Welcome Guest.   Make a donation to an author on the site October 24, 2014, 01:52:48 PM  *

Please login or register.
Or did you miss your validation email?


Login with username and password (forgot your password?)
Why not become a lifetime supporting member of the site with a one-time donation of any amount? Your donation entitles you to a ton of additional benefits, including access to exclusive discounts and downloads, the ability to enter monthly free software drawings, and a single non-expiring license key for all of our programs.


You must sign up here before you can post and access some areas of the site. Registration is totally free and confidential.
 
The N.A.N.Y. Challenge 2011! Download 30+ custom programs!
   
   Forum Home   Thread Marks Chat! Downloads Search Login Register  
Pages: [1] 2 Next   Go Down
  Reply  |  New Topic  |  Print  
Author Topic: Speech to Text Software?  (Read 10428 times)
Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« on: July 31, 2011, 03:51:04 AM »

Does anyone know of any software that can load an audio file and spit out text? It doesn't need to be 100% accurate. It just needs to work for the most part.

I bought a Dragon Naturally Speaking license (download), but it doesn't work. I'll save the rant. If you really need a rant, here's something to help a bit:


The only things that I've seen that look remotely decent are SDKs, and I don't want to do any programming. I just want to get things done. Sad
Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
joiwind
Participant
*
Posts: 480


carpe momentum

View Profile Give some DonationCredits to this forum member
« Reply #1 on: July 31, 2011, 06:14:06 AM »

Edited out - made a mistake !  Grin
« Last Edit: July 31, 2011, 06:20:41 AM by joiwind » Logged

.: I use K-Meleon - the browser you can control - but I love Pale Moon too :.
Ath
Supporting Member
**
Posts: 2,234



see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #2 on: July 31, 2011, 06:27:20 AM »

I'd start at this StackOverflow thread and follow the links mentioned there.
Logged

Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #3 on: July 31, 2011, 06:56:46 AM »

I'd start at this StackOverflow thread and follow the links mentioned there.

Thanks, but no luck. Sad

Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
joiwind
Participant
*
Posts: 480


carpe momentum

View Profile Give some DonationCredits to this forum member
« Reply #4 on: August 11, 2011, 06:31:17 AM »

@Ren : there is this strange thing that may be able to do something near to what you are looking for. I haven't tried it out myself yet (50 + mb download) but I will do as it looks fun to play with.

And check this site.

And then there's this the blurb says : "Cool C writes at the speed of speech and is always ready to read. Cool C is the fastest and easiest way to get your thoughts down on paper .... Just talk to Cool C and your words will be typed as you talk. When you are done, click READ and Cool C will read everything typed back to you."

The gui is vile beyond words (joke) and it doesn't seem possible to get a key for the trial, but I thought I'd bring it to your notice anyway.  Wink
« Last Edit: August 11, 2011, 07:36:24 AM by joiwind » Logged

.: I use K-Meleon - the browser you can control - but I love Pale Moon too :.
Curt
Supporting Member
**
Posts: 6,338

see users location on a map View Profile Give some DonationCredits to this forum member
« Reply #5 on: August 11, 2011, 09:34:56 AM »

maybe Adobe Audition CSS 5.5

Edited:
No.
--------

Contro asked for almost the same, but didn't find anything.
« Last Edit: August 11, 2011, 09:44:57 AM by Curt » Logged
Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #6 on: August 11, 2011, 05:13:19 PM »

No luck. The Cool C ReadWrite wouldn't run without a license, and the company is out of business it looks like. (Web site gone.)

@joiwind - The first link was a 404. Which did you mean there?
Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
J-Mac
Supporting Member
**
Posts: 2,867


see users location on a map View Profile Read user's biography. Give some DonationCredits to this forum member
« Reply #7 on: August 12, 2011, 11:48:55 PM »

Windows 7 - and Vista, I think - has its own Windows Speech Recognition engine/program. I understand that it's pretty decent too.

I have used Dragon and I can tell you that the base program is pretty much a demo; you need to use the Pro version, which costs quite a bit more!

Jim
Logged

"I am getting so tired of slitting the throats of people who say that I am a violent psychopath."
xtabber
Supporting Member
**
Posts: 385


View Profile Give some DonationCredits to this forum member
« Reply #8 on: August 14, 2011, 08:18:43 AM »

The quality of speech recognition depends on a lot of factors. If you want to use it for yourself, you can usually adapt your speech patterns to optimize results. If you want to capture speech from others and convert it to text, what you get is pretty unpredictable.

I moved my "business" phone # to Google Voice last year, which allows me to check messages as text transcriptions on my personal Android phone instead of listening to them.  Some people's voices don't "take" and either don't get transcribed at all, or get horribly mixed up, even though the voice message is perfectly clear to me. Others come through flawlessly, even though they are more difficult for me to hear.

Although it's not a publisheedl API and is not supported by Google, some folks have used Google Voice for voice recognition. See here for an example.

There are a number of voice recognition engines available for IVR (Interaactive Voice Recognition), which more and more firms (in the U.S., anyway) are turning to automate the initial contact phase of their telephone support services. Microsoft's Tellme is supposed to be built into Windows 8, and is available now for integration into commercial IVR solutions.

Unfortunately these IVR solutions are also being used for automated telephone marketing and polling, which is one reason I prefer to check my voice mail via transcription.
Logged
Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #9 on: August 14, 2011, 08:39:27 AM »

So far I've turned up nothing useful. Sure there are engines, but I don't want to do development for this. And if I had to, I'd want to work in C# and not C.

And I most certainly do not want to pay for every single word that goes through it. (A lot of SDKs are server-based and not much more than an uploader.)

I really just want something that "kind of" works. It doesn't need to be perfect, but good enough to go back and read or edit.

Well, I think I give up.
Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #10 on: August 14, 2011, 08:42:04 AM »

Tellme:

Quote
Cloud Platform

For enterprises, ISVs and service providers who want to build phone-based customer care using standards-based VoiceXML, use Tellme Studio with the Microsoft Tellme IVR Service.

Yep. Not for me.
Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
Shades
Member
**
Posts: 1,672


see users location on a map View Profile Give some DonationCredits to this forum member
« Reply #11 on: August 14, 2011, 09:07:28 AM »

WAV to text (trial/USD149.95 single developer license) could be what you are looking for.

It certainly looks easy enough to implement and is supported in: Visual C++, Visual Basic, Delphi, C++ Builder, .Net languages, Java and scripts like Perl, Php, Python etc.

You do need a separate SAPI5 speech recognizer though. Office 2003 is the last version of Office that shipped with one (but you can still download it from alternative sources). Windows 7 comes by default with one. And J-Mac is right, that one is quite decent.
Logged
joiwind
Participant
*
Posts: 480


carpe momentum

View Profile Give some DonationCredits to this forum member
« Reply #12 on: August 14, 2011, 12:25:18 PM »

No luck. The Cool C ReadWrite wouldn't run without a license, and the company is out of business it looks like. (Web site gone.)

@joiwind - The first link was a 404. Which did you mean there?

Sorry Ren, try this and look for AARON and AIB. But I'm not at all sure that you can use WAVs, just a micro.
Logged

.: I use K-Meleon - the browser you can control - but I love Pale Moon too :.
Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #13 on: August 15, 2011, 07:49:30 PM »

No luck. The Cool C ReadWrite wouldn't run without a license, and the company is out of business it looks like. (Web site gone.)

@joiwind - The first link was a 404. Which did you mean there?

Sorry Ren, try this and look for AARON and AIB. But I'm not at all sure that you can use WAVs, just a micro.

Downloading now...

On a side note, they use Google Docs for the download:

Quote
Sorry, we are unable to scan this file for viruses.

The file exceeds the maximum size that we scan. Download anyway

And that seems very odd. It's a glaring security hole. If you want to infect someone, simply upload a large file. Odd...

Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
1NR1
Supporting Member
**
Posts: 29


View Profile Read user's biography. Give some DonationCredits to this forum member
« Reply #14 on: August 22, 2011, 06:18:31 AM »

Well, what do you know, something I know about.

Here's how I do transcriptions from various sources. First off, Dragon is the best program for this, rant or rave, hands down, I've used them all since L&H, Via Voice etc. So unless you have a way to unlock the TV COP SHOW Prop computer that the pretty girl types into and quickly finds the secrets of the universe and the perps/unsubs pet's middle initial, you are going to have a learning curve. So I'll skip right to the short cut.

First, for a recorded file you have never performed any "training for" (I'll assume you've seen the tv commercial where the professors lecture appears miraculously quick and correct as a text document on a computer from 30 feet away (10 meters) using only the microphone installed in the computer cover?  If you haven't, no worries.  It's the same computer as the TV COP SHOW Prop computer that the pretty girl types into and quickly finds the secrets of the universe...  OK.  not going to happen.)

Now Curt (famously) is the only poster who got this right and was kind of "glossed over" and his suggestion about using Audition seemed to end.

Back to the shortcut. You need to process the file before you drag it into 'dragonpad'. The quick way of putting it would be to say, the best file should sound something like Donald Duck.  No, seriously.  Think about it. The less mid range/low and harmonics there are the better the speech engine will do.  I am NOT going to get into the audio analysis of all this here.

Second, my experience is you are better off starting with a .wav file.  Basically cut the lows and mids so it sounds somewhat "tinny". Pull out the pops and hiss and other noise. Slow it to about 67%. Then drag that processed sound file into Dragon or whatever.  (You may need to convert to mp3.)

Here's some summary points:

The clearer, less noisy, better articulated speaking on the original, the more accurate the text file will be.

Having a high quality microphone positioned properly is huge. (see above)

You can get around 80% accuracy. Remember most speech recognition programs spell the words correctly 100% of the time.  They just spell the wrong words.

About this 80%. It's not a distributed %, You may get a complete paragraph with 98% accuracy, and then a sentence completely unintelligible.

If you can get the speaker to dictate a few paragraphs from Dragons training files placing the mic at the pick-up position will greatly help accuracy.

Some recorded situations just don't work.

Hope this helps.  Cheers.

NR
Washington DC
Logged
Contro
Participant
*
Posts: 2,171

View Profile Give some DonationCredits to this forum member
« Reply #15 on: August 26, 2011, 04:16:51 PM »

Is a pending subject. it's not easy....
Logged
joiwind
Participant
*
Posts: 480


carpe momentum

View Profile Give some DonationCredits to this forum member
« Reply #16 on: August 30, 2011, 12:53:42 PM »

Renegade, another one you might like to look at here (look for PROBLEM ORIENTED RECORDS installer), there's a full description at Softpedia here.
I know it talks about medical records and so on but it contains a speech recognition word processor.

You never know ...  tongue
Logged

.: I use K-Meleon - the browser you can control - but I love Pale Moon too :.
joiwind
Participant
*
Posts: 480


carpe momentum

View Profile Give some DonationCredits to this forum member
« Reply #17 on: September 13, 2011, 05:26:12 AM »

Waking up an old thread with a new find for Renegade : Dictation Pro (free..?) - it only works with Vista and Win 7 ... Angry
Logged

.: I use K-Meleon - the browser you can control - but I love Pale Moon too :.
anandcoral
Honorary Member
**
Posts: 237



see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #18 on: September 13, 2011, 06:20:32 AM »

Yeah, just read about "Dictation Pro" in http://freewarehome.com/ (new listings) and was wondering if any one could tell it's worthness.

Now since @joiwind mentioned it, I hope @Renegade will try and give some feedback  smiley

brothersoft.com has some but all paidware, same for naturalreaders.com.

@Renegade, http://chronicle.com/blog...h-to-text-solutions/23016 gives tips to use Google Voice to make voicemail left for you, transcribed and then sent to your Gmail inbox !

I haven't tried any, and will be happy if someone reverts with the results.

Regards,

Anand
Logged
TalksToPCs
Supporting Member
**
Posts: 21

View Profile Give some DonationCredits to this forum member
« Reply #19 on: September 25, 2011, 02:59:56 PM »

Hi

I specialise in speech recognition software, I sell Dragon NaturallySpeaking and I always get it to work with my clients.
You might want to get help on a dedicated Dragon forum (like KnowBrainer Forum, which I am not affiliated with) if you cannot resolve problems on your own or if you don't want to call Nuance for assistance.

The only viable alternative for Windows Vista or 7 is Windows Speech Recognition, but you will need an add-on from eMicrophones (WSR Toolkit, http://emicrophones.com/p-3033-wsrtoolkit-v2.aspx; no affiliation here either) to transcribe audio files. Everything else is probably a nice try but if I were you, I would do anything to get Dragon NaturallySpeaking working with your setup. It really gets the job done.

Boris
Logged
Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #20 on: September 25, 2011, 08:25:23 PM »

Do I need the Pro version of DNS to transcribe files?

They have no trial versions available that I could find, which makes it very difficult to figure out.
Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
J-Mac
Supporting Member
**
Posts: 2,867


see users location on a map View Profile Read user's biography. Give some DonationCredits to this forum member
« Reply #21 on: September 25, 2011, 08:48:45 PM »

Do I need the Pro version of DNS to transcribe files?

They have no trial versions available that I could find, which makes it very difficult to figure out.

Basically, yes. Standard does almost nothing; no commands, just basic transcription but no way to properly correct it. They used to have a "Preferred" edition but I don’t know if that is still offered. Preferred does have the ability to create command scripts but is somewhat limited. Global commands - which are the most useful and necessary for some tasks - is only available in the Pro edition, or at least that was the case through Version 10. I used the Standard edition of DNS 7, and then the Preferred edition of DNS 8. I finally purchased the Pro version of DNS 9 and got the most use out of that but not enough error-free usage to justify buying DNS 10.

Jim
Logged

"I am getting so tired of slitting the throats of people who say that I am a violent psychopath."
Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #22 on: September 25, 2011, 09:17:15 PM »

Do I need the Pro version of DNS to transcribe files?

They have no trial versions available that I could find, which makes it very difficult to figure out.

Basically, yes. Standard does almost nothing; no commands, just basic transcription but no way to properly correct it. They used to have a "Preferred" edition but I don’t know if that is still offered. Preferred does have the ability to create command scripts but is somewhat limited. Global commands - which are the most useful and necessary for some tasks - is only available in the Pro edition, or at least that was the case through Version 10. I used the Standard edition of DNS 7, and then the Preferred edition of DNS 8. I finally purchased the Pro version of DNS 9 and got the most use out of that but not enough error-free usage to justify buying DNS 10.

Jim


Hmmm... I'd really like to try it first...

Is this the right one?

http://shop.nuance.com/st...US/pd/productID.231504200

They've got 666 trillion versions, and I really don't want to go through the pain of buying it AGAIN and then returning it because it doesn't do what I need.

(It would be nice if they had a complete feature set table... I suppose that's too much to ask what the product does... sigh...)

I'm somewhat tempted to see if I can find a cracked version to try and verify that it works before spending $200 on it... Nah... I can't be bothered...
Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
J-Mac
Supporting Member
**
Posts: 2,867


see users location on a map View Profile Read user's biography. Give some DonationCredits to this forum member
« Reply #23 on: September 25, 2011, 11:50:42 PM »

Looks like they have relabeled what I called the "Preferred" edition and now call it "Premium".

IMO the Professional version was the only one that was worthwhile. Of course it appears that the price difference is still very large! (Though it is actually lower now than when I purchased DNS Pro 9).

Thank you.

Jim
Logged

"I am getting so tired of slitting the throats of people who say that I am a violent psychopath."
Renegade
Charter Member
***
Posts: 11,639



Tell me something you don't know...

see users location on a map View Profile WWW Give some DonationCredits to this forum member
« Reply #24 on: September 26, 2011, 12:09:15 AM »

Looks like they have relabeled what I called the "Preferred" edition and now call it "Premium".

IMO the Professional version was the only one that was worthwhile. Of course it appears that the price difference is still very large! (Though it is actually lower now than when I purchased DNS Pro 9).

Ack... I don't really want to spend, what was it? 5, 6, 7, 800 dollars? Yikes. For those nutty numbers, I'd want a command line interface so that I could automate things... Sheesh...

Would the $200 version work for what I need?
Logged

Slow Down Music - Where I commit thought crimes...

Freedom is the right to be wrong, not the right to do wrong. - John Diefenbaker
Pages: [1] 2 Next   Go Up
  Reply  |  New Topic  |  Print  
 
Jump to:  
   Forum Home   Thread Marks Chat! Downloads Search Login Register  

DonationCoder.com | About Us
DonationCoder.com Forum | Powered by SMF
[ Page time: 0.054s | Server load: 0.04 ]