birm1h3                                                      mebec4                                                       ymggkl1

                  Bird Song Recognition Project

   ymggm2                                                      birm1h2                                                    mebec7

(click on any of the spectrum analyzer outputs above to hear the audio bird song each represent !)

The Bird Song Recognition project involves the development of a Java application designed to identify various bird song types that it has learned to recognize using a neural net backpropagation strategy. Learning occurs through the input of many samples of various song types. The application then analyzes additional bird songs to determine if it has learned the song type in the past, and notifies the end user if a match is found. If no match is found, the user is notified that the song type for the particular song is not yet known.

screen shot of Bird Song Recognizer

Algorithms

The project uses a stochastic gradient descent version of the backpropagation algorithm to update node weights until the defined songs are learned and can be recognized consistently. The general backpropagation layout can be found in figure 1, while the specific gradient descent algorithm used was from Mitchell, 1997.

figure 1






References


Churchland, Paul M., The Engine of Reason, the Seat of the Soul, MIT Press, 1995.

Kompe, Ralph, Prosody in Speech Understanding Systems, Springer-Verlag Berlin Heidelberg, 1997

McClelland, James L., Rumelhart, David E., Parallel Distributed Processing : Explorations in the Microstructure of Cognition, MIT Press, 1988.

Mitchell, Tom M., Machine Learning, McGraw-Hill Companies, Inc., 1997.