FAQ Search Today's Posts Mark Forums Read
» Video Reviews

» Linux Archive

Linux-archive is a website aiming to archive linux email lists and to make them easily accessible for linux users/developers.


» Sponsor

» Partners

» Sponsor

Go Back   Linux Archive > Ubuntu > Ubuntu Studio User

 
 
LinkBack Thread Tools
 
Old 07-05-2008, 10:00 AM
"Dotan Cohen"
 
Default Speech recognition

2008/7/4 Pastor JW <pastor_jw@the-inner-circle.org>:
> Even so I'd bet it would win in guessing proper context over most of the
> people's writting I have seen on maillists!! A good friend of mine bought
> one of the programs that was supposed to write out what he said as he is a
> rather poor typist. In six months worth of work he became a MUCH better
> typist from correcting the mistakes of the program! Anyway, he now no longer
> uses the program. Besides, it would likely not work anymore with Vista. Not
> to worry though as his printer no longer works under Vista anyway!
>

You should point his this new operating system that works with many
Windows XP programs no longer supported under Vista, and most hardware
too:
http://kubuntu.com

Dotan Cohen

http://what-is-what.com
http://gibberish.co.il
א-ב-ג-ד-ה-ו-ז-ח-ט-י-ך-כ-ל-ם-מ-ן-*-ס-ע-ף-פ-ץ-צ-ק-ר-ש-ת

A: Because it messes up the order in which people normally read text.
Q: Why is top-posting such a bad thing?
--
kubuntu-users mailing list
kubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/kubuntu-users
 
Old 07-05-2008, 10:03 AM
"Dotan Cohen"
 
Default Speech recognition

> There are two ways to do speech recognition, though. The generic way is a
> long way from identifying dialects and accents, but the other method allows
> individual users to train the program. That should have little trouble
> with one person dictating a book, but often fails if you get a cold! In
> either case, homonyms are going to be difficult.
>

The Dragon Naturally Speaking reviews call it 99.8% accurate for most
people out of the box, and it learns. You really should see the video
on their site. Apparently, it finds the context of a word by analyzing
a few words to the left and to the right, so it can properly type "the
bear's bare butt". If it works in Ubuntu, I'd pay $100 for it.

Dotan Cohen

http://what-is-what.com
http://gibberish.co.il
א-ב-ג-ד-ה-ו-ז-ח-ט-י-ך-כ-ל-ם-מ-ן-*-ס-ע-ף-פ-ץ-צ-ק-ר-ש-ת

A: Because it messes up the order in which people normally read text.
Q: Why is top-posting such a bad thing?
--
kubuntu-users mailing list
kubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/kubuntu-users
 
Old 07-05-2008, 12:10 PM
Steven Vollom
 
Default Speech recognition

Dotan Cohen wrote:
>> There are two ways to do speech recognition, though. The generic way is a
>> long way from identifying dialects and accents, but the other method allows
>> individual users to train the program. That should have little trouble
>> with one person dictating a book, but often fails if you get a cold! In
>> either case, homonyms are going to be difficult.
>>
>>
>
> The Dragon Naturally Speaking reviews call it 99.8% accurate for most
> people out of the box, and it learns. You really should see the video
> on their site. Apparently, it finds the context of a word by analyzing
> a few words to the left and to the right, so it can properly type "the
> bear's bare butt". If it works in Ubuntu, I'd pay $100 for it.
>
> Dotan Cohen
>
> http://what-is-what.com
> http://gibberish.co.il
> א-ב-ג-ד-ה-ו-ז-ח-ט-י-ך-כ-ל-ם-מ-ן-*-ס-ע-ף-פ-ץ-צ-ק-ר-ש-ת
>
> A: Because it messes up the order in which people normally read text.
> Q: Why is top-posting such a bad thing?
>
Years ago, I used Naturally Speaking. I would read as I wrote. When I
saw a mistake, I would immediately say 'correct that', it gave choices
with a number before them. I would then say 'take 3' if the third
choice was correct. It always worked well and rarely slowed the
dictation much. It sure was a lot faster and more accurate than
typing. I misspell words more than the program did. When I changed to
Linux, it was one of the programs that I missed the most, but not
enought to keep XP on my machine. In any event, I have heard that the
newest versions have corrected most of the errors that I experienced
before and have ironed out most of the problems I read that you all talk
about. Recently, I heard that Wine, the Windows emulator, works well
with Dragon Naturally Speaking, I have considered purchasing the current
version. I would still like to hear from someone using Naturally
Speaking on Wine before I spend the $100 to purchase. I hope this
information is useful.

Steven Vollom

--
kubuntu-users mailing list
kubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/kubuntu-users
 
Old 07-05-2008, 12:29 PM
"Dotan Cohen"
 
Default Speech recognition

2008/7/5 Steven Vollom <stevenvollom@sbcglobal.net>:
> Years ago, I used Naturally Speaking. I would read as I wrote. When I
> saw a mistake, I would immediately say 'correct that', it gave choices
> with a number before them. I would then say 'take 3' if the third
> choice was correct. It always worked well and rarely slowed the
> dictation much. It sure was a lot faster and more accurate than
> typing. I misspell words more than the program did. When I changed to
> Linux, it was one of the programs that I missed the most, but not
> enought to keep XP on my machine. In any event, I have heard that the
> newest versions have corrected most of the errors that I experienced
> before and have ironed out most of the problems I read that you all talk
> about. Recently, I heard that Wine, the Windows emulator, works well
> with Dragon Naturally Speaking, I have considered purchasing the current
> version. I would still like to hear from someone using Naturally
> Speaking on Wine before I spend the $100 to purchase. I hope this
> information is useful.
>

Write to Nuance and ask them about DNS on Linux. If we don't ask, then
they will never produce it. Make sure to mention that you are an
existing customer. Let us know what their response is. Thanks!

Dotan Cohen

http://what-is-what.com
http://gibberish.co.il
א-ב-ג-ד-ה-ו-ז-ח-ט-י-ך-כ-ל-ם-מ-ן-*-ס-ע-ף-פ-ץ-צ-ק-ר-ש-ת

A: Because it messes up the order in which people normally read text.
Q: Why is top-posting such a bad thing?
--
kubuntu-users mailing list
kubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/kubuntu-users
 
Old 07-05-2008, 01:02 PM
Steven Vollom
 
Default Speech recognition

David Fletcher wrote:
> At 02:58 04/07/2008, you wrote:
>
>> I read another response in this forum and it was suggested that Dragon
>> Naturally Speaking 9 works good in Wine, the Windows emulator. I
>> haven't as yet tried it, but I am going to. I used to use Naturally
>> Speaking for all my word processing. It works super. The programs that
>> I use using Wine work the same as they do on Microsoft OS's.
>>
>> Steven
>>
>
> I'll certainly be interested in seeing a result on this, but I'll
> reiterate that its intended use is for writing a book. I'm told that
> book publishers generally don't thank authors for submitting work as
> word processor files of any sort, but are very happy indeed to
> receive LaTeX files.
>
> Having had a play with LaTeX over the last couple of weeks and found
> out how to duplicate my standard letter writing layout with it, I've
> found that the best editor so far is kate - it knows the LaTeX syntax
> so it can run the spelling checker properly i.e. it makes no attempt
> to spell check the formatting instructions.
>
> So, if it's possible to run Dragon under Wine, with the dictated text
> going into kate, that could be the way to go.
>
> Dave
>
>
> Dear Dave,
I am curious. Are the publishers dissatisfied because the dictated work
is sent in saved data form? I mean, if they were to read the book
printed on paper, how would they know if the document was dictated from
a word processor.

The primary reason I used Naturally Speaking was to keep from making
errors, not save paper. I believe you can format or even use a
publishing format and still use Naturally Speaking.

It has been so long since I have used Microsoft (also I am getting older
and the memory is getting soft) that I can't remember the publishing
program that I used for Microsoft processors, but it worked with the
same quality using Naturally Speaking as when I was just dictating an
email. You had the ability to include photographs. You could have the
page numbers automatically entered and type on both sides of a sheet.
It appeared to produce publishable work from a saved file.

I am probably over my head in this conversation, because I am not an
author, but I used the program for similar private purposes and had
success. I am not trying to sell Naturally Speaking either, it is just
my experience with an older version was much better than the comments I
have been reading in the forum. Including error corrections, I believe
I worked at over 100 words per minute. That is a lot faster than I can
type (and I don't type error free).

Steven

--
kubuntu-users mailing list
kubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/kubuntu-users
 
Old 07-05-2008, 02:18 PM
"Dotan Cohen"
 
Default Speech recognition

2008/7/5 Steven Vollom <stevenvollom@sbcglobal.net>:
> I am curious. Are the publishers dissatisfied because the dictated work
> is sent in saved data form? I mean, if they were to read the book
> printed on paper, how would they know if the document was dictated from
> a word processor.
>
> The primary reason I used Naturally Speaking was to keep from making
> errors, not save paper. I believe you can format or even use a
> publishing format and still use Naturally Speaking.
>
> It has been so long since I have used Microsoft (also I am getting older
> and the memory is getting soft) that I can't remember the publishing
> program that I used for Microsoft processors, but it worked with the
> same quality using Naturally Speaking as when I was just dictating an
> email. You had the ability to include photographs. You could have the
> page numbers automatically entered and type on both sides of a sheet.
> It appeared to produce publishable work from a saved file.
>
> I am probably over my head in this conversation, because I am not an
> author, but I used the program for similar private purposes and had
> success. I am not trying to sell Naturally Speaking either, it is just
> my experience with an older version was much better than the comments I
> have been reading in the forum. Including error corrections, I believe
> I worked at over 100 words per minute. That is a lot faster than I can
> type (and I don't type error free).
>
> Steven
>

The video on the Nuance website states that DNS works with any
Windows-based program. They show usage of the program only with MS
products, though, such as Word, IE, and OE.

Dotan Cohen

http://what-is-what.com
http://gibberish.co.il
א-ב-ג-ד-ה-ו-ז-ח-ט-י-ך-כ-ל-ם-מ-ן-*-ס-ע-ף-פ-ץ-צ-ק-ר-ש-ת

A: Because it messes up the order in which people normally read text.
Q: Why is top-posting such a bad thing?
--
kubuntu-users mailing list
kubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/kubuntu-users
 
Old 07-08-2008, 03:59 PM
Pablo El Feo
 
Default Speech recognition

>
> The video on the Nuance website states that DNS works with any
> Windows-based program. They show usage of the program only with MS
> products, though, such as Word, IE, and OE.
>
> Dotan Cohen
>

Probably this video can show the use of speech recognition in an average
environment. At least my experience was similar.

http://www.youtube.com/watch?v=MzJ0CytAsec

It's kind of a joke, he isn't helping the program at all but, it can get that
frustrating.


--
kubuntu-users mailing list
kubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/kubuntu-users
 
Old 03-25-2009, 09:44 PM
Jerry James
 
Default Speech recognition

I've had multiple friends & colleagues who have fallen prey to our
occupational hazard of RSI.* Some ten years ago or more, I worked on
integrating IBM's ViaVoice for Linux with XEmacs for the benefit of a
couple of XEmacs developers who were suffering from that problem at
the time.* Unfortunately, IBM dropped support for its Linux product
while I was still working on the integration.

I'm thinking about working on something like that again, but need a
voice recognition product to work with.* I've been looking at CMU
Sphinx [1] as a possibility, and have made test RPMs out of a few
pieces of that project [2,3,4].

Questions for the list:

Is anybody already working on packaging up some voice recognition product?

Does anybody know of anything more accessible than CMU Sphinx (it
appears to be very powerful, but is definitely not for newbies; also,
not all pieces of it have been released yet)?

Is anybody interested in working with me on getting some voice
recognition product packaged up in usable form on Fedora?

References:
[1] http://www.cmusphinx.org/
[2] http://jjames.fedorapeople.org/sphinxbase/
[3] http://jjames.fedorapeople.org/pocketsphinx/
[4] http://jjames.fedorapeople.org/SphinxTrain/
--
Jerry James
http://loganjerry.googlepages.com/

--
fedora-devel-list mailing list
fedora-devel-list@redhat.com
https://www.redhat.com/mailman/listinfo/fedora-devel-list
 
Old 03-25-2009, 09:44 PM
Jerry James
 
Default Speech recognition

I've had multiple friends & colleagues who have fallen prey to our
occupational hazard of RSI.* Some ten years ago or more, I worked on
integrating IBM's ViaVoice for Linux with XEmacs for the benefit of a
couple of XEmacs developers who were suffering from that problem at
the time.* Unfortunately, IBM dropped support for its Linux product
while I was still working on the integration.

I'm thinking about working on something like that again, but need a
voice recognition product to work with.* I've been looking at CMU
Sphinx [1] as a possibility, and have made test RPMs out of a few
pieces of that project [2,3,4].

Questions for the list:

Is anybody already working on packaging up some voice recognition product?

Does anybody know of anything more accessible than CMU Sphinx (it
appears to be very powerful, but is definitely not for newbies; also,
not all pieces of it have been released yet)?

Is anybody interested in working with me on getting some voice
recognition product packaged up in usable form on Fedora?

References:
[1] http://www.cmusphinx.org/
[2] http://jjames.fedorapeople.org/sphinxbase/
[3] http://jjames.fedorapeople.org/pocketsphinx/
[4] http://jjames.fedorapeople.org/SphinxTrain/
--
Jerry James
http://loganjerry.googlepages.com/

--
fedora-devel-list mailing list
fedora-devel-list@redhat.com
https://www.redhat.com/mailman/listinfo/fedora-devel-list
 
Old 03-25-2009, 10:16 PM
Orion Poplawski
 
Default Speech recognition

Jerry James wrote:

Is anybody interested in working with me on getting some voice
recognition product packaged up in usable form on Fedora?


I'm happy to help - we have someone here in a similar position. But I
have no leads on good software.


--
Orion Poplawski
Technical Manager 303-415-9701 x222
NWRA/CoRA Division FAX: 303-415-9702
3380 Mitchell Lane orion@cora.nwra.com
Boulder, CO 80301 http://www.cora.nwra.com

--
fedora-devel-list mailing list
fedora-devel-list@redhat.com
https://www.redhat.com/mailman/listinfo/fedora-devel-list
 

Thread Tools




All times are GMT. The time now is 05:52 AM.

VBulletin, Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.
Content Relevant URLs by vBSEO ©2007, Crawlability, Inc.
Copyright 2007 - 2008, www.linux-archive.org