I know its a general question topic, but still i want to know whats the fastest speech recognition library in C++?
Currently I am using Microsoft SAPI with kniect. It works fine and recognizes words but its abit slow, some times it takes 1,2 seconds to recognize a word and in my case this lag is causing alot of interaction issues for the user.
I checked the sample provided with the kinect, in which the turtle moves left right according to words recognized but even thats a bit slow.
So I was wondering if there is any faster library then sapi, that can be used in cases like a robot using voice recognition you say "left" then "right" but robot keeps moving left and turns right after 1,2 seconds its a bit frustrating for the user.
The issue is not being fast, but proper way to use the API. Speech recognition is a time-consuming process so the main trick is to start recognition of the audio as soon as it's recorded, in parallel with the recording. Then to the moment phrase end is spoken you will have almost all the results and can react immediately.
The response time of 0.2 seconds can be achieved this way, but you need more flexible API to implement this. A good choice is CMUSphinx, an open source speech recognition framework which you can use for your implementation