Re: [CODE4LIB] Transcription/dictation software?

2012-02-27 Thread Joe Hourcle 
On Feb 27, 2012, at 1:52 PM, Suchy, Daniel wrote:

> Hello all,
> 
> At my campus we offer podcasts of course lectures, recorded in class and then 
> delivered via iTunes and as a plain Mp3 download (http://podcast.ucsd.edu).  
> I have the new responsibility of figuring out how to transcribe text versions 
> of these audio podcasts for folks with hearing issues.
> 
> I was wondering if any of you are using or have played with 
> dictation/transcription software and can recommend or de-recommend any?   My 
> first inclination is to go with open-source, but I'm open to anything that 
> works well and can scale to handle hundreds of courses.

I remember seeing a poster on a wall at the University of Maryland presenting 
work on a grant on doing this sort of work ... but I think it was for 
intelligence intercepts, as it was DoD funded and being used for Arabic.

This might've been the project:

Global Autonomous Language Exploration
http://projects.ldc.upenn.edu/gale/index.html

I have no idea why it's on a UPenn website, but it's listed at:

http://ischool.umd.edu/content/research-and-projects

And one of the researchers is Doug Oard, which matches what I remembered.

It might've also been "Supporting Information Access Using Computational 
Linguistics", which was also DoD funded, but doesn't have a website link in 
that list.  And they didn't verify the links to faculty pages, so try one of 
the links to 'Douglas Oard' rather than 'Douglas Ward' if you want to contact 
him.

I also don't know if they were doing full transcription / translation, or if 
they were just looking for specific words to alert a human translator to review 
it.

...

Also, in the earlier list that Todd linked to, Zooniverse was mentioned.  They 
have a framework for mechanical turk-type stuff, but they tend to be science 
oriented, and I don't know if they've ever done audio transcription.  It's not 
exactly what they deal with, but they might be interested in helping, as at the 
2010 DCC, someone said they had the problem of not enough work for their 
volunteers to do.  (although, that might've changed since then).

https://www.zooniverse.org/researchers

-Joe

Re: [CODE4LIB] Transcription/dictation software?

2012-02-27 Thread Tom Keays 
My wife, for a linguistics research project, recorded the responses of her
subjects to a list of questions, so that she could transcribe them and
analyze them. She got Dragon Dictate with the intention of getting a rough
transcription and then, listening to the tape, correct the errors. With so
many subjects, she found that the software, which was trained to her voice,
never gave good enough results to be faster than transcribing them herself
by hand. So, keep that issue in mind. I would imagine that, if there were
just a few lecturers for the podcast, that a speech transcription solution
might work out, provided you could get the lecturers to spend a little time
helping to train the software. However, you need to find out how many
different voices a given dictation software can be trained to reliably
understand. If it is fewer than the number of lecturers, it probably not be
worth it. If it did work, you could send rough transcriptions and the audio
and have Mechanical Turk do clean up edits rather than the whole
transcription.

Tom

On Mon, Feb 27, 2012 at 1:52 PM, Suchy, Daniel  wrote:

> Hello all,
>
> At my campus we offer podcasts of course lectures, recorded in class and
> then delivered via iTunes and as a plain Mp3 download (
> http://podcast.ucsd.edu).  I have the new responsibility of figuring out
> how to transcribe text versions of these audio podcasts for folks with
> hearing issues.
>
> I was wondering if any of you are using or have played with
> dictation/transcription software and can recommend or de-recommend any?
> My first inclination is to go with open-source, but I'm open to anything
> that works well and can scale to handle hundreds of courses.
>
> Thanks in advance!
> Dan
>
> *
> Daniel Suchy
> User Services Technology Analyst
> University of California, San Diego Libraries
> 858.534.6819
> dsu...@ucsd.edu
>

Re: [CODE4LIB] Transcription/dictation software?

2012-02-27 Thread Richard Wallis 
Hi,

Not sure of Mechanical Turk.

However, have used CastingWords [http://castingwords.com/] successfully for
transcribing podcasts - their budget rate is $1/minute.

~Richard

On 27 February 2012 20:22, Nathan Tallman  wrote:

> Is Amazon Mechanical Turk expensive? Anyone know an average cost for an
> hour of audio?
>
> Nathan
>
> On Mon, Feb 27, 2012 at 1:56 PM, Sean Hannan  wrote:
>
> > Mechanical Turk it.
>



-- 
Richard Wallis
Founder, Data Liberate
http://dataliberate.com
Tel: +44 (0)7767 886 005

Linkedin: http://www.linkedin.com/in/richardwallis
Skype: richard.wallis1
Twitter: @rjw
IM: rjw3...@hotmail.com

Re: [CODE4LIB] Transcription/dictation software?

2012-02-27 Thread Yitzchak Schaffer 

On 02/27/2012 15:22, Nathan Tallman wrote:

Is Amazon Mechanical Turk expensive? Anyone know an average cost for an
hour of audio?



I used to do transcriptions on the worker side. I preferred clips of 
30-60 seconds; there seemed to be a better going rate. Often there would 
be a big set of such clips, and I would end up doing a bunch of them. I 
think they went for 10 or 20 cents a clip. But there's a wide range. 
You'll probably want to double them up, i.e. get two or three workers to 
do each bit, and then normalize and diff them for QA.


--
Yitzchak Schaffer
Systems Manager
Touro College Libraries
212.742.8770 ext. 2432
http://www.tourolib.org/

Access Problems? Contact systems.libr...@touro.edu

Re: [CODE4LIB] Transcription/dictation software?

2012-02-27 Thread Nathan Tallman 
Is Amazon Mechanical Turk expensive? Anyone know an average cost for an
hour of audio?

Nathan

On Mon, Feb 27, 2012 at 1:56 PM, Sean Hannan  wrote:

> Mechanical Turk it.

Re: [CODE4LIB] Transcription/dictation software?

2012-02-27 Thread todd.d.robb...@gmail.com 
Dan,

Here's a great list Ben Brumfield has put together that compares a lot of
the options out there (note: there are quite a few in here that are for
manuscript stuff):
https://docs.google.com/spreadsheet/ccc?key=0AsXpm6NXLstzdExZZzhaclhIY1ZtMk5yazJlT1FReUE#gid=0

Tod

-- 
Tod Robbins
iSchool GSA Crew
MLIS Candidate 2012
University of Washington

Re: [CODE4LIB] Transcription/dictation software?

2012-02-27 Thread Jason Stirnaman 
That's what I hear, too. You might also look at 
http://support.google.com/youtube/bin/answer.py?hl=en&answer=100076 

Jason

>>> On 2/27/2012 at 12:56 PM, in message , Sean 
>>> Hannan  wrote:


Mechanical Turk it.

(I hear that's what all the hipsters do while they watch Downton Abbey.)

-Sean


On 2/27/12 1:52 PM, "Suchy, Daniel"  wrote:

> Hello all,
>
> At my campus we offer podcasts of course lectures, recorded in class and then
> delivered via iTunes and as a plain Mp3 download (http://podcast.ucsd.edu).  I
> have the new responsibility of figuring out how to transcribe text versions of
> these audio podcasts for folks with hearing issues.
>
> I was wondering if any of you are using or have played with
> dictation/transcription software and can recommend or de-recommend any?   My
> first inclination is to go with open-source, but I'm open to anything that
> works well and can scale to handle hundreds of courses.
>
> Thanks in advance!
> Dan
>
> *
> Daniel Suchy
> User Services Technology Analyst
> University of California, San Diego Libraries
> 858.534.6819
> dsu...@ucsd.edu

Re: [CODE4LIB] Transcription/dictation software?

2012-02-27 Thread Sean Hannan 
Mechanical Turk it.

(I hear that's what all the hipsters do while they watch Downton Abbey.)

-Sean


On 2/27/12 1:52 PM, "Suchy, Daniel"  wrote:

> Hello all,
> 
> At my campus we offer podcasts of course lectures, recorded in class and then
> delivered via iTunes and as a plain Mp3 download (http://podcast.ucsd.edu).  I
> have the new responsibility of figuring out how to transcribe text versions of
> these audio podcasts for folks with hearing issues.
> 
> I was wondering if any of you are using or have played with
> dictation/transcription software and can recommend or de-recommend any?   My
> first inclination is to go with open-source, but I'm open to anything that
> works well and can scale to handle hundreds of courses.
> 
> Thanks in advance!
> Dan
> 
> *
> Daniel Suchy
> User Services Technology Analyst
> University of California, San Diego Libraries
> 858.534.6819
> dsu...@ucsd.edu

[CODE4LIB] Transcription/dictation software?

2012-02-27 Thread Suchy, Daniel 
Hello all,

At my campus we offer podcasts of course lectures, recorded in class and then 
delivered via iTunes and as a plain Mp3 download (http://podcast.ucsd.edu).  I 
have the new responsibility of figuring out how to transcribe text versions of 
these audio podcasts for folks with hearing issues.

I was wondering if any of you are using or have played with 
dictation/transcription software and can recommend or de-recommend any?   My 
first inclination is to go with open-source, but I'm open to anything that 
works well and can scale to handle hundreds of courses.

Thanks in advance!
Dan

*
Daniel Suchy
User Services Technology Analyst
University of California, San Diego Libraries
858.534.6819
dsu...@ucsd.edu