| dc.description.abstract | Sri Lanka has a rich history of music, with a wide
variety of traditional instruments. However, a significant
challenge in Sri Lankan music is the lack of software capable
of identifying which traditional instruments are played in a
song. This paper presents a novel approach to address the gap
in instrument classification by a standard traditional deep
learning approach, using a flute, a pitched instrument, and
gataberaya, an unpitched indigenous drum, using 249
manually recorded audio samples. These instruments play a
crucial role in folk and ceremonial music. The classification
model was trained on 168 flute and 81 gataberaya raw audio
files which were in varying lengths and were single noted.
These audio files were turned into Mel-spectrograms to train
the Convolutional Neural Network model featuring two
convolutional layers. This included class imbalance handling
and data augmentation methods for both raw audio and Mel
spectrograms, which increased the dataset size to 5,632 before
the model training process. The raw audio data augmentation
techniques used were noise addition and time stretch.
Frequency masking and time masking were added for Mel
spectrograms. The model achieved a training accuracy of
98.17%, a validation accuracy of 99.26%, and a testing
accuracy of 99.63%, showing reliability and consistency. This
approach provides a valuable tool for improving music
education and potentially preserves cultural heritage by
facilitating easier identification and analysis of Indigenous
music. | en_US |
