LumenVox has created an easy to use and flexible Speech Recognition API. This document will guide a developer on how to use the API to develop speech recognition-enabled applications.
For convenience, a C language API (LV_SRE) and a C++ class API (class LVSpeechPort) are provided.
This is general outline for using either API in a single port application on a single audio file. If more than one audio sample needs to be processed, loop on steps 3 and 4, including step 2 only if each sample needs a different grammar:
Initialize a speech port.
Load a standard grammar, or create a custom grammar in a voice channel.
Acquire audio data (this is the responibility of the client application) and load the audio data into the same voice channel as step 2.
Decode the audio data and process the results.
Close the speech port.
Complete Help Topic List | Speech Engine Product Information