Multi-label Cross-lingual automatic music genre classification from lyrics with Sentence BERT
This provides a scalable solution for music information retrieval systems, particularly for underrepresented languages and cultural domains, though it is incremental in applying existing methods to a new task.
The paper tackled the problem of multi-label cross-lingual music genre classification from lyrics by using multilingual Sentence BERT embeddings, improving the genre-wise average F1-Score from 0.35 to 0.69 on a bilingual Portuguese-English dataset.
Music genres are shaped by both the stylistic features of songs and the cultural preferences of artists' audiences. Automatic classification of music genres using lyrics can be useful in several applications such as recommendation systems, playlist creation, and library organization. We present a multi-label, cross-lingual genre classification system based on multilingual sentence embeddings generated by sBERT. Using a bilingual Portuguese-English dataset with eight overlapping genres, we demonstrate the system's ability to train on lyrics in one language and predict genres in another. Our approach outperforms the baseline approach of translating lyrics and using a bag-of-words representation, improving the genrewise average F1-Score from 0.35 to 0.69. The classifier uses a one-vs-all architecture, enabling it to assign multiple genre labels to a single lyric. Experimental results reveal that dataset centralization notably improves cross-lingual performance. This approach offers a scalable solution for genre classification across underrepresented languages and cultural domains, advancing the capabilities of music information retrieval systems.