Re: Build a speech generating device
On Sat, Jul 30, 2011 at 02:22:59PM +0200, Frederik Elwert wrote: * Dasher, as a complete different approach. I might be a good replacement for a regular virtual keyboard once mobility decreases to a level where a regular keyboard is hard to handle. But it seems not to be very well maintained, it???s quite unstable and I did not manage to get all of its functionality working I'm sorry to hear this - please let me know what problems you are having... We have already put together dasher running on android writing into talkadroid to provide mobile speech generation (both available from the android market place). The most recent dasher in the git repository (git clone git://git.gnome.org/dasher) will use speechdispatcher or gnome speech if it is installed on your system, and in combination with control mode will speak what you write. Best wishes, Patrick (dasher maintainer) -- Ubuntu-accessibility mailing list Ubuntu-accessibility@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-accessibility
Re: Build a speech generating device
Dear Patrick, Am Samstag, den 30.07.2011, 14:59 +0100 schrieb Patrick Welche: On Sat, Jul 30, 2011 at 02:22:59PM +0200, Frederik Elwert wrote: * Dasher, as a complete different approach. I might be a good replacement for a regular virtual keyboard once mobility decreases to a level where a regular keyboard is hard to handle. But it seems not to be very well maintained, it???s quite unstable and I did not manage to get all of its functionality working I'm sorry to hear this - please let me know what problems you are having... With the version in the Ubuntu repository I couldn’t get speech output working, and the direct mode was unreliable (only few of the characters were actually passed to the target application). We have already put together dasher running on android writing into talkadroid to provide mobile speech generation (both available from the android market place). The most recent dasher in the git repository (git clone git://git.gnome.org/dasher) will use speechdispatcher or gnome speech if it is installed on your system, and in combination with control mode will speak what you write. Okay, that sounds interesting. I’ll try out the latest code, maybe it already solves the issues I had. Otherwise, I’ll report back. In the documentation for dasher[1], it sais that it’s also possible to speak each word or on stop, not just in control mode. But I didn’t find any way to configure that. (But since control mode already failed, I didn’t investigate further.) I also just found a blog article that describes how to set up OpenMary as a speechdispatcher module.[2] That would probably allow to integrate dasher with OpenMary easily. On the other hand, if I write a speech synthesis frontend for normal keyboard use anyway, I might also just use dasher for text input and leave the rest to that application. I’ll see what works best. Thanks, Frederik [1] http://library.gnome.org/users/dasher/unstable/reallife.html.en [2] http://www.theopensourcerer.com/2011/05/05/speak-to-me/ -- Ubuntu-accessibility mailing list Ubuntu-accessibility@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-accessibility
Re: Build a speech generating device
Hi Justin, (I’m cc’ing the lists, as this might be valuable information for others. Hope that’s okay.) Am Samstag, den 30.07.2011, 09:50 -0400 schrieb Justin Duperre: Hi Frederik - I briefly worked on GNOME Caribou for a senior project in college. I am not sure of the state of presage integration, but what I can tell you is that a lot of work has been done on Caribou lately. In the past six months there have been major contributions to the code. It would definitely be a good choice for your project as the team is very active. Yes, I also saw that in the course of GNOME 3 Caribou got a lot of attention. Since I couldn’t find an official release, I was just wondering how far this is from completion, so that one can actually start using it, and if word prediction was just an experiment or part of the recent development efforts. I have also used Dasher, and I agree with everything you said about it. I think both cover slightly different usage scenarios, so it’d be great to have both available. Are you planning on making this a public open source project? Currently, I’m only doing a bit of research. My primary aim is to use existing and stable software. But the parts I might end up writing myself will be open source. I think primarily of an improved gespeaker, or a new speechd frontend. (Having OpenMary support in speechd will probably make things much easier.) Besides actually writing code, I am planning to document the project, so that others can benefit from my findings and experience. Regards, Frederik -- Ubuntu-accessibility mailing list Ubuntu-accessibility@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-accessibility
Re: Build a speech generating device
On 30/07/11 15:39, Frederik Elwert wrote: I also just found a blog article that describes how to set up OpenMary as a speechdispatcher module.[2] That would probably allow to integrate dasher with OpenMary easily. I wrote that article, give me a shout or find me in #ubuntu-accessibility on freenode if you want any help setting it up. Alan. -- The Open Learning Centre is rebranding, find out about our new name and look at http://libertus.co.uk -- Ubuntu-accessibility mailing list Ubuntu-accessibility@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-accessibility
Re: Build a speech generating device
On Sat, 30 Jul 2011, Frederik Elwert wrote: there are only few speech generating devices (SGDs) available on the market, and those are as limited as they are expensive, I plan to build a custom SGD using a tablet computer as a basis and applying available I don't know about the hardware. I knew people who used Texas Instruments chips, but I don't expect they'd include all the German phonemes. The primary components I identified to be necessary are * a virtual keyboard with word prediction OK, the only one I know of is Dasher, which you have found. The inference group have a thing called Tapir, which is designed for on screen text entry like texting. I don't think it will do all the symbols on the keyboard, but it is at http://www.inference.phy.cam.ac.uk/tapir/ It didn't seem to be a quick way of getting text in, but for people with low mobility it may have some use. In the book Beautiful Code [Andy Oram, Greg Wison, O'Reilly, 2007, ISBN:9780596510046] Chapter 30 When a button is all that connects you to the world discusses the software used by Professor Hawking. It claims the download is at http://holisticit.com/eLocutor/elocutorv3.htm although I can find nothing useful there. The search engines take me to http://hawking.sourceforge.net/ and it appears that the download is available as an executable or a Zip file, so I suspect it is Windows only. For prediction there is also Presage http://presage.sourceforge.net/ which is really a library, so could be attached to something else. It does have some wxPython demos, which I can't get working [on Cygwin], though your experience on Linux could well be better. Way back, there used to be a program called reactivekbd, which was a predictive text entry system that could be used from the shell. It seems to be here: http://ftp.sunet.se/pub/usenet/ftp.uu.net/comp.sources.unix/volume20/reactivekbd/ I had that working under Sunos 4.mumble, but have not retried recently. The dasher project does have the Tcl/Tk dasher which may still be useful if you can't get the rest to build and work, but that ought to reasonably easy to connect to the HTTP interface of OpenMary. * pre-defined text snippets * a speech synthesizer backend (for German language output) I think espeak supports German, but I'm not in a position to comment on the quality. http://espeak.sourceforge.net/ * a frontend to the speech synthesizer Both OpenMary and Espeak have front ends you can type into. The OpenMary example client is in Java, and there is a Ruby one and a Python one in the repository now. They will need more work for non-Windows: lots of choices for sound on Linux. For the speech synthesizer, I currently plan to use OpenMary[1], since its output quality is significantly better than espeak?s, even with mbrola voices. I think they are dropping mbrola voices because they need a non-java backend for it, and they mostly have prosody working now. See Msg Id: 4da410ad.8040...@dfki.de posted to Mary-users on 12 APR 2011. For the speech synthesizer frontend, I plan to either adapt gespeaker, I don't know about gespeaker, so I searched, and found this: http://alternativeto.net/software/gespeaker/ thereby finding Kmouth http://www.schmi-dt.de/kmouth/index.en.html which claims to have word completion and a phrase book, as well as history. [The rest trimmed] Hope some of that helps, Hugh -- Ubuntu-accessibility mailing list Ubuntu-accessibility@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-accessibility
Re: Build a speech generating device
On Sat, 30 Jul 2011, Hugh Sasse wrote: In the book Beautiful Code [Andy Oram, Greg Wison, O'Reilly, 2007, s/Wison/Wilson/ ISBN:9780596510046] Chapter 30 When a button is all that connects Hugh -- Ubuntu-accessibility mailing list Ubuntu-accessibility@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-accessibility