[Kde-accessibility] Simon

[David Cuevas]

Good afternoon,

I was studying some voice recognition softwares out there, but i found
Simon and i was pretty impressed.

Can you tell me where can i download and setup portuguese context /
scenarios and use it with dictation mode?

Is it possible to use this dictation module in apps developed by me?!

Kind regards!

[Peter Grasch]

Hi,

Post by David Cuevas
Can you tell me where can i download and setup portuguese context /
scenarios and use it with dictation mode?
Is it possible to use this dictation module in apps developed by me?!

Sorry, dictation is not yet supported in Simon.

If you want to help make it a reality in the future, please consider donating
a few minutes of your time and submit portoguese audio recordings:
http://www.voxforge.org/pt/Read

Thanks!

Best regards,
Peter

[Steve Cookson]

Hi Guys,

Well I'd love to see dictation in Simon. Is it really only the lack of
a speech corpus that makes it not so?

There is a very active Brazilian group at Coruja which I believe is
linked to the FalaBrasil group at
http://www.laps.ufpa.br/falabrasil/simonbr.php. As far as European
Portuguese is concerned, I'm not aware of similar groups.

Do these groups not have the required vocab?

I guess from your reply, that it's not available in English or German
either.

For our command and control we only use about 5 commands and we have
sampled these independently. Amazingly they even work when I use them
in my strong British accent.

In the future we would like to add a list of medical words, but in the
meantime we'll use some form of pointers, eg popups controlled
alphabetically.

Good luck,

Regards

Steve.

Post by Peter Grasch
Hi,

Post by David Cuevas
Can you tell me where can i download and setup portuguese context /
scenarios and use it with dictation mode?
Is it possible to use this dictation module in apps developed by me?!

Sorry, dictation is not yet supported in Simon.
If you want to help make it a reality in the future, please consider donating
http://www.voxforge.org/pt/Read
Thanks!
Best regards,
Peter
_______________________________________________
kde-accessibility mailing list
https://mail.kde.org/mailman/listinfo/kde-accessibility

[Peter Grasch]

Hi Steve,

Post by Steve Cookson
Well I'd love to see dictation in Simon. Is it really only the lack of
a speech corpus that makes it not so?

No, of course not. To build a dictation capable system, you need a good
acoustic model, a good language model and a dictating application. We have
starting points for all of them but for a serious system, they all need work.

Post by Steve Cookson
There is a very active Brazilian group at Coruja which I believe is
linked to the FalaBrasil group at
http://www.laps.ufpa.br/falabrasil/simonbr.php. As far as European
Portuguese is concerned, I'm not aware of similar groups.
Do these groups not have the required vocab?

No, that's by far not the biggest problem, it's relatively easy to get
relatively good vocabulary lists (crawling online resources to get a text
corpus and using simple counting to select the N most frequent words is a
common and good strategy).

Post by Steve Cookson
I guess from your reply, that it's not available in English or German
either.

Correct.

Post by Steve Cookson
For our command and control we only use about 5 commands and we have
sampled these independently. Amazingly they even work when I use them
in my strong British accent.

Sure. But the more choice, the more difficult.

Post by Steve Cookson
In the future we would like to add a list of medical words, but in the
meantime we'll use some form of pointers, eg popups controlled
alphabetically.

Good idea. However, medical terminology is actually very easy to recognize
(distinguish) as the words are so long. Coming back to dictation, "pulmonary
edema" is actually arguably easier to write than "hey" - and definitely easier
than "hay" :)

Best regards,
Peter

[David Cuevas]

Hello guys, again :).

I would like to ask you, if you can help me:

I've been googling as hard as i can, heading to find an open-sourcing
application that is able to upload a media file containing, for example, an
entire conversation, and transcribe that same conversation on a text file,
but my search was effortless...

...Since i believe you guys are more used to these voice applications, can
you help me enumerating a few applications, if they exist?

I would be very appreciated if you can help me :).

Kind regards,

David

[Peter Grasch]

Hello,

Post by David Cuevas
I've been googling as hard as i can, heading to find an open-sourcing
application that is able to upload a media file containing, for example, an
entire conversation, and transcribe that same conversation on a text file,
but my search was effortless...

There is no such thing in the open source world that would be usable in any
real world scenario. Sorry.

Best regards,
Peter

[David Cuevas]

Hello Peter,

Thanks for your flash-gordon-style reply :D.

Well, i'm very appreciated since you gave me at least one concrete answer
so that i can finish my research. Even that represents a null conclusion.

Once again, thank you very much!

Kind regards,

David

Post by Peter Grasch
Hello,

Post by David Cuevas
I've been googling as hard as i can, heading to find an open-sourcing
application that is able to upload a media file containing, for example,

an

Post by David Cuevas
entire conversation, and transcribe that same conversation on a text

file,

Post by David Cuevas
but my search was effortless...

There is no such thing in the open source world that would be usable in any
real world scenario. Sorry.
Best regards,
Peter

[Peter Grasch]

Post by David Cuevas
Hello Peter,
Thanks for your flash-gordon-style reply :D.
Well, i'm very appreciated since you gave me at least one concrete answer
so that i can finish my research. Even that represents a null conclusion.
Once again, thank you very much!

Glad to help, but sad that this is the state of FOSS speech recognition.

Best regards,
Peter

[Steve Cookson]

Hi Peter,

Thanks for your reply.

Post by Peter Grasch
Good idea. However, medical terminology is actually very easy to recognize
(distinguish) as the words are so long. Coming back to dictation, "pulmonary
edema" is actually arguably easier to write than "hey" - and definitely easier
than "hay":)

Many medical terms are very similar too:

esofagite actínica
esofagite cáustica
esofagite descamativa
esofagite eosinofílica
esofagite erosiva
esofagite herpética
esofagite por citomegalovirus

or

colite actínica
colite de Behçet
colite isquêmica
colite microscópica
colite por desvio de trânsito
colite pseudomembranosa
colite ulcerativa

What do you think?

Regards

Steve.

[Peter Grasch]

Post by Steve Cookson

Post by Peter Grasch
Good idea. However, medical terminology is actually very easy to recognize
(distinguish) as the words are so long. Coming back to dictation,
"pulmonary edema" is actually arguably easier to write than "hey" - and
definitely easier than "hay":)

esofagite actínica
esofagite cáustica
esofagite descamativa
esofagite eosinofílica
esofagite erosiva
esofagite herpética
esofagite por citomegalovirus
or
colite actínica
colite de Behçet
colite isquêmica
colite microscópica
colite por desvio de trânsito
colite pseudomembranosa
colite ulcerativa
What do you think?

I don't see how those are overly similar.

An intuitive and very indicative way to look at it is through the edit
distance of the phonetic transcriptions. The higher the edit distance, the
more diverse. For example, "eight", "mate", "kate", "gate", etc. all have an
edit distance of one.
I don't speak Portoguese but it looks like the terms you provided would be
pronounced quite differently...

Best regards,
Peter

[Steve Cookson]

Hi Peter,

On the subject of long lists, the issue for us is giving each one a
command and data, so on calling

esofagite descamativa

really what I want it to do is call 'alt-d' for diagnosis and d123,
say, being the code for the specific diagnosis.

Does that work?

Regards

Steve.

Post by Peter Grasch

Post by Steve Cookson

Post by Peter Grasch
Good idea. However, medical terminology is actually very easy to recognize
(distinguish) as the words are so long. Coming back to dictation,
"pulmonary edema" is actually arguably easier to write than "hey" - and
definitely easier than "hay":)

esofagite actínica
esofagite cáustica
esofagite descamativa
esofagite eosinofílica
esofagite erosiva
esofagite herpética
esofagite por citomegalovirus
or
colite actínica
colite de Behçet
colite isquêmica
colite microscópica
colite por desvio de trânsito
colite pseudomembranosa
colite ulcerativa
What do you think?

I don't see how those are overly similar.
An intuitive and very indicative way to look at it is through the edit
distance of the phonetic transcriptions. The higher the edit distance, the
more diverse. For example, "eight", "mate", "kate", "gate", etc. all have an
edit distance of one.
I don't speak Portoguese but it looks like the terms you provided would be
pronounced quite differently...
Best regards,
Peter

[Peter Grasch]

Hello Steve,

Post by Steve Cookson
On the subject of long lists, the issue for us is giving each one a
command and data, so on calling
esofagite descamativa
really what I want it to do is call 'alt-d' for diagnosis and d123,
say, being the code for the specific diagnosis.
Does that work?

? Of course..?

I'm not 100 % sure what your question here is. Can you set up a command to
press Alt-D? Yes. Can you set up a command that presses Alt-D, writes "d123"
and releases the shortcut? Yes. (Shortcut to press, Text Macro to write,
Shortcut to release, all wrapped in a Composite command).

Also consider some trigger magicL Say, you'd want all commands starting with
"esofagite" to do the same thing, then you could set up a command to the
trigger "esofagite %%1" to catch everything that matches the regexp "esofagite
.*" (if you use one instead of two percent signs, it will only match a single
word instead of arbitrary strings).

Best regards,
Peter