Hi Sophie,
We don’t yet have any TEI template on our website for the TEI we use (yet). This work is part of our ESRC project, Digital Futures, that has built on online qual data browsing system and which will provide citation to interview extracts within the system: http://ukdataservicedigitalfutures.wordpress.com/ and http://ukdataservice.ac.uk/about-us/projects/digital-futures/details.aspx.
We are using 3 metadata standards: the Data Documentation Initiative (DDI) (for collection level records), TEI for individual transcripts and Qudex for object relations which allows powerful description of objects, sub-objects (interview extracts extracts) and relationships between objects. http://www.data-archive.ac.uk/create-manage/projects/qudex?index=1
We are in the process of starting to document this in some detail, now the standards have been agreed. I also will be putting up a longer blog soon with exemplar DDI, TEI and QuDEx files. I can certainly send an anonymised TEI file on request to anyone who wants a copy. We use only a minimal set of tags.
Best wishes,
Louise
-----Original Message-----
From: Research Data Management discussion list [mailto:[log in to unmask]] On Behalf Of Sai Deng
Sent: 26 September 2013 14:46
To: [log in to unmask]
Subject: Re: Voice Recognition Software for transcribing interviews
Importance: High
Hi Louise,
Would you provide more details and resources?
I only found this page in UK Data Archive: http://ukdataservice.ac.uk/manage-data/format/transcription.aspx
We're interested in transcribing veteran interview audios and videos from the history department. We have many of those interviews lacking full text. The metadata is not encoded in TEI, but DC only.
I'm new to voice transcription. If you and/or anybody else could provide some guidance to beginners, that would be great.
Thanks!
Sophie
-----Original Message-----
From: Research Data Management discussion list [mailto:[log in to unmask]] On Behalf Of Corti, Louise
Sent: Thursday, September 26, 2013 7:54 AM
To: [log in to unmask]
Subject: Re: Voice Recognition Software for transcribing interviews
Hi Andy,
Yes, most use the Text Encoding Initiative (TEI) metadata capture. It suits transcriptions well and enables mark up of almost anything in speech or structure. Lots of resources on the TEI site.
We also have TEI in production for interview transcripts and self-directed writing at the UK Data Archive, so happy to show you a template of an XML TEI document that we use if you'd like.
Best wishes,
Louise
__________________________
Louise Corti
Director, Collections Development and Producer Relations __________________________ T +44(0) 1206 872145 E [log in to unmask] W www.data-archive.ac.uk __________________________ UK Data Service UK Data Archive University of Essex Wivenhoe Park Colchester Essex CO4 3SQ
__________________________
Legal Disclaimer: Any views expressed by the sender of this message are not necessarily those of the UK Data Service or the UK Data Archive.
This email and any files with it are confidential and intended solely for the use of the individual(s) or entity to whom they are addressed.
----Original Message-----
From: Research Data Management discussion list [mailto:[log in to unmask]] On Behalf Of Andy Turner
Sent: 25 September 2013 16:25
To: [log in to unmask]
Subject: Re: Voice Recognition Software for transcribing interviews
Importance: High
Haha :-) I dinna ken.
Phil Woodland (copied in) looks to be an expert on transcription technology working on a current EPSRC project [1, 2].
I wonder if there is a recommended metadata standard for interview transcriptions. I would have thought that the categorised values of the accents involved would be part of this. I expect that the person transcribing the interview would generate much of this data.... For some interviews it is unwanted to get the interviewee to read out a standard text for automatic classification purposes.
There are lots of transcriptions out there... I wonder how good all the metadata is...
[1] http://www.languagesciences.cam.ac.uk/pdfs-from-launch-event/phil-woodland-pdfs
[2] http://www.natural-speech-technology.org/
Andy
http://www.geog.leeds.ac.uk/people/a.turner/
-----Original Message-----
From: Research Data Management discussion list [mailto:[log in to unmask]] On Behalf Of Valerie McCutcheon
Sent: 25 September 2013 15:44
To: [log in to unmask]
Subject: Re: Voice Recognition Software for transcribing interviews
That is why all us West of Scotland folk go shopping for pretty toes (potatoes)
-----Original Message-----
From: Research Data Management discussion list [mailto:[log in to unmask]] On Behalf Of McDonagh, Gregor
Sent: 25 September 2013 15:32
To: [log in to unmask]
Subject: Re: Voice Recognition Software for transcribing interviews
About ten years ago my wife was a disability advisor in universities so I played with Dragon. Even if people are prepared to do the prep of feeding back their pronunciations this stage may frustrate. A few words in Dragon simply wouldn't accept my pronunciation of the 'a' in "tab" and that was the end of it. I admit I have had elocution lessons, but sharely [sic] a Coventry originating accent isn't that strong wrt to 'a'.
Gregor McDonagh.
-----Original Message-----
From: Research Data Management discussion list [mailto:[log in to unmask]] On Behalf Of Tim Banks
Sent: 24 September 2013 17:40
To: [log in to unmask]
Subject: Re: Voice Recognition Software for transcribing interviews
In my experience, the reason 'why voice recognition software is not more commonly used' is simply down to the capability of the software currently available. As you say, voice recognition software (Dragon Naturally Speaking Pro being one of the more popular options) has to learn your voice and even then you have to speak very clearly and deliberately, ideally with short gaps between each word, in order for it to work with a high degree of accuracy (& let's face it, when transcribing interviews, accuracy is very important). Apple's Siri service uses some of the most advanced voice recognition technology currently available, running on hugely powerful server farms but still falls very short of being able to accurately transcribe a typical interview.
Re-speaking an interview is the best compromise between speed and accuracy and I suspect this will be the case for the foreseeable future.
Tim
------------------------
Faculty IT Manager
Faculties of PVAC & ESSL
University of Leeds
Leeds
LS2 9JT
-----Original Message-----
From: Research Data Management discussion list [mailto:[log in to unmask]] On Behalf Of Howe, Veronica
Sent: 24 September 2013 17:08
To: [log in to unmask]
Subject: Voice Recognition Software for transcribing interviews
A great deal of research data consists of transcripts of interviews recorded using digital voice recorders and then transcribed, typically into MS Word, by someone listening to it in real time and typing what they hear. Converting digital audio files into digital text files in this way seems quite labour intensive and therefore costly, which makes me wonder why voice recogniton software is not more commonly used.
I gather that the main problem with voice recognition software is that it is designed to recognise a single voice, rather than the two or more voices in a typical interview situation. I understand that some researchers have overcome this by playing back the interview audio so the (recognised) interviewer can repeat what the interviewee said, which is presumably quicker than transcribing it, even allowing for correcting the inevitable inaccuracies.
Given that the interview is such a common research methodology, I would be interested to know if anyone has any experience of using voice recognition software, or using products that can do this to sufficiently high standards.
Veronica Howe
Research Data Manager
Archives and Information Management
Library Services
Kings College London
Room 102
26-29 Drury Lane
London WC2B 5RL
0207 848 1030
Email: [log in to unmask]
Web: www.kcl.ac.uk/library/using/info-management/index.aspx
Connect with us at twitter.com/kingslibraries
This message (and any attachments) is for the recipient only. NERC is subject to the Freedom of Information Act 2000 and the contents of this email and any reply you make may be disclosed by NERC unless it is exempt from release under the Act. Any material supplied to NERC may be stored in an electronic records management system.
|