Music mood has been recognized as an important access point for music and many online music services support browsing by mood. However, how people judge music mood has not been well studied in the Music Information Retrieval (MIR) domain. In particular, people's cultural background is often assumed to be an important factor in music mood perception, but this assumption has not been verified by ...

In this paper we compare different methods to compute music similarity between songs. The presented approaches have been reported by other authors in the field and we implemented minor improvements of them. We evaluated the different methods on a common database of MP3 encoded songs covering different genres, albums and artists. We used the best approach of the evaluation in a P2P scenario to c...

UNLABELLED Exposure to music may be useful in the P300 retest and avoid habituation. AIM To verify the influence of the exposure to different kinds of music in P300 in young females. STUDY DESIGN Clinical prospective. MATERIAL AND METHOD Forty-five women aged from 20 to 36 years were evaluated. P300 was studied before and after musical stimulation with different rhythms. Brazilian songs, ...

The aim of the project was to develop a music mood classifier. There are many categories of mood into which songs may be classified, e.g. happy, sad, angry, brooding, calm, uplifting, etc. People listen to different kinds of music depending on their mood. The development of a framework for estimation of musical mood, robust to the tremendous variability of musical content across genres, artists...

We create a canonical encoding for multi-instrument MIDI songs into natural language, then use deep NLP techniques such as character LSTM variants to compose rock music that surpasses the prior state of the art and is competitive with certain pieces of music composed by human rock bands. We further define a neural network architecture for learning multi-instrument music generation in concert, b...

Music recommendation systems built on top of music information retrieval (MIR) technologies are usually designed to provide new ways to discover and listen to digital music collections. However, they do not typically assist in another important aspect of musical activity, music learning. In this study we present the application Hotttabs, an online music recommendation system dedicated to guitar...

Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks. We propose a generative adversarial model that works on continuous sequential data, and apply it by training it on a collection of classical music. We conclude that it generates music that sounds better and better as the model is trained, report statistics on generated music, and...

Hit songs, books, and movies are many times more successful than average, suggesting that "the best" alternatives are qualitatively different from "the rest"; yet experts routinely fail to predict which products will succeed. We investigated this paradox experimentally, by creating an artificial "music market" in which 14,341 participants downloaded previously unknown songs either with or witho...

Music emotion recognition today is based on techniques that require high quality and large emotionally labeled sets of songs to train algorithms. Manual and professional annotations of songs are costly and hardly accomplished. There is a high need for datasets that are public, highly polarized, large in size and following popular emotion representation models. In this paper we present the steps...

Typical content-based methods for music classification and retrieval mainly deal with global statistics or features of pre-divided songs. However, focusing on local, heterogeneous fragments and features is mandatory for flexible analysis. We propose a musical word scheme based on clustering as the base for local pattern extraction, robust classification and flexible music retrieval.