I have no experience with it, but Azure has a speech recognition service via an API.
http://datamarket.azure.com/dataset/bing/speechrecognition One implementation of it is the "Speech Recognition Control" which is a small app that installs on Windows and lets Windows developers use it for native Windows apps. http://datamarket.azure.com/dataset/bing/speechcontrol I also assume that this is the speech engine that Cortana uses in Windows10, and that Skype uses for it's real-time speech translation services, in which case, Microsoft will be investing heavily in making it work well. http://www.skype.com/en/translator-preview/ In my experience, the biggest factor in accurate translation is quality of the source audio. Calls from cell phones don't translate well, while HD audio is nearly 100%. John On Thu, Sep 17, 2015 at 9:23 AM, Leif Madsen <[email protected]> wrote: > I did some research in this area a while ago, and came up with these three > service providers. It might not be exactly what you're looking for, but > might fill some niches. > > > - Clarify (http://clarify.io/) > - VoiceBase (http://www.voicebase.com/public/) > - VoiceCloud (http://www.voicecloud.com/) > > > On 24 July 2015 at 13:44, Jim Van Meggelen <[email protected]> > wrote: > > > Thanks Lloyd, that's really interesting. I've reached out to them to see > > what they're up to these days. > > > > Jim > > > > > > On Fri, Jul 24, 2015 at 11:18 AM, Lloyd Aloysius < > [email protected] > > > > > wrote: > > > > > The following was recorded on year 2013 ClueCon conference(FreeSWITCH) > > > > > > https://www.youtube.com/watch?v=viJxyyDaJoA > > > > > > Waterloo based company - http://www.vestec.com/ > > > > > > Lloyd > > > > > > On Fri, Jul 24, 2015 at 10:49 AM, Nabeel Jafferali <[email protected]> > > > wrote: > > > > > > > This was posted to the asterisk-biz list a few weeks ago: > > > > > > > > http://www.speechaas.com/#/home > > > > > > > > -- > > > > Nabeel Jafferali > > > > > > > > On Fri, Jul 24, 2015 at 9:05 AM, Jim Van Meggelen < > > > > [email protected] > > > > > wrote: > > > > > > > > > Here is an example of something that looks interesting: > > > > > > > > > > > > > > > > > > > > > > > > > http://www.nuance.com/for-business/customer-service-solutions/hosted-contact-center-solutions/index.htm > > > > > > > > > > > > > > > > > > > > On Fri, Jul 24, 2015 at 8:53 AM, Jim Van Meggelen < > > > > > [email protected] > > > > > > wrote: > > > > > > > > > > > I'm curious about people's experience with speech recognition > > > > > development. > > > > > > > > > > > > For myself, I'd like to be able to use an external service of > some > > > sort > > > > > > (similar to google's API), supply it a grammar (i.e. list of > names > > > > from a > > > > > > voicemail directory), and have it be supported by a company who > > has a > > > > > good > > > > > > knowledge of speech recognition (i.e. their recognition engine is > > > > robust > > > > > > and gives reliable results). > > > > > > > > > > > > I would so love to use google's speech API, but it's not really > > > > > > production-ready, as google doesn't support it for commercial use > > > > > (there's > > > > > > a quota and you can't supply custom grammar so far as I've been > > able > > > to > > > > > > tell). Still, it's an excellent engine in so many ways. > > > > > > > > > > > > There's always been Sphinx, but I have never had the impression > > this > > > > has > > > > > > gone far beyond the academic, and from what I've seen it's not > > > > something > > > > > to > > > > > > be taken on lightly. > > > > > > > > > > > > Then there are the commercial products, but I really can't figure > > out > > > > how > > > > > > to choose amongst them. > > > > > > > > > > > > Anybody had any good experiences they'd be willing to share? > > > > > > > > > > > > > > > > > > Jim > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > -- > Leif Madsen. > http://www.leifmadsen.com > http://www.oreilly.com/catalog/asterisk > -- John Lange www.johnlange.ca
