Is there a way to mark the point in an audio file where a certain word occurs?

I would like to be able to find a place in an audio file in which a word occurs.

So far I've discovered that I would need to use the Speech Framework. The SFSpeechAudioBufferRecognitionRequest has two append methods -- append(AVAudioPCMBuffer) and appendAudioSampleBuffer(CMSampleBuffer). I would need to use one of those two buffer types. Is this something that can be done with Apple technology? Anyone have done this before.