Endowing machines with sensing capabilities similar to those of humans is a prevalent
quest in engineering and computer science. In the pursuit of making computers sense their …

This paper surveys the state of the art in automatic emotion recognition in music. Music is
oftentimes referred to as a “language of emotion”[1], and it is natural for us to categorize …

The immense scale of the recent large language models (LLM) allows many interesting
properties, such as, instruction-and chain-of-thought-based fine-tuning, that has significantly …

Audio pattern recognition is an important research topic in the machine learning area, and
includes several tasks such as audio tagging, acoustic scene classification, music …

A common assumption in multimodal learning is the completeness of training data, ie, full
modalities are available in all training examples. Although there exists research endeavor in …

Self-supervised learning (SSL) has recently emerged as a promising paradigm for training
generalisable models on large-scale data in the fields of vision, text, and speech. Although …

Audio signal processing algorithms generally involves analysis of signal, extracting its
properties, predicting its behaviour, recognizing if any pattern is present in the signal, and …

Current deep-learning models are mostly built upon neural networks, ie multiple layers of
parameterized differentiable non-linear modules that can be trained by backpropagation. In …

The decomposition of a music audio signal into its vocal and backing track components is
analogous to image-to-image translation, where a mixed spectrogram is transformed into its …

We introduce the Free Music Archive (FMA), an open and easily accessible dataset suitable
for evaluating several tasks in MIR, a field concerned with browsing, searching, and …