Re: One question about speech2text poor performance

2008-01-16 Thread David Huggins-Daines
Marco Solari wrote: > Hi! > I have a question about the voice recognition problem on the Nokia platform, > hoping it's not too off-topic... > I see on this platform some voice recognition tool is available, but it's > extremely resource demanding, slow and performs with quite a low success > percen

Re: R: One question about speech2text poor performance

2008-01-16 Thread David Hagood
On Wed, 2008-01-16 at 17:07 +0200, Eero Tamminen wrote: > This list is for Nokia internet tablets and their Linux based maemo > software. Your question is about Nokia phones which run S40 and S60 > (Symbian OS) based software. Forum Nokia would probably be more > appropriate place to ask. I am

Re: One question about speech2text poor performance

2008-01-16 Thread David Huggins-Daines
David Huggins-Daines wrote: > Yes, this is exactly the case. Recognizing a limited set of names in > isolation is not at all computationally intensive compared to > recognizing full sentences of connected words. > > See: http://en.wikipedia.org/wiki/Dynamic_time_warping Also, Nokia has actually

Re: One question about speech2text poor performance

2008-01-16 Thread David Huggins-Daines
Marco Solari wrote: > The question is: is the task of recognizing a small set of utterances > basically different from the task of recognizing spoken words out of a > bigger dictionary (I limit the problem to single words, not considering the > spoken speech...) Yes, this is exactly the case. Reco

Re: R: One question about speech2text poor performance

2008-01-16 Thread Eero Tamminen
Tel.: +39115212596 > Fax.: +39114368715 > > http://www.koinesistemi.it/clausola-esonero-responsabilita > > -Messaggio originale- > Da: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] Per conto di David Hagood > Inviato: mercoledì 16 gennaio 2008 13.20 > A: maemo-

R: One question about speech2text poor performance

2008-01-16 Thread Marco Solari
lausola-esonero-responsabilita -Messaggio originale- Da: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Per conto di David Hagood Inviato: mercoledì 16 gennaio 2008 13.20 A: maemo-developers@maemo.org Oggetto: Re: One question about speech2text poor performance I'd ask this of the Nokia fol

Re: One question about speech2text poor performance

2008-01-16 Thread David Hagood
I'd ask this of the Nokia folks: what do you guys use in the cell phones? I'm sure it is a commercial package, but it would be interesting to know. ___ maemo-developers mailing list maemo-developers@maemo.org https://lists.maemo.org/mailman/listinfo/maem

Re: One question about speech2text poor performance

2008-01-15 Thread Scott Bambrough
Graham Cobb wrote: > On Tuesday 15 January 2008 19:01:11 Mike Klein wrote: > > Things may have improved in the last few years, but my guess is that until > there is a wikipedia-style project to allow people to contribute free speech > samples, there is unlikely to be very good open source spee

Re: One question about speech2text poor performance

2008-01-15 Thread Graham Cobb
On Tuesday 15 January 2008 19:01:11 Mike Klein wrote: > History lesson: 1Mhz Apple][ had >90% voice recognition > ability...program was written by Bill Budge I believe. > > The resources have to be there. Back in the days when I knew something (not much) about speech-rec the issue was not CPU pow

Re: One question about speech2text poor performance

2008-01-15 Thread Mike Klein
History lesson: 1Mhz Apple][ had >90% voice recognition ability...program was written by Bill Budge I believe. The resources have to be there. mike Marco Solari wrote: > Hi! > I have a question about the voice recognition problem on the Nokia platform, > hoping it's not too off-topic... > I se

One question about speech2text poor performance

2008-01-15 Thread Marco Solari
Hi! I have a question about the voice recognition problem on the Nokia platform, hoping it's not too off-topic... I see on this platform some voice recognition tool is available, but it's extremely resource demanding, slow and performs with quite a low success percentage... I'm asking myself how co