I have an audio file (u8, 128kbps) of the sounds produced while playing a game app and clips of its three distinct sounds.
The file consists of sequences of these, separated by silences, indicating next move (0.5 sec), correct move (0.5 sec, immediately followed by next move), and game over (5 sec).
I want to construct a data frame with a row for each move and columns containing game count, duration in seconds, and correct indicator.
Can someone suggest how I can approach this? I have a reasonably adept understanding of R. I looked at tuneR and more or less have a grasp on its functions.
chatGPT has been frustratingly useless.