Speech(string) words from sentences

[louislouis]

hey guys,
I am currently working on a project that uses the speech(string) node. It works perfectly fine when i say single trigger words that are embedded in the word list (like “replay”). However, when I say a sentence that contains the trigger word, like “I want to replay the video”, it fails to recognize the trigger word.
As it is mainly a problem with the windows speek recognition, can you think of a possible alternative or maybe a workaround for that situation in vvvv?

i found an older post with a similar problem, but without a solution.

Help Request Dumbing Down the Speech Node

Hey Guys, I’m having some trouble with the Speech node. It makes use of the microsoft Speech recognition node. It works quite awesomely for the most part, but I’m having a problem. At the moment, it works well at responding to clear, seperate keywords. For example, I set the searched term as “fiber” and it responds well to when I clearly say fiber. Sometimes it even recognizes “fiber” when I put it into context, such as “we used a very special fiber in order to…”. The problem comes up if Micr…

Thank you
-Louis

[antokhio]

Well, as far as I know you can use azure speech recogniser but it takes quite an amount of time to send to a server and get a replay…
This is not implemented and can be implemented using VL…
Maybe there are more libs you can implement using VL, not sure anything out of the box will suite your needs

[sebescudie]

hei there,

this might help : Azure Speech Recognizer Demo

[louislouis]

thank you antokhio und sebescudie, that looks promising, will give it a try!