I Am Sitting in a Room is a piece by composer Alvin Lucier. It consists of an audio recording of Lucier sitting in a room reciting a few lines. That recording is played in the same room and recorded. Then that recording is recorded. And so on.
I am sitting in a room different from the one you are in now. I am recording the sound of my speaking voice and I am going to play it back into the room again and again until the resonant frequencies of the room reinforce themselves so that any semblance of my speech, with perhaps the exception of rhythm, is destroyed. What you will hear, then, are the natural resonant frequencies of the room articulated by speech. I regard this activity not so much as a demonstration of a physical fact, but more as a way to smooth out any irregularities my speech might have.
Here's an mp3 of the original performance. Listening to it, I wonder how much of the distortion at the end is due to the "resonant frequencies of the room" and how much is just artifacts of the rerecording process. (via djacobs)
Upgrade: It's the Larsen effect in action.
The frequency of the resulting sound is determined by resonant frequencies in the microphone, amplifier, and loudspeaker, the acoustics of the room, the directional pick-up and emission patterns of the microphone and loudspeaker, and the distance between them.
(thx, eric)