Efficient Detection of Co-Located Participant Devices in Teleconferencing Sessions

Audio data is captured by a participant computing device connected to a teleconferencing session using an audio capture device associated with the device. The audio data includes audio originating from an audio source co-located with the device. Subsequent to obtaining the audio data, second audio data is received that comprises second audio captured using a second audio capture devices associated with second participant computing devices connected to the teleconferencing session. Based on reception of the second audio data subsequent to capture of the audio data, a determination is made that some of the second audio originates from the audio source co-located with the device. Based on the determination, co-location information indicating that the device is co-located one or more of the second participant computing devices is generated.