This paper introduces effective design choices for text-to-music retrieval systems. An ideal
text-based retrieval system would support various input queries such as pre-defined tags …

There is a limited amount of large-scale public datasets that contain downloadable music
audio files and rich lead singer metadata. To provide such a dataset to benefit research in …

Supervised machine learning for music information retrieval requires a large annotated
training set, and is thus an expensive and time-consuming process. To circumvent this …

We introduce a framework that recommends music based on the emotions of speech. In
content creation and daily life, speech contains information about human emotions, which …

Contrastive learning constitutes an emerging branch of self-supervised learning that
leverages large amounts of unlabeled data, by learning a latent space, where pairs of …

In this paper, we study whether music source separation can be used as a pre-training
strategy for music representation learning, targeted at music classification tasks. To this end …

Cloned voices of popular singers sound increasingly realistic and have gained popularity
over the past few years. They however pose a threat to the industry due to personality rights …

Singing voice is one of the most essential elements of music. It provides impactful emotional
expressions through melody and lyrics and has the potential to move people's hearts and …