An identification system of monophonic musical tones

The present paper describes the problem of defining a method recognizing musical tones in the context of automatic identification systems. This study had arisen from the demand to have a tool to detect a musical tone among available alternatives of a library of previously recorded musical tones produced by instruments of the same class
¹
. This work is based on a comparison criterion to measure the distance between the features of the actual tone and the reference database ones. The algorithm is realized in two distinct steps. At first, digital processing techniques are used with the purpose to obtain features pattern vectors from the waveforms. These resulting patterns are, subsequently, elaborated using the Least Squares Optimal Filtering. The algorithm is relatively simple and may be implemented efficiently with low latency on DSP processors.