From West to East: Who can understand the music of the others better?
This addresses the bias in music information retrieval models toward Western music, offering insights for cross-cultural applications, though it is incremental as it applies existing transfer learning methods to new data.
The study investigated whether deep learning models trained on Western music can effectively represent non-Western music cultures, using transfer learning across datasets from Western, Eastern Mediterranean, and Indian art music. Results showed competitive auto-tagging performance in all domains via transfer learning, with the best source dataset varying by culture.
Recent developments in MIR have led to several benchmark deep learning models whose embeddings can be used for a variety of downstream tasks. At the same time, the vast majority of these models have been trained on Western pop/rock music and related styles. This leads to research questions on whether these models can be used to learn representations for different music cultures and styles, or whether we can build similar music audio embedding models trained on data from different cultures or styles. To that end, we leverage transfer learning methods to derive insights about the similarities between the different music cultures to which the data belongs to. We use two Western music datasets, two traditional/folk datasets coming from eastern Mediterranean cultures, and two datasets belonging to Indian art music. Three deep audio embedding models are trained and transferred across domains, including two CNN-based and a Transformer-based architecture, to perform auto-tagging for each target domain dataset. Experimental results show that competitive performance is achieved in all domains via transfer learning, while the best source dataset varies for each music culture. The implementation and the trained models are both provided in a public repository.