Ubuntu :: Finding Speech Recognition Software To Write Assignments?
Sep 13, 2010
I'm finding increasingly difficult to type because of neurological problems. I've just had a meeting with someone from university who said they could get me some speech recognition software to write assignments. I was wondering if anyone knows of any which will run on Ubuntu rather than just Windows. (I don't have Windows on either of my computers)
One of my friends seems to have been won over to the idea of me installing Linux onto his pc but he relies heavily on Dragon NaturallySpeaking voice recognition which unfortunately isn't available for Linux.
I have installed Fedora 11 recently on a new system. Sphinx speech recognition was working fine on my old system. When i run the same project on my new system, the system does not respond as it is waiting for microphone voice input.Then I checked the microphone and have set it properly and its working now. The details how i made my microphone working is at the following link:
[URL]
Quote:
Originally Posted by danfe [root@amit ~]# uname -r 2.6.30.10-105.2.23.fc11.i686.PAE [root@amit ~]# lspci | grep Audio
My wife is taking an online language course that requires Windows in order to record and playback speech (for pronunciation training). I decided the easiest thing to do would be to clone a VM I use on my machine for tasks that can only be accomplished in a Windows environment. I did so, and successfully installed the speech recognition utility on the Windows guest VM. Unfortunately, although the microphone works just fine--I can hear my voice in the headphones--no sound is recorded by the speech recognition utility. Just to be clear, the microphone is fully functional under GNU/Linux. My wife has been using Skype without any issues at all. That is, Skype used to work. Somewhere during the course of trying to resolve the voice recording problem I managed to break Skype. I have no idea how.
It's a long story, but I'll try to be as brief as possible. When I could not get the VM solution to work properly, I thought maybe the problem was with the VM, so I checked the original copy on my own machine. No problem there. Windows sees and hears the microphone just fine (using the testing utility under sound configuration). So how is it possible that the microphone doesn't work in the cloned VM image? Before you stop me, allow me to note that both machines have identical motherboards, and both are configured to use the onboard sound. Sound works on the Linux host and the Windows guest VM. Both sound and microphone work in the original VM image on my machine, but only sound works in the cloned VM on my wife's machine.
If you've followed me down the rabbit hole this far, please continue with me a bit further as things get stranger and stranger. After triple checking all the setting in KMix (I'm running Squeeze/KDE on both machines) to be sure they were identical, I noted that I was unable to view/add/enable the "channel" option on my wife's machine. Why, I have no idea. As I said, the machines are identical as can be both regarding hardware and software. Out of desperation, I decided to set up an account for my wife on my machine. I created her account, made sure she had the necessary audio permissions, then cloned my VM to her account. Same problem.
I would love for someone to point out what I'm missing here. Same hardware, identical VM (clone), same permissions, same sound configurations in KMix and under the Windows guest VM. How is it possible for the microphone to work for me, but not for my wife? Is there some mystery configuration file somewhere that has magically been altered for her account alone? The worst part about this entire process is that I've broken my wife's Skype, which is a big deal seeing as we live in a tiny country in the heart of Africa and cell phone communications are very expensive.
i want to backup some of my personal settings. for work i used emblems in nautilus to flag files i already processed (manually). now, i do not find any possiblity to back up the emblem-assignments. from older threads i figured out, that these assignments were in an .xml file in the ~/.nautilus/metadata folder, which is empty since newer versions of nautilus.i also tried to get some useful information out of the .local/share/gvfs-metadata/* files, but i did not succeed with this approach either (just used the "strings" command on them).edit: i'm aware, that i could write a script reading the metadata of the files via gvfs-info. the problem is, i cannot access the files from home, only at work via windows share.
I want a tool / library / package in C/C++/Python for basically Text to Speech - Speech to Text in Linux.I've tried pyttsx in python , but it runs only in windows as expected, in Linux (openSUSE 11.2 , the script just hangs up )festival in C. - in Ubuntu - Could not configured it successfully.
My wife is purchasing a netbook with no internal CD/DVD writing device, so we plan to purchase an external CD/DVD USB-2.0 read/write device. Our local PC shop has the following 3 external USB-2.0 DVD read/write devices:
(a) Samsung DVD-Burner SE-S084F/RSBS [not listed on Samsung site - too old ? ]
(b) LG DVD-Burner GE24NU21 USB2.0 [not listed on LG site - too old ? ]
(c) Super-Multi Portable DVD Rewrite (GP10 Lite USB2.0 Slimline) GP10NB20 (mentions Mac OS/X support, which is encouraging)
None of those are listed in the openSUSE HCL. Has anyone successfully used any of these with GNU/Linux (my google surfing on this revealed no GNU/Linux complaint nor any success stories) ? Or is there another such external USB-2.0 read/write DVD burner device that is recommended ?
I recently installed another harddrive into my Arch Linux computer. The first time I booted up all worked fine. The next time I restarted my computer though I was greeted with a /dev/sda2 not found error.
See, basically sometimes my boot harddrive is sda and sometimes it's sdb. It appears to be completely random and I don't see any options for making it non-random in the BIOS. How do I fix this?
Keytouch assignments do not take with Logitech Access keyboard. E.g. I have set MyHome key to run <firefox> but it runs a file browser instead. E-Mail works, but that's about all. None of the multimedia keys work.
Just fitted my netbook (Acer Aspire One) with 10.04 and now trying to connect to DSL Internet with Ethernet cable through Siemens 4200 modem.The "Ethernet" light on the modem does not come on as it does when i'm in Windows on the netbook nor as it does when I connect my desktop (with an earlier version of 10.04 with no wireless capability).
I'm trying to migrate to Ubuntu from Mac OS X. I have set up a dual boot on my MacBook and I am currently working to get everything I need for my computing-life up and running in Ubuntu.
I have found almost everything, expect a speech synthesis similar to the one native to Mac OS X's.
I use the OS X speech synthesis to have text I have written read back to be, I'm not blind; just really good a missing small words. What I don't want is to have all the menus and bottoms read out, only text I have selected.
I have tried something with 'festival' and some GUI overlay (think that is what it is called) but it read absolutely everything out loud (and sounds like Amiga's speech engine, i.e. a quite low quality).
In my Mac OS X I have a really nice set up (with a voice called Alex) where I can start speech of selected text with "cmd + ; " and stop it with " cmd+' " (two shortcuts not used by the system).
Are there any Speech recognization (Speech to text) software to use with Ubuntu (Lucid Lynx),So that I can dictate text in to a word processing program with them?
I installed Ubuntu on a machine of our laboratory. Since we are at the university connections may pass through a proxy (whose url we ignore). All things concerning system update are nearly unusable. Several posts say to add in apt strings like $ export http_proxy="http:" $ export ftp_proxy="http:" but I don't know the url proxy at all.Firefox is set to "Direct internet connection" and all work well. In Windows all connection properties were set to "automatic" and updates were ok.Is there a way to have an automatic recognition by apt?
In this case I have a video capture device but when plugged in (usb) the os doesn't recognise it. Is there software (device manager) where you can a least identyfy it?
Is there any way to get a text to speech engine on ubuntu like microsoft mike and mary? I tried espeak and gespeaker, but their selection of voices weren't too good.
My unit does not have internal DVD capability so I installed an external Sony that XP recognizes but ubuntu does not. I am 910 is that makes a difference.
I've got a bunch of hand-written notes which I would like to put into Kabikaboo (great app by the way) - but it is a real pain reading stuff then typing it up. I'd like a speech-to-text app, so I can just read my notes out loud and the computer will turn them into text files.Looking through Synaptic, all I can find is Julius; and that does not seem to be an easy-to-use app at all. So many parameters to set, an impenetratable (to me) manpage; and although I am a CLI user quite often, some kind of GUI would be nice.
I just upgraded on system from RedHat 4.0 to 4.8 and I'm having issues recognizing flash drives on the system. After a little bit of googling and attempting what some people recommend I am still having issues. I've tried the lsusb command but it doesn't seem to be recognized. I've searched the media and dev directories but found nothing showing any system recognition of USB devices. The ports do work as I've hopped the mouse and keyboard around to all of them and they work just fine.