Aldebaran documentation What's new in NAOqi 2.4.3?

ALSoundDetection

NAOqi Audio - Overview | API


What it does

The ALSoundDetection module detects significative sounds in incoming audio buffers. This detection is based on the audio signal level and as such behaves similarly on any type of sound (provided it is loud enough).

How it works

The processing is made on the front microphone signal. The raw signal is first smoothed by calculating the signal mean on a moving window.

A peak based detection is then applied on this averaged signal to provide the user (through ALMemory in SoundDetected) with the index of the detected sound start.

The end of that sound is eventually detected when the level of the averaged signal comes back to its original value (before the peak detection).

The SoundDetected key shows from 1 to n sounds detected in the last audio buffer:

[[index_1, type_1, confidence_1, time_1],
 ...,
[index_n, type_n, confidence_n, time_n]]

Where:

  • index is the indexes of starting and ending points of a detected sound.
  • type contains 1 for starting point and 0 for ending point.
  • confidence gives an estimate of the probability [0;1] that the sound detected by the module corresponds to a real sound.
  • time is the detection time in micro seconds.

Getting started

Using Choregraphe, the SoundDetected key can be retrieved and used (like any others) as a stimulating input to any other box by right clicking on diagrams left border: Add input from ALMemory.