What libraries are available for analyzing audio files for spoken keywords and / or speech in text?

Question

I'm a superhero after hours, and I'm trying to create an application that analyzes audio for spoken keywords. (Think of emergency calls / 911) If the keyword is "robbery" and this word is pronounced in the provided audio, I would like to mark this file and possibly translate it into text.

What development libraries or software applications exist for this kind of thing? C ++ or Java libraries are preferred, but not required.

Answer 1

The Wiki page here is a good starting point. Of the ones mentioned there, I think that CMU Sphinx is the most active.

Answer 2

You can work with Praat http://www.fon.hum.uva.nl/praat/ , it is an excellent program for working with phonetics, and it has its own scripting language. You can also find many scripts in the Praat community. You can also use sendpraat http://www.fon.hum.uva.nl/praat/sendpraat.html to work with praat functions as a subroutine.