Speech-to-Text

classic Classic list List threaded Threaded
37 messages Options
12
Reply | Threaded
Open this post in threaded view
|

Speech-to-Text

Donald D Henson-2
Does anyone know of an Open Source application to accept continuous
speech and convert it to text? I've found a couple of proprietary apps
but you  have to use Voice mail as an input. Any suggestions appreciated.

Don Henson
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Joseph Loo

On Wed, 2008-04-30 at 15:37 -0600, Donald D Henson wrote:
> Does anyone know of an Open Source application to accept continuous
> speech and convert it to text? I've found a couple of proprietary apps
> but you  have to use Voice mail as an input. Any suggestions appreciated.
>
> Don Henson
Have you looked at CMU Sphinx
http://cmusphinx.sourceforge.net/html/cmusphinx.php
--
Joseph Loo
[hidden email]

--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Chuck Payne-2
On Wed, Apr 30, 2008 at 10:12 PM, Joseph Loo <[hidden email]> wrote:

>
>  On Wed, 2008-04-30 at 15:37 -0600, Donald D Henson wrote:
>  > Does anyone know of an Open Source application to accept continuous
>  > speech and convert it to text? I've found a couple of proprietary apps
>  > but you  have to use Voice mail as an input. Any suggestions appreciated.
>  >
>  > Don Henson
>  Have you looked at CMU Sphinx
>  http://cmusphinx.sourceforge.net/html/cmusphinx.php
>  --
>  Joseph Loo
>  [hidden email]
>
>
>
>  --
>  To unsubscribe, e-mail: [hidden email]
>  For additional commands, e-mail: [hidden email]
>
>

Here a great site, that help me out with the stuff that I am doing
because I am dyslexlic

http://www.hackosis.com/index.php/2007/11/24/transform-linux-into-a-talking-companion/

http://www.hackosis.com/index.php/2007/12/22/linux-easily-convert-text-to-wav-with-festival/

Now if I can get a clean voice for Festival. The default one a bit too
much like SAM.
--
--
Command, n.:
 Statement presented by a human and accepted by a computer in
such a manner as to make the human feel as if he is in control.
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Joseph Loo

On Wed, 2008-04-30 at 23:49 -0400, Chuck Payne wrote:

> On Wed, Apr 30, 2008 at 10:12 PM, Joseph Loo <[hidden email]> wrote:
> >
> >  On Wed, 2008-04-30 at 15:37 -0600, Donald D Henson wrote:
> >  > Does anyone know of an Open Source application to accept continuous
> >  > speech and convert it to text? I've found a couple of proprietary apps
> >  > but you  have to use Voice mail as an input. Any suggestions appreciated.
> >  >
> >  > Don Henson
> >  Have you looked at CMU Sphinx
> >  http://cmusphinx.sourceforge.net/html/cmusphinx.php
> >  --
> >  Joseph Loo
> >  [hidden email]
> >
> >
> >
> >  --
> >  To unsubscribe, e-mail: [hidden email]
> >  For additional commands, e-mail: [hidden email]
> >
> >
>
> Here a great site, that help me out with the stuff that I am doing
> because I am dyslexlic
>
> http://www.hackosis.com/index.php/2007/11/24/transform-linux-into-a-talking-companion/
>
> http://www.hackosis.com/index.php/2007/12/22/linux-easily-convert-text-to-wav-with-festival/
>
> Now if I can get a clean voice for Festival. The default one a bit too
> much like SAM.
Under Opensuse does not have all the available voices. You might want to
got to the festival site and download the other voices.
Alternatively, you can buy some of the voices available to Festival.
--
Joseph Loo
[hidden email]

--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Donald D Henson-2
In reply to this post by Joseph Loo
Joseph Loo wrote:
> On Wed, 2008-04-30 at 15:37 -0600, Donald D Henson wrote:
>> Does anyone know of an Open Source application to accept continuous
>> speech and convert it to text? I've found a couple of proprietary apps
>> but you  have to use Voice mail as an input. Any suggestions appreciated.
>>
>> Don Henson
> Have you looked at CMU Sphinx
> http://cmusphinx.sourceforge.net/html/cmusphinx.php

Yes. I saw that one. There is way to many references to researchers and
developers. I was hoping for a production-ready system. Is there
anything like that for Sphinx?

Don Henson

--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Donald D Henson-2
In reply to this post by Chuck Payne-2
Chuck Payne wrote:

> On Wed, Apr 30, 2008 at 10:12 PM, Joseph Loo <[hidden email]> wrote:
>>  On Wed, 2008-04-30 at 15:37 -0600, Donald D Henson wrote:
>>  > Does anyone know of an Open Source application to accept continuous
>>  > speech and convert it to text? I've found a couple of proprietary apps
>>  > but you  have to use Voice mail as an input. Any suggestions appreciated.
>>  >
>>  > Don Henson
>>  Have you looked at CMU Sphinx
>>  http://cmusphinx.sourceforge.net/html/cmusphinx.php
>>  --
>>  Joseph Loo
>>  [hidden email]
>>
>>
>>
>>  --
>>  To unsubscribe, e-mail: [hidden email]
>>  For additional commands, e-mail: [hidden email]
>>
>>
>
> Here a great site, that help me out with the stuff that I am doing
> because I am dyslexlic
>
> http://www.hackosis.com/index.php/2007/11/24/transform-linux-into-a-talking-companion/
>
> http://www.hackosis.com/index.php/2007/12/22/linux-easily-convert-text-to-wav-with-festival/
>
> Now if I can get a clean voice for Festival. The default one a bit too
> much like SAM.

That's going in the wrong direction. I don't want the computer to talk
to me. I want to talk to the computer, have it listen, and turn what I
say into text. Although the conversion process should be relatively
fast, it does not need to be real time.

Don Henson

--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Rikard Johnels
In reply to this post by Donald D Henson-2
On Wednesday 30 April 2008 23:37, Donald D Henson wrote:
> Does anyone know of an Open Source application to accept continuous
> speech and convert it to text? I've found a couple of proprietary apps
> but you  have to use Voice mail as an input. Any suggestions appreciated.
>
> Don Henson

A few years back there was something called ViaVioce from IBM (i think)
I never got that to work, and as far as i know its been discontinued for
ages...
I havent seen any speech-to-text utilities for linux, nor for windows too for
that matter.
The last time i saw it was on my brothers Amiga way back in the early days.
He actually had it responding to voicecommands.
And there was also a simple voicerecognition software bundled with a
SoundBlaster sound card at one point. But that vas a very long time ago.

I too would love to have speech-to-text, as i am LOUSY at speed typing, and as
i sometimes tell short stories to my friends, it would be heaven to be able
to get them into printed matter...



attachment0 (196 bytes) Download Attachment
Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

gregfreemyer
On Sat, May 3, 2008 at 3:45 AM, Rikard Johnels <[hidden email]> wrote:

> On Wednesday 30 April 2008 23:37, Donald D Henson wrote:
>  > Does anyone know of an Open Source application to accept continuous
>  > speech and convert it to text? I've found a couple of proprietary apps
>  > but you  have to use Voice mail as an input. Any suggestions appreciated.
>  >
>  > Don Henson
>
>  A few years back there was something called ViaVioce from IBM (i think)
>  I never got that to work, and as far as i know its been discontinued for
>  ages...
>  I havent seen any speech-to-text utilities for linux, nor for windows too for
>  that matter.
>  The last time i saw it was on my brothers Amiga way back in the early days.
>  He actually had it responding to voicecommands.
>  And there was also a simple voicerecognition software bundled with a
>  SoundBlaster sound card at one point. But that vas a very long time ago.
>
>  I too would love to have speech-to-text, as i am LOUSY at speed typing, and as
>  i sometimes tell short stories to my friends, it would be heaven to be able
>  to get them into printed matter...
>

I think in Windows "Dragon NaturallySpeaking" is the leading solution.
 I don't use it so no firsthand feedback here.

http://nuance.com/naturallyspeaking/

A little history of products (including some OSS ones) and whats
available is at:
http://en.wikipedia.org/wiki/List_of_speech_recognition_software

Greg
--
Greg Freemyer
Litigation Triage Solutions Specialist
http://www.linkedin.com/in/gregfreemyer
First 99 Days Litigation White Paper -
http://www.norcrossgroup.com/forms/whitepapers/99%20Days%20whitepaper.pdf

The Norcross Group
The Intersection of Evidence & Technology
http://www.norcrossgroup.com
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Donald D Henson-2
Greg Freemyer wrote:

> On Sat, May 3, 2008 at 3:45 AM, Rikard Johnels <[hidden email]> wrote:
>> On Wednesday 30 April 2008 23:37, Donald D Henson wrote:
>>  > Does anyone know of an Open Source application to accept continuous
>>  > speech and convert it to text? I've found a couple of proprietary apps
>>  > but you  have to use Voice mail as an input. Any suggestions appreciated.
>>  >
>>  > Don Henson
>>
>>  A few years back there was something called ViaVioce from IBM (i think)
>>  I never got that to work, and as far as i know its been discontinued for
>>  ages...
>>  I havent seen any speech-to-text utilities for linux, nor for windows too for
>>  that matter.
>>  The last time i saw it was on my brothers Amiga way back in the early days.
>>  He actually had it responding to voicecommands.
>>  And there was also a simple voicerecognition software bundled with a
>>  SoundBlaster sound card at one point. But that vas a very long time ago.
>>
>>  I too would love to have speech-to-text, as i am LOUSY at speed typing, and as
>>  i sometimes tell short stories to my friends, it would be heaven to be able
>>  to get them into printed matter...
>>
>
> I think in Windows "Dragon NaturallySpeaking" is the leading solution.
>  I don't use it so no firsthand feedback here.
>
> http://nuance.com/naturallyspeaking/
>
> A little history of products (including some OSS ones) and whats
> available is at:
> http://en.wikipedia.org/wiki/List_of_speech_recognition_software
>
> Greg

Thanks for the links. I'd seen most of the OSS stuff. All that I've seen
so far are nowhere near production use. Dragon Naturally Speaking looks
promising, though. Their web site convinced  me to plunk down a hundred
bucks for a copy of their cheapest product. After I've had a chance to
use it for a few days, I'll post a review here. It has to be physically
shipped so it'll be a couple of weeks.

Don Henson

--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

David C. Rankin
Donald D Henson wrote:

> Greg Freemyer wrote:
>> On Sat, May 3, 2008 at 3:45 AM, Rikard Johnels <[hidden email]>
>> wrote:
>>> On Wednesday 30 April 2008 23:37, Donald D Henson wrote:
>>>  > Does anyone know of an Open Source application to accept continuous
>>>  > speech and convert it to text? I've found a couple of proprietary
>>> apps
>>>  > but you  have to use Voice mail as an input. Any suggestions
>>> appreciated.
>>>  >
>>>  > Don Henson
>>>
>>>  A few years back there was something called ViaVioce from IBM (i think)
>>>  I never got that to work, and as far as i know its been discontinued
>>> for
>>>  ages...
>>>  I havent seen any speech-to-text utilities for linux, nor for
>>> windows too for
>>>  that matter.
>>>  The last time i saw it was on my brothers Amiga way back in the
>>> early days.
>>>  He actually had it responding to voicecommands.
>>>  And there was also a simple voicerecognition software bundled with a
>>>  SoundBlaster sound card at one point. But that vas a very long time
>>> ago.
>>>
>>>  I too would love to have speech-to-text, as i am LOUSY at speed
>>> typing, and as
>>>  i sometimes tell short stories to my friends, it would be heaven to
>>> be able
>>>  to get them into printed matter...
>>>
>>
>> I think in Windows "Dragon NaturallySpeaking" is the leading solution.
>>  I don't use it so no firsthand feedback here.
>>
>> http://nuance.com/naturallyspeaking/
>>
>> A little history of products (including some OSS ones) and whats
>> available is at:
>> http://en.wikipedia.org/wiki/List_of_speech_recognition_software
>>
>> Greg
>
> Thanks for the links. I'd seen most of the OSS stuff. All that I've seen
> so far are nowhere near production use. Dragon Naturally Speaking looks
> promising, though. Their web site convinced  me to plunk down a hundred
> bucks for a copy of their cheapest product. After I've had a chance to
> use it for a few days, I'll post a review here. It has to be physically
> shipped so it'll be a couple of weeks.
>
> Don Henson
>

It will take more than a few days before you can make an objective comparison.
With all speech recognition software you have to "train" it which is a fairly
time consuming process. Though from other I know who have actually done it,
after the training is done, you can use it very reliably.

The "training" will create a "voice" file based upon your voice inflection,
pause, annunciation, etc. The process involves beginning with a default
male/female voice file and going though a correction process where the
difference in your specific manner of speaking is captured in your voice file
and that is used to augment the recognition of words, etc..

Since your voice file will take some time to create, tweak, get just right,
etc., make sure your know what that file is and BACK IT UP regularly.
Otherwise, after several weeks of use, if something bad should happen, then you
are right back to step one.

I hope that helps.

--
David C. Rankin, J.D., P.E.
Rankin Law Firm, PLLC
510 Ochiltree Street
Nacogdoches, Texas 75961
Telephone: (936) 715-9333
Facsimile: (936) 715-9339
www.rankinlawfirm.com
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

John Andersen-2
On Sat, May 3, 2008 at 1:23 PM, David C. Rankin
<[hidden email]> wrote:
> With all speech recognition software you have to "train" it
> which is a fairly time consuming process.

I can't speak to Dragon products, but the need to train is the key
thing that newer
technology is trying to eliminate in speech recognition.  My phone requires no
training, I can just say "call David Rankin" and it would find you in the
address book.  Same with Ford Active Sync. Same with some modern
telephone answering systems.  (Call HP tech support to hear a demo.)

Admittedly these things are using a vastly reduced vocabulary. But never the
less, training is on the way out.

--
----------JSA---------
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Anders Johansson-7
On Saturday 03 May 2008 23:59:00 John Andersen wrote:
> Admittedly these things are using a vastly reduced vocabulary. But never
> the less, training is on the way out.

Doesn't that require that dialects disappear as well?

I can easily find three English/American dialects which *you* couldn't
understand. What chance would your phone have? In Sweden, some dialects might
as well be different languages - the words really are the same, but they're
pronounced so differently from how I would pronounce them, that in practice
there is virtually no similarity. Here in Germany, the difference between
Fränkisch and Hochdeutch makes my life difficult on a daily basis, I can't
even begin to imagine what an algorithm would look like that could
incorporate them both.

And I'm told the situation in countries like India is even more extreme

So sure, training might be on the way out, as long as you adhere to some sort
of "standard" way of speaking. But for most of us, I think it will always be
needed

Anders
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

John Andersen-2
On Sat, May 3, 2008 at 3:13 PM, Anders Johansson <[hidden email]> wrote:
> On Saturday 03 May 2008 23:59:00 John Andersen wrote:
>  > Admittedly these things are using a vastly reduced vocabulary. But never
>  > the less, training is on the way out.
>
>  Doesn't that require that dialects disappear as well?
>
>  I can easily find three English/American dialects which *you* couldn't
>  understand. What chance would your phone have?

Phones are sold into specific markets, and they know about several
languages, you select one when setting up the phone.

I can't say how well it would work for an Australian or Indian speaker
but my phone, sold to the North American market works quite well
with finding names in the phone book, selecting menu options, etc.
Works equally well for my wife.  No clue how they do this.

Nuance Inc is the big dog in this area.  They have been buying up
the competition mostly for patents.  They have their software in many
different phones, Personal Navigation Devices, Automobile accessories
and desktop applications.

Disclosure: I'm a stock holder of Nuance.
I suspect Voice reco is going to go big time in many different
industry segments in coming years, which is why I bought the
stock.

--
----------JSA---------
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

martin glazer-3
In reply to this post by John Andersen-2
Microsoft software inside of a Ford vehicle, scares
the hell out of me.


--- John Andersen <[hidden email]> wrote:

> On Sat, May 3, 2008 at 1:23 PM, David C. Rankin
> <[hidden email]> wrote:
> > With all speech recognition software you have to
> "train" it
> > which is a fairly time consuming process.
>
> I can't speak to Dragon products, but the need to
> train is the key
> thing that newer
> technology is trying to eliminate in speech
> recognition.  My phone requires no
> training, I can just say "call David Rankin" and it
> would find you in the
> address book.  Same with Ford Active Sync. Same with
> some modern
> telephone answering systems.  (Call HP tech support
> to hear a demo.)
>
> Admittedly these things are using a vastly reduced
> vocabulary. But never the
> less, training is on the way out.
>
> --
> ----------JSA---------
> --
> To unsubscribe, e-mail:
> [hidden email]
> For additional commands, e-mail:
> [hidden email]
>
>

--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Ken Schneider - openSUSE
martin glazer pecked at the keyboard and wrote:
> Microsoft software inside of a Ford vehicle, scares
> the hell out of me.
>

If you think that is scary...

Microsoft software used by the military in there ships...

now THAT is scary.

--
Ken Schneider
SuSe since Version 5.2, June 1998
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Fred A. Miller
Ken Schneider wrote:
> martin glazer pecked at the keyboard and wrote:
>> Microsoft software inside of a Ford vehicle, scares
>> the hell out of me.
>>
>
> If you think that is scary...
>
> Microsoft software used by the military in there ships...
> now THAT is scary.

Supposedly, that has change and Linux has replaced MickySoft.

Fred

--
MickySoft Aims to Lasso Everything With Live Mesh.
What will get "lassoed" is your private data as
hackers, virus and trojan writers have a field day!
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Doug McGarrett
In reply to this post by Anders Johansson-7
On Saturday 03 May 2008 18:13, Anders Johansson wrote:

> On Saturday 03 May 2008 23:59:00 John Andersen wrote:
> > Admittedly these things are using a vastly reduced vocabulary. But never
> > the less, training is on the way out.
>
> Doesn't that require that dialects disappear as well?
>
> I can easily find three English/American dialects which *you* couldn't
> understand. What chance would your phone have? In Sweden, some dialects
> might as well be different languages - the words really are the same, but
> they're pronounced so differently from how I would pronounce them, that in
> practice there is virtually no similarity. Here in Germany, the difference
> between Fränkisch and Hochdeutch makes my life difficult on a daily basis,
> I can't even begin to imagine what an algorithm would look like that could
> incorporate them both.

Where is Fränkisch spoken?  When I was in Germany in the mid 70's, most
Germans of 40 years or younger could speak a "general German" such as was
heard on the radio or TV.  This did not seem to be true in Switzerland, altho
the Swiss could understand my "general German."  Even some of the older
folks--I met a fellow from the Rheinland whose accent betrayed him, but he
told me that if he spoke the language that he used at home, no-one in
Stuttgart could understand him.  But he also told me that his kids were
learning a general German in school, and starting to use it at home.

At any rate, if almost everyone can speak a "general German," then speech
to text should be possible in that language.

Without being as fluent in Italian, it seemed to me when I was there in the
80's, that the same sort of thing was happening.

>
> And I'm told the situation in countries like India is even more extreme
>
India is a different story:  they are actually speaking different languages,
not dialects.  I don't remember how many different languages, but the number
100 would not surprise me.

> So sure, training might be on the way out, as long as you adhere to some
> sort of "standard" way of speaking. But for most of us, I think it will
> always be needed
>
> Anders

doug
 
Blessed are the peacemakers ... for they shall be shot at from both sides.
-A.M. Greeley
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

David C. Rankin
In reply to this post by John Andersen-2
John Andersen wrote:

> On Sat, May 3, 2008 at 1:23 PM, David C. Rankin
> <[hidden email]> wrote:
>> With all speech recognition software you have to "train" it
>> which is a fairly time consuming process.
>
> I can't speak to Dragon products, but the need to train is the key
> thing that newer
> technology is trying to eliminate in speech recognition.  My phone requires no
> training, I can just say "call David Rankin" and it would find you in the
> address book.  Same with Ford Active Sync. Same with some modern
> telephone answering systems.  (Call HP tech support to hear a demo.)
>
> Admittedly these things are using a vastly reduced vocabulary. But never the
> less, training is on the way out.
>

        I definitely need a new phone. The Motorola v3xx is pretty good, but I end up
in shouting matches with it just trying to get it to dial "Don". You know the
scenario.

me: "name dial" "Don"
phone: "did you say home?"
me: "no"
phone: "say a command"
me: "name dial"
phone: "say the name"
me: "Don"
phone: "did you say home?"
me: "NO you %$#@#^%#$ phone, I said DON"
phone: "say a command"
AAARRRGGHHHH!

        Seriously, my understanding is that with relatively few choices, the VR
phones, etc. can do a good job because on the 1 or 2 word commands they
receive, they can check it against their address book for possible 1 or 2 word
answers. That dramatically cuts down on, or almost eliminates the training
required.

        On the other hand, general VR applications that you dictate too don't have
that luxury. The vocabulary they deal with is orders of magnitude greater than
a 1 or 2 word comparison to an address book.

        I hope they have progressed far enough to eliminate most of the training, but
just a couple of years ago, the training for dragon, etc. was on the order of
weeks. Especially for specialized vocabulary. Imaging saying "vscanf" or
"strtol" into the mic and then listening to the hard drive whir... much less
"Respondeat Superior" or "melanoma".

--
David C. Rankin, J.D., P.E.
Rankin Law Firm, PLLC
510 Ochiltree Street
Nacogdoches, Texas 75961
Telephone: (936) 715-9333
Facsimile: (936) 715-9339
www.rankinlawfirm.com
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

John Andersen-2
On Sat, May 3, 2008 at 6:37 PM, David C. Rankin
<[hidden email]> wrote:

> John Andersen wrote:
>
> > On Sat, May 3, 2008 at 1:23 PM, David C. Rankin
> > <[hidden email]> wrote:
> >
> > > With all speech recognition software you have to "train" it
> > > which is a fairly time consuming process.
> > >
> >
> > I can't speak to Dragon products, but the need to train is the key
> > thing that newer
> > technology is trying to eliminate in speech recognition.  My phone
> requires no
> > training, I can just say "call David Rankin" and it would find you in the
> > address book.  Same with Ford Active Sync. Same with some modern
> > telephone answering systems.  (Call HP tech support to hear a demo.)
> >
> >
> > Admittedly these things are using a vastly reduced vocabulary. But never
> the
> > less, training is on the way out.
> >
> >
>
>         I definitely need a new phone. The Motorola v3xx is pretty good, but
> I end up in shouting matches with it just trying to get it to dial "Don".
> You know the scenario.
>
>  me:     "name dial" "Don"
>  phone:  "did you say home?"
>  me:     "no"
>  phone:  "say a command"
>  me:     "name dial"
>  phone:  "say the name"
>  me:     "Don"
>  phone:  "did you say home?"
>  me:     "NO you %$#@#^%#$ phone, I said DON"
>  phone:  "say a command"
>  AAARRRGGHHHH!


LOL.
Exactly the same problem here with a friend named Dan.
I had to put him in the phonebook as Daniel.
(Moto Krazr k1).  This will probably be my last Motorola phone
unless stunning new designs are released, because its getting
to be a fairly old design.



--
----------JSA---------
--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

Reply | Threaded
Open this post in threaded view
|

Re: Speech-to-Text

Joseph Loo
In reply to this post by Rikard Johnels

On Sat, 2008-05-03 at 09:45 +0200, Rikard Johnels wrote:

> On Wednesday 30 April 2008 23:37, Donald D Henson wrote:
> > Does anyone know of an Open Source application to accept continuous
> > speech and convert it to text? I've found a couple of proprietary apps
> > but you  have to use Voice mail as an input. Any suggestions appreciated.
> >
> > Don Henson
>
> A few years back there was something called ViaVioce from IBM (i think)
> I never got that to work, and as far as i know its been discontinued for
> ages...
> I havent seen any speech-to-text utilities for linux, nor for windows too for
> that matter.
> The last time i saw it was on my brothers Amiga way back in the early days.
> He actually had it responding to voicecommands.
> And there was also a simple voicerecognition software bundled with a
> SoundBlaster sound card at one point. But that vas a very long time ago.
>
> I too would love to have speech-to-text, as i am LOUSY at speed typing, and as
> i sometimes tell short stories to my friends, it would be heaven to be able
> to get them into printed matter...
>
>
My understanding, IBM did not sell the Linux version. In certain cases
VIA voice can be bought at least that is what I have been told.
--
Joseph Loo
[hidden email]

--
To unsubscribe, e-mail: [hidden email]
For additional commands, e-mail: [hidden email]

12