Voice Recognition

Voice or speech recognition includes methodologies and technologies that enable the recognition and translation of spoken language into text by computers and computerized devices. It is also known as "automatic speech recognition" (ASR), "computer speech recognition", or just "speech to text" (STT). Voice recognition applications include voice user interfaces such as voice dialling (e.g. "Call home"), call routing (e.g. "I would like to make a collect call"), appliance control, search, simple data entry, preparation of structured documents, speech-to-text processing, and aircraft (usually termed Direct Voice Input).

Share tech news, updates, or what's on your mind.

Sign up to Post

How can I get Dragon to dictate on my AOL Email? I should also note that after the update there are numerous times I can't get on the internet.
Free Tool: ZipGrep
Free Tool: ZipGrep

ZipGrep is a utility that can list and search zip (.war, .ear, .jar, etc) archives for text patterns, without the need to extract the archive's contents.

One of a set of tools we're offering as a way to say thank you for being a part of the community.

Hi ,

I have a multimedia room with the following equipment in it:

- Denon AVR-X4300
- Dali In-Wall Speakers
- Dali Centre Speaker
- Dali Subwoofer
- Projector Sony HW45ES
- BluRay player Oppo UDP-203

Which of these products would work better with this equipment, the Amazon Echo or the Amazon Dot?

My ref: 1029743
I am a deaf individual and have never been able to use the telephone efficiently due to the fact that I need to lipread.  I sometimes hear snippets of the conversation, but not reliably enough to conduct a professional conversation.  I am not the only one in this boat either.

Over the years I have tried assisted typing services and even voice recognition apps, but I am yet to find anything that works effectively.  Last year I obtained a small grant and put this into the development of an Android voice recognition app, but unfortunately it didn't work very well and I ran out of funding.  I was dealing with an Indian firm and I think they were using an off the shelf online service to process the speech, which was very unreliable and led to unacceptable delays in the processed text appearing on screen.  It was clear to me after this experience that I need to work with experts in the field to stand a chance of success.

I've been toying with the idea of setting up a crowdfunding project to help develop an app that can overcome the obstacles faced by millions of deaf people.  But first It would be helpful to obtain opinions from voice recognition experts, for instance, what is the current state of play in the field?  What limitations are we going to face?  What sort of money are looking at?  Obviously I'm going to need to quantify the whole process before I can put it before the crowd funders or investors.  

I'd love to find any interested experts I can work with towards …
im trying to use Speech Recognizer class and I have no sr engine.

Can I use this?

  await   Windows.ApplicationModel.VoiceCommands.VoiceCommandDefinitionManager.InstallCommandDefinitionsFromStorageFileAsync(IStorageFile file);

is this going to create an engine or something???

Will I be able to use speech recognizer???

what is Cortana???
Windows 7 SP1 64-bit system unable to update Dragon v15 with Error 13000 from software manager.  I can login to the client Nuance.com account, but do not see any option to download updates.  Is there a download available for just the updates?  Any other thoughts?
Is there good speech recognition for ubuntu?
It is pretty amazing what Amazon has made available to developers now. I am hoping to get to investigate https://developer.amazon.com/public/solutions/alexa/alexa-voice-service/content/avs-api-overview soon.  This really opens up the door for speech driven applications.

Expert Comment

by:Brandon Lyon
If you have any questions let me know. I've already used the Alexa Skills Kit for some small stuff.
What are the choices available for converting spoken words into text --like my iPhone does.  I'd like to speak into my microphone and convert it into a word document. Is there a built-in feature that I'm not using?  Or do I need to purchase something?
what is the best audio editing software
I have an audio file that has multiple people speaking on it.
I want to reduce the sound of one/2 persons and enhance  the voice of other person. it looks there is some hiss sound and some kind of noise. I also want to remove it.

in short I could say.. I a looking for a software that has the capability to split multiple sounds edit/enhance them individually and then save it.  

is that possible???
I use my iphone alot to record meetings, because I have poor listening skills, or I think I just have selective hearing. To refresh my memory on meeting discussions, i usually listen to my recordings later and write down important details. It's becoming a time consuming process. I want the ability to convert my voice recording from my iphone into a text file so I can view it in text. How can I accomplish this?
On Demand Webinar: Networking for the Cloud Era
On Demand Webinar: Networking for the Cloud Era

Did you know SD-WANs can improve network connectivity? Check out this webinar to learn how an SD-WAN simplified, one-click tool can help you migrate and manage data in the cloud.


How do you remove software when it is not included in the Control Panel > Programs & Features folder?

For example, the screenshot below shows something called "FlexNet Connect Common Software Manager" which apparently is clandestinely installed on your system with Dragon NaturallySpeaking (Nuance) voice recognition software. It occasionally pops up and I'd like to just get rid of it.


• How can an "app" be running (and listed in the Task Manager) but not displayed in Program & Features?

• Is it okay to just find the app in the Program Files,  Program Files (x86), and/or ProgramData and delete whatever folders are there?

• I use Everything (Search Utility). Can I just delete all the files/folders which turn up there when searched for "FlexNet", etc?

• What other/better methods are available to accomplish the same objective.

By the way, I have a Malwarebytes account but I guess it does not consider something like this software as being malicious.

Dear Experts,

My clients need to open and listen to a group of .sri files, created by VXI Voice It recorder.  The problem is, the product has not been manufactured, and supporting website for player is no longer available.  I found many file converters that claims to handle SRI, but when I try these converters, it will not open SRI files.  I have tried SONY Voice Editor, Dragon Naturally Speaking, NCH Switch, etc.
Please advise.
Hello Experts,

Can someone please let me know if there is any software / application that will recognise voice, from say a video, a convert that voice to written text, or subtitles or captions?

I'm not sure if I'm making myself clear, but I hope someone understands what I'm trying to say.


I am looking for a software which can convert voice to text file.  I already have dragon one but i am looking for a second option as well in order to compare the both.  Need to do it as a part of my assignment.

Suggestions will b highly appreciated
i'm working for a doctors office and we have an answering service which answers their call during off hours and forwards a text to the dr. when a patient has an issue.  this answering service is getting increasingly incompetent (rude, beligerant with patients, make lots of mistakes).  i've heard of people using google voice and using the voicemail transcription service to forward a text of a voicemail the patient leaves the dr to the dr's cellphone.  i'm looking for some help setting this up.  i've gone to the google voice site and the google voice help forums.  but, don't understand the process of porting to google voice.  do i have to port the cell phone i want texts forwarded to google voice?  will i no longer be subscribed to AT&T?  i don't understand where google voice begins and AT&T ends.  i understand it's a $20 fee to port the number.  is this a monthly fee? or a one time charge? i have several doctors which are on call. do i have to port all their numbers?  and am i thinking of this correctly? the mobile number is the one you port?  the patient calls the office number ( a land line) and the voicemail is transcribed and forwarded to the cell phone number?
I'm using Google voice typing to catalogue a some bookshelves of books, it's working well but I'm not able to command a new line reliably so my workaround is just to use a word that's easily picked up, like "banana" for example, and then find/replace that word when i'm finished.

This also has the advantage that a pause is not needed, so i can read titles faster, albeit sounding a bit bananas!

I could do this in Microsoft Word if I still had it. Is it possible in Google docs? Or google sheets, or another tool, preferably online, that i can easily copy paste the text to.

I want to catalogue some shelves of books without taking them off the shelf. I'd like just to read out the book title, author and publisher and have this logged on my phone. If I do this with Google voice it returns the correct book. How can i save the first result of a search and immediately return Google back to listening mode? This would effectively generate a list by dictation. I have not been able to find an app that does this.
Dragon Naturally Speaking often recommends running with UAC disabled.... how dangerous is this?   If I have good anti-virus and anti-malware software is that enough?  (And what would good AV/AM be?)
After performing a clean install of Windows 10, reinstalling my software and restoring my data, I noticed that my Windows partition was considerably larger than it had been prior to upgrading from Windows 7. At the time, I simply assumed that Windows 10 was larger than Windows 7. I accepted that as a reasonable explanation, but couldn't help but notice other symptoms that my partition was growing. I use Acronis's True Image to create a backup of my partition every day. Those backups took longer and longer as the partition grew.

A couple of months after installing Windows 10, I attempted to create a number of virtual machines using both vSphere and VMware. I was not successful. What is significant about that is that I had trouble removing the virtual disks from my system. Recently, while trying to figure out what was taking up all the space on my disk, I came across a 70 gigabyte file under the Virtual Machines directory tree. When I tried removing it, I was denied access. With the help of experts on this site I managed to overcome that obstacle and get the directory removed. Much to my amazement, that single action reclaimed 500 gigabytes of space!? I don't know where the other 400+ gigabytes came from, but I suspect there was something hidden within the Virtual Machines directory tree. The amount of the C: partition being used went from approximately 800 gigabytes down to 282! The next time I ran a backup, it finished in half the time!

Approximately one week later, the…
Free Tool: SSL Checker
Free Tool: SSL Checker

Scans your site and returns information about your SSL implementation and certificate. Helpful for debugging and validating your SSL configuration.

One of a set of tools we are providing to everyone as a way of saying thank you for being a part of the community.

I am using Dragon Naturally speaking 14 and while the installation went well it heard and created a dictation box upon complete set up i can not get the "transcription source is currently off  - click to turn on"  but no matter what i do i can not get the microphone to turn on.  
I want Dragon Home Version 13 to “run in the background”. I saw some webpages that said this requires the expensive Dragon Medical Practice Edition, but I figured out a way to do it with Dragon Home.

Unfortunately, my solution requires two computers, and I hope some experts exchange magician can improve this solution to only need a single computer.

Here are the details:

I often transcribe PDFs that contain faxes of multipage contracts. I ignore most of the boilerplate language, and transcribe only the important items. (OCR will not work)

The “smooth” solution is to view the PDF on my laptop computer, while using dragon on my main computer to input into Dragon and Notepad.

My physical interaction is on the laptop and my finger never leaves the laptop’s page down key. The main computer “runs in the background” and I don’t touch it until I am done.

I speak the item from page 1.
I tap the laptop pgdn key and speak the text from page 2.
Etc. etc.

If I try to do the same thing on a single computer with dual monitors, things become extremely cumbersome and look like this.

I view page 1 of pdf
I click on Notepad document and speak the text from pdf page 1
I click on pdf and page down to page 2
I click on Notepad and speak the text from page 2
Etc. etc.

All that clicking completely ruins the transcription experience.

Does anybody know how to configure dragon for single computer so that the pdf is active at all times, and dragon interacts with Notepad (or dictation box) …
I watched the following 43 videos already and got some exposure to Python this past week...


Now I need to get some better videos, develop some hands on experience with Python and steps into learning about the ntlk Python library.

What are your suggestions for a crash course? Free Videos?

I am new to Python and NLTK, but am eager to learn.

What kinds of things can you do with the Natural Language Tool Kit?

Clean install of Windows 10 Pro and Dragon NaturallySpeaking 13 Premium.
If Dragon is running then Chrome has a black window. If Dragon is not running then Chrome is OK.
Tried disabling Dragon extension in Chrome, but this made no difference - still a black window.

The computer has a NVIDIA NVS300 dual screen card with two screens attached. We have other computers on the network running the same combination but without Dragon which all seem to work fine.

Chrome version       51.0.2704.79
Windows version 10.0.10586

Many thanks for any ideas!
I need to setup an IVR (Interactive Voice Response) configuration with my Office 365/SfB telephone number. When customers call my number, I want them to navigate through a selection system to better navigate to the correct department/person.

All of the users that I want the phone to navigate to already have O365 accounts and telephone numbers.

Voice Recognition

Voice or speech recognition includes methodologies and technologies that enable the recognition and translation of spoken language into text by computers and computerized devices. It is also known as "automatic speech recognition" (ASR), "computer speech recognition", or just "speech to text" (STT). Voice recognition applications include voice user interfaces such as voice dialling (e.g. "Call home"), call routing (e.g. "I would like to make a collect call"), appliance control, search, simple data entry, preparation of structured documents, speech-to-text processing, and aircraft (usually termed Direct Voice Input).

Top Experts In
Voice Recognition

No Top Experts for this time period. Answer questions to earn the title!