Musical Instrument Recognition Using Their Distinctive Characteristics in Artificial Neural Networks
This work addresses instrument classification for audio processing applications, but it is incremental as it builds on existing methods with specific feature comparisons.
The study tackled musical instrument recognition by training an Artificial Neural Network on audio samples transformed to the frequency domain, comparing features like attack and initial frequency, and found that using the full data achieved 93.5% accuracy, while attack-only and initial 100 Hz resulted in 80.2% and 64.2% accuracy, respectively.
In this study an Artificial Neural Network was trained to classify musical instruments, using audio samples transformed to the frequency domain. Different features of the sound, in both time and frequency domain, were analyzed and compared in relation to how much information that could be derived from that limited data. The study concluded that in comparison with the base experiment, that had an accuracy of 93.5%, using the attack only resulted in 80.2% and the initial 100 Hz in 64.2%.