Separating audio from a single audio source via text based editing

Hi there, I shot an interview that needed a simple audio edit, after export, to bring one of the speakers up in volume. Trouble was, the audio layers were flattened, so I only had single track audio to work with. Yes the best way is to get the original files and boost the audio there, but that wasn't an option. So I looked at text based editing to help. I transcribed the audio, created the speakers, highlighted each segment where one of them spoke and copied them into another layer. Then I nested the audio to create two tracks and adjust the audio across the whole interview. 

My question is, would it be viable to have this be automated within premiere. Would it not be possible to click a button to have the speakers separated into two tracks from one? If it is possible, how could it be implemented and what would it look like?