getting started with speech recognition and speech synthesis -
i want started speech recognition , speech synthesis in prototype based on speech recognition told me use microsoft speech server (sdk , on)
when have this, how programm application, , programming language (development enviroment?)?
has experience asterisk or svox?
i need do:
speech recognition speech synthesis
i doesn't have speech recognition - think 30 -50 words should enough beginning. i'm working windows.
thanks in advance
if choose use microsoft speech engine, there .net framework apis. mentioned in other post, there 2 namespaces (system.speech desktop use , microsoft.speech server use). can program in .net language , can use visual studio.
there article published few years ago @ http://msdn.microsoft.com/en-us/magazine/cc163663.aspx. best introductory article i’ve found far. however, based on prerelease version of winfx api , system.speech classes changed when vista released. samples in article not compile because of these breaking api changes , have not found updates or errata explain this. search internet method name “appendresultkeyvalue”, you’ll find few forum posts http://www.ms-news.net/f3012/system-speech-breaking-changes-3025734.html people ran same problem.
it still introductory article , worth reading. little bit of hacking, can sample app working.
Comments
Post a Comment