge/icassp10margem.pdf http://waxy.org/2008/09/audio_transcription_with_mechanical_turk/ http://chronicle.com/blogs/profhacker/the-reliability-efficiencyaffordabilit... http://castingwords.com/ (They seem to use MTurk, but wrap it for customers.) Best, Alex On Fri, Jun 24, 2011 at 1:09 PM, <jhuns@vt.edu> wrote:

I think many people are looking and have been looking for this holy grail.  What most people have done when they have a good deal of data is hire a transcription service to do it for them _______________________________________________ The Air-L@listserv.aoir.org mailing list is provided by the Association of Internet Researchers http://aoir.org Subscribe, change options or unsubscribe at: http://listserv.aoir.org/listinfo.cgi/air-l-aoir.org

Join the Association of Internet Researchers: http://www.aoir.org/

-- // // This email is // [x] assumed public and may be blogged / forwarded. // [ ] assumed to be private, please ask before redistributing. // // Alexander C. Halavais, ciberflâneur // http://alex.halavais.net //

Thank you - sounds like an interesting DIY solution to a problem that most of us seem to share... I am indeed considering paying a transcription service to do the work but having to operate within the restricted budget of a PhD I thought I would try this list first since a lot of useful suggestions have come through it before. keep them coming! wishing all a good weekend, F ________________________________________ From: Peaslee, Robert [robert.peaslee@ttu.edu] Sent: 24 June 2011 15:11 To: FILIPPO TREVISAN; air-l@listserv.aoir.org Subject: Re: [Air-L] voice recognition software for interview transcription? Hi Filippo, et al... I have heard tell of folks who listen to their interviews in one ear and then speak them verbatim - more or less in real time - into a software like Dragon Naturally Speaking (which as I understand it is only useful if you want to use your own voice). Word is that this allows you transcribe a 90-minute interview in something like 2-3 hours, rather than 5 or 6. I have never, however, actually met any of these people, I haven't tried it myself, and I would imagine that it takes as much getting accustomed to as does any other skill. Best of luck, r -- Robert Moses Peaslee, Ph.D. Assistant Professor Department of Electronic Media & Communication Texas Tech University Research Chair, AEJMC Visual Communications Division Editorial Board, American Communication Journal College of Mass Communications, TTU Box 43082 Lubbock, TX 79409, USA e: robert.peaslee@ttu.edu p: 806.742.6500, x. 283 f: 806.742.1085 Chain of many mirrors, the cinema is at once a weak and a robust mechanism: like the human body, like a precision tool, like a social institution. And the fact is that it is really all of these at the same time. - Christian Metz On 6/24/11 12:02 PM, "FILIPPO TREVISAN" <f.trevisan.1@research.gla.ac.uk> wrote: Dear AoIR-ers, I'm currently transcribing interview recordings for my PhD and I was looking at voice recognition software as a possible way to speed up the process. however, I have struggled to find a piece of software that is reliable enough to do the job and was wondering whether any of you could recommend one? many thanks in anticipation. best, Filippo ------------- Filippo Trevisan Doctoral Candidate: Digital Politics & Disability Affiliate Researcher American Studies Program Georgetown University Car Barn 308A 3520 Prospect Street, NW Washington, DC 20007 office: 202-687-7878 cell: 703-225-9344 email: f.trevisan.1@research.gla.ac.uk web: http://www.gla.ac.uk/departments/urbanstudies/studentpages/filippotrevisan/ --------- UK contact details: School of Social and Political Sciences University of Glasgow 25 Bute Gardens Glasgow - UK G12 8RS tel: +44 (0)141 330 4377 mob: +44 (0)782 8567252 email: f.trevisan.1@research.gla.ac.uk _______________________________________________ The Air-L@listserv.aoir.org mailing list is provided by the Association of Internet Researchers http://aoir.org Subscribe, change options or unsubscribe at: http://listserv.aoir.org/listinfo.cgi/air-l-aoir.org Join the Association of Internet Researchers: http://www.aoir.org/

another transcription support programme, works quite nice, it's free, available for mac and pc. in addition, the website provides excellent (!!!) information on audio recorders, transcription, software. "f5 is a program which supports the transcription progress, the progress of manually writing down interview situations from video or audio files. Your work is alleviated by f5, because it slows down the playback speed without changing the pitch. You can control the playback with a footswitch or shortcuts. Whenever you pause the playback, f5 automatically rewinds it. An innovative function of f5 is that it synchronises your text with your current media file by adding a cue point to every paragraph. This allows you to directly jump to the passage you want to replay." http://www.audiotranskription.de/english/f5 in case you're dealing with insensitive topics and are mentally prepared, you might want to contemplate making use of the well-educated, deprived global workforce queuing up for a nickel at odesk and the likes. --andreas As a fellow doctoral student, I can relate to the limited budget! I've had good results using VoiceWalker, a free software (see http://www.linguistics.ucsb.edu/projects/transcription/tools.html). Without affecting your original recording, it will loop an audio file (i.e., playing 12 seconds three times), so you don't have to pause, rewind, etc. I've found it very helpful, for what it's worth. -Shannon