Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
Hi :) I get the feeling there isn't anything really new but maybe updates have changed things a little. It's mostly just that there have been a few things out there that might suit different requirements. Regards from Tom :) On 4 December 2014 at 02:34, Andrew Douglas Pitonyak wrote: > I have not looked in a long time... I have trouble with my wrists > sometime, so, it would be nice if I had something that would integrate... > > Been a few years since I looked so perhaps it is time for another look. > > On 12/03/2014 04:48 AM, Tom Davies wrote: > >> Hi :) >> We have the same thread going on the Accessibility Mailing List now too. >> It might be worth looking at it through the Nabble or GMane interfaces. >> >> Over there Eric suggested NaturallySpeaking 13 but had several good >> detailed points about issues relating to the whole area of speech and >> voice >> recognition. Well worth a read if this area interests you but it's about >> as long as one of my longer mails. Interesting though! :) >> >> >> Wrt Bible, Koran or Torah study programs Linux does have quite a large >> range of different packages to help. For the Bible there are different >> programs to cover different versions (such as the King James(?) vs >> whatever >> and whatever else). Of course each person needs something slightly >> different so i can well imagine Andrew's typical hefty research into a >> topic of interest didn't find anything to suit him but something there >> might suit you, if you are interested. >> >> Regards from >> Tom :) >> >> >> >> >> On 3 December 2014 at 04:55, Walther Koehler >> wrote: >> >> High Eric, >>> >>> thank you for that information. I was trying to get a speech recognition >>> system running for some time. >>> I have been using the IBM-line of speech recognition ViaVoice/Nuance >>> under >>> Win98 with some success. Now, I planned to use it in VirtualBox. >>> >>> -Do you have experience with ViaVoice, are there reasons to prefer >>> NaturalSpeaking? >>> >>> -Why did you choose KVM over VirtualBox? >>> >>> Have a good day >>> >>> Walther >>> >>> Am Dienstag, 2. Dezember 2014 schrieb Eric: >>> On 12/2/2014 3:08 PM, charles meyer wrote: > Hi Tom, > > I spoke with someone who uses Linux and they shared that Sphinx - > voice translation is new so many may not have tried it yet. > > Sorry for jumping the gun, so to speak. > It's speech recognition, not voice translation. If I throw you off the top of the building, I'm going to hear your voice. If I push you near the edge of the roof, I would hear your speech.. Sphinx has been around for at least 15 years in different forms. It has been, and probably always will be a system designed for IVR (interactive voice response, "speak or press one to get ignored by a customer service representative"). It is not and never will be a system for general-purpose speech recognition. The only useful speech recognition packages are NaturallySpeaking with a not very close runner-up of Windows speech recognition. Google speech recognition would be in the running if it wasn't bound to a very limited number of apps with no user accessible grammars. I'm currently experimenting with running Windows in a KVM virtual machine, running NaturallySpeaking there and find a way to see the output of NaturallySpeaking back to the Linux host OS. If I can get the audio stream clean enough, it looks like a promising technique for adding speech recognition to Linux Now all I need some help to figure out what I don't know about injecting keystrokes into linux and may be help with fixing up KVM so it passes audio cleanly under most conditions. >>> >>> >>> -- >>> To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org >>> Problems? >>> http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ >>> Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette >>> List archive: http://listarchives.libreoffice.org/global/users/ >>> All messages sent to this list will be publicly archived and cannot be >>> deleted >>> >>> > -- > Andrew Pitonyak > My Macro Document: http://www.pitonyak.org/AndrewMacro.odt > Info: http://www.pitonyak.org/oo.php > > > -- > To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org > Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to- > unsubscribe/ > Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette > List archive: http://listarchives.libreoffice.org/global/users/ > > All messages sent to this list will be publicly archived and cannot be > deleted > -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users
Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
I have not looked in a long time... I have trouble with my wrists sometime, so, it would be nice if I had something that would integrate... Been a few years since I looked so perhaps it is time for another look. On 12/03/2014 04:48 AM, Tom Davies wrote: Hi :) We have the same thread going on the Accessibility Mailing List now too. It might be worth looking at it through the Nabble or GMane interfaces. Over there Eric suggested NaturallySpeaking 13 but had several good detailed points about issues relating to the whole area of speech and voice recognition. Well worth a read if this area interests you but it's about as long as one of my longer mails. Interesting though! :) Wrt Bible, Koran or Torah study programs Linux does have quite a large range of different packages to help. For the Bible there are different programs to cover different versions (such as the King James(?) vs whatever and whatever else). Of course each person needs something slightly different so i can well imagine Andrew's typical hefty research into a topic of interest didn't find anything to suit him but something there might suit you, if you are interested. Regards from Tom :) On 3 December 2014 at 04:55, Walther Koehler wrote: High Eric, thank you for that information. I was trying to get a speech recognition system running for some time. I have been using the IBM-line of speech recognition ViaVoice/Nuance under Win98 with some success. Now, I planned to use it in VirtualBox. -Do you have experience with ViaVoice, are there reasons to prefer NaturalSpeaking? -Why did you choose KVM over VirtualBox? Have a good day Walther Am Dienstag, 2. Dezember 2014 schrieb Eric: On 12/2/2014 3:08 PM, charles meyer wrote: Hi Tom, I spoke with someone who uses Linux and they shared that Sphinx - voice translation is new so many may not have tried it yet. Sorry for jumping the gun, so to speak. It's speech recognition, not voice translation. If I throw you off the top of the building, I'm going to hear your voice. If I push you near the edge of the roof, I would hear your speech.. Sphinx has been around for at least 15 years in different forms. It has been, and probably always will be a system designed for IVR (interactive voice response, "speak or press one to get ignored by a customer service representative"). It is not and never will be a system for general-purpose speech recognition. The only useful speech recognition packages are NaturallySpeaking with a not very close runner-up of Windows speech recognition. Google speech recognition would be in the running if it wasn't bound to a very limited number of apps with no user accessible grammars. I'm currently experimenting with running Windows in a KVM virtual machine, running NaturallySpeaking there and find a way to see the output of NaturallySpeaking back to the Linux host OS. If I can get the audio stream clean enough, it looks like a promising technique for adding speech recognition to Linux Now all I need some help to figure out what I don't know about injecting keystrokes into linux and may be help with fixing up KVM so it passes audio cleanly under most conditions. -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted -- Andrew Pitonyak My Macro Document: http://www.pitonyak.org/AndrewMacro.odt Info: http://www.pitonyak.org/oo.php -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted
Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
On 03/12/14 12:55, Tim---Kracked_P_P---webmaster wrote: > Is there any FREE ones that work well for Windows? No. The entire field is wrapped up in mathematical algorithms that have been illegally granted patents. > That is what the speech recognition really us needed. All of that was available, before Nuance decided that they would help those with a11y requirements by ensuring that R&D was stopped, and working products were pulled from the market place. Indeed, the achievement that Nuance is proudest of, is that those with a11y needs no longer have the tools that would help them. jonathon -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted
Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
On 12/03/2014 07:55 AM, Tim---Kracked_P_P---webmaster wrote: I see on TV "Dragon Natural Speaking". That is the "NaturalSpeaking" your have listed below, right? yes. Which package[s] is[are] good for Linux - i.e. Debian based ones like Ubuntu and Linux Mint. none so far. they are all windows based and will stay that way. this is why I'm trying to make encyst windows and DNS (Dragon NaturallySpeaking) inside of kvm. Is there any FREE ones that work well for Windows? none. all useful speech reco is decidedly not libre. Nuance is really locked up that way. It would be real nice to get a Linux Box set up for a neighbor that is blind - since I do not have a spare Windows system and she cannot afford to buy the Windows OS like Win7. Be nice to have it set up for "reading" e-books - in their epub format or converted to text - instead of trying to find audio book copies. Of course you will need the voice commands to run the system to get the "box" to find the book, play, pause, stop, go back, etc.. That is what the speech recognition really us needed. look into making a simple Braille keypad with those controls using a rasberry pi. you probably could make the whole ebook reader out of one. feel free to contact me off list for design ideas. -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted
Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
On 12/02/2014 11:55 PM, Walther Koehler wrote: High Eric, thank you for that information. I was trying to get a speech recognition system running for some time. I have been using the IBM-line of speech recognition ViaVoice/Nuance under Win98 with some success. Now, I planned to use it in VirtualBox. ooh, that is old stuff. you should look for a sale on DNS 13 this month. nuance should have preferred on sale for 100$ instead of 200$. pick yourself up an logitech h800 headset form staples and off you go. -Do you have experience with ViaVoice, are there reasons to prefer NaturalSpeaking? via voice was the package of choice for court stenographers because it could be tuned but overall NaturallySpeaking was a better choice. look up natlink/vocola for a python based extension environment to nat-speak. -Why did you choose KVM over VirtualBox? because VBox has really lousy audio handling. could not get a clear stream of audio to nat-speak so recognition was terrible. hoping I can get/find a solution for kvm and usb audio. -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted
Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
I see on TV "Dragon Natural Speaking". That is the "NaturalSpeaking" your have listed below, right? Which package[s] is[are] good for Linux - i.e. Debian based ones like Ubuntu and Linux Mint. Is there any FREE ones that work well for Windows? It would be real nice to get a Linux Box set up for a neighbor that is blind - since I do not have a spare Windows system and she cannot afford to buy the Windows OS like Win7. Be nice to have it set up for "reading" e-books - in their epub format or converted to text - instead of trying to find audio book copies. Of course you will need the voice commands to run the system to get the "box" to find the book, play, pause, stop, go back, etc.. That is what the speech recognition really us needed. On 12/02/2014 11:55 PM, Walther Koehler wrote: High Eric, thank you for that information. I was trying to get a speech recognition system running for some time. I have been using the IBM-line of speech recognition ViaVoice/Nuance under Win98 with some success. Now, I planned to use it in VirtualBox. -Do you have experience with ViaVoice, are there reasons to prefer NaturalSpeaking? -Why did you choose KVM over VirtualBox? Have a good day Walther Am Dienstag, 2. Dezember 2014 schrieb Eric: On 12/2/2014 3:08 PM, charles meyer wrote: Hi Tom, I spoke with someone who uses Linux and they shared that Sphinx - voice translation is new so many may not have tried it yet. Sorry for jumping the gun, so to speak. It's speech recognition, not voice translation. If I throw you off the top of the building, I'm going to hear your voice. If I push you near the edge of the roof, I would hear your speech.. Sphinx has been around for at least 15 years in different forms. It has been, and probably always will be a system designed for IVR (interactive voice response, "speak or press one to get ignored by a customer service representative"). It is not and never will be a system for general-purpose speech recognition. The only useful speech recognition packages are NaturallySpeaking with a not very close runner-up of Windows speech recognition. Google speech recognition would be in the running if it wasn't bound to a very limited number of apps with no user accessible grammars. I'm currently experimenting with running Windows in a KVM virtual machine, running NaturallySpeaking there and find a way to see the output of NaturallySpeaking back to the Linux host OS. If I can get the audio stream clean enough, it looks like a promising technique for adding speech recognition to Linux Now all I need some help to figure out what I don't know about injecting keystrokes into linux and may be help with fixing up KVM so it passes audio cleanly under most conditions. -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted
Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
Hi :) We have the same thread going on the Accessibility Mailing List now too. It might be worth looking at it through the Nabble or GMane interfaces. Over there Eric suggested NaturallySpeaking 13 but had several good detailed points about issues relating to the whole area of speech and voice recognition. Well worth a read if this area interests you but it's about as long as one of my longer mails. Interesting though! :) Wrt Bible, Koran or Torah study programs Linux does have quite a large range of different packages to help. For the Bible there are different programs to cover different versions (such as the King James(?) vs whatever and whatever else). Of course each person needs something slightly different so i can well imagine Andrew's typical hefty research into a topic of interest didn't find anything to suit him but something there might suit you, if you are interested. Regards from Tom :) On 3 December 2014 at 04:55, Walther Koehler wrote: > High Eric, > > thank you for that information. I was trying to get a speech recognition > system running for some time. > I have been using the IBM-line of speech recognition ViaVoice/Nuance under > Win98 with some success. Now, I planned to use it in VirtualBox. > > -Do you have experience with ViaVoice, are there reasons to prefer > NaturalSpeaking? > > -Why did you choose KVM over VirtualBox? > > Have a good day > > Walther > > Am Dienstag, 2. Dezember 2014 schrieb Eric: > > On 12/2/2014 3:08 PM, charles meyer wrote: > > > Hi Tom, > > > > > > I spoke with someone who uses Linux and they shared that Sphinx - > > > voice translation is new so many may not have tried it yet. > > > > > > Sorry for jumping the gun, so to speak. > > > > It's speech recognition, not voice translation. If I throw you off the > > top of the building, I'm going to hear your voice. If I push you near > > the edge of the roof, I would hear your speech.. > > > > Sphinx has been around for at least 15 years in different forms. It has > > been, and probably always will be a system designed for IVR (interactive > > voice response, "speak or press one to get ignored by a customer service > > representative"). It is not and never will be a system for > > general-purpose speech recognition. > > > > The only useful speech recognition packages are NaturallySpeaking with a > > not very close runner-up of Windows speech recognition. Google speech > > recognition would be in the running if it wasn't bound to a very limited > > number of apps with no user accessible grammars. I'm currently > > experimenting with running Windows in a KVM virtual machine, running > > NaturallySpeaking there and find a way to see the output of > > NaturallySpeaking back to the Linux host OS. If I can get the audio > > stream clean enough, it looks like a promising technique for adding > > speech recognition to Linux > > > > Now all I need some help to figure out what I don't know about injecting > > keystrokes into linux and may be help with fixing up KVM so it passes > > audio cleanly under most conditions. > > > > -- > To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org > Problems? > http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ > Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette > List archive: http://listarchives.libreoffice.org/global/users/ > All messages sent to this list will be publicly archived and cannot be > deleted > -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted
Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
High Eric, thank you for that information. I was trying to get a speech recognition system running for some time. I have been using the IBM-line of speech recognition ViaVoice/Nuance under Win98 with some success. Now, I planned to use it in VirtualBox. -Do you have experience with ViaVoice, are there reasons to prefer NaturalSpeaking? -Why did you choose KVM over VirtualBox? Have a good day Walther Am Dienstag, 2. Dezember 2014 schrieb Eric: > On 12/2/2014 3:08 PM, charles meyer wrote: > > Hi Tom, > > > > I spoke with someone who uses Linux and they shared that Sphinx - > > voice translation is new so many may not have tried it yet. > > > > Sorry for jumping the gun, so to speak. > > It's speech recognition, not voice translation. If I throw you off the > top of the building, I'm going to hear your voice. If I push you near > the edge of the roof, I would hear your speech.. > > Sphinx has been around for at least 15 years in different forms. It has > been, and probably always will be a system designed for IVR (interactive > voice response, "speak or press one to get ignored by a customer service > representative"). It is not and never will be a system for > general-purpose speech recognition. > > The only useful speech recognition packages are NaturallySpeaking with a > not very close runner-up of Windows speech recognition. Google speech > recognition would be in the running if it wasn't bound to a very limited > number of apps with no user accessible grammars. I'm currently > experimenting with running Windows in a KVM virtual machine, running > NaturallySpeaking there and find a way to see the output of > NaturallySpeaking back to the Linux host OS. If I can get the audio > stream clean enough, it looks like a promising technique for adding > speech recognition to Linux > > Now all I need some help to figure out what I don't know about injecting > keystrokes into linux and may be help with fixing up KVM so it passes > audio cleanly under most conditions. -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted
Re: [libreoffice-users] Re: Sphinx - voice translation - Linux
On 12/2/2014 3:08 PM, charles meyer wrote: Hi Tom, I spoke with someone who uses Linux and they shared that Sphinx - voice translation is new so many may not have tried it yet. Sorry for jumping the gun, so to speak. It's speech recognition, not voice translation. If I throw you off the top of the building, I'm going to hear your voice. If I push you near the edge of the roof, I would hear your speech.. Sphinx has been around for at least 15 years in different forms. It has been, and probably always will be a system designed for IVR (interactive voice response, "speak or press one to get ignored by a customer service representative"). It is not and never will be a system for general-purpose speech recognition. The only useful speech recognition packages are NaturallySpeaking with a not very close runner-up of Windows speech recognition. Google speech recognition would be in the running if it wasn't bound to a very limited number of apps with no user accessible grammars. I'm currently experimenting with running Windows in a KVM virtual machine, running NaturallySpeaking there and find a way to see the output of NaturallySpeaking back to the Linux host OS. If I can get the audio stream clean enough, it looks like a promising technique for adding speech recognition to Linux Now all I need some help to figure out what I don't know about injecting keystrokes into linux and may be help with fixing up KVM so it passes audio cleanly under most conditions. -- To unsubscribe e-mail to: users+unsubscr...@global.libreoffice.org Problems? http://www.libreoffice.org/get-help/mailing-lists/how-to-unsubscribe/ Posting guidelines + more: http://wiki.documentfoundation.org/Netiquette List archive: http://listarchives.libreoffice.org/global/users/ All messages sent to this list will be publicly archived and cannot be deleted