Computational Creativity is a multidisciplinary field that tries to obtain creative behaviors from computers. One of its most prolific subfields is that of Music Generation (also called Algorithmic Composition or Musical Metacreation), that uses computational means to compose music. Due to the multidisciplinary nature of this research field, it is sometimes hard to define precise goals and to keep track of what problems can be considered solved by state-of-the-art systems and what instead needs further developments. With this survey, we try to give a complete introduction to those who wish to explore Computational Creativity and Music Generation. To do so, we first give a picture of the research on the definition and the evaluation of creativity, both human and computational, needed to understand how computational means can be used to obtain creative behaviors and its importance within Artificial Intelligence studies. We then review the state of the art of Music Generation Systems, by citing example for all the main approaches to music generation, and by listing the open challenges that were identified by previous reviews on the subject. For each of these challenges, we cite works that have proposed solutions, describing what still needs to be done and some possible directions for further research.

The importance of recommender systems has grown in recent years, as these systems are becoming one of the primary ways in which we access content on the Internet. Along with their use, concerns about the fairness of the recommendations they propose have rightfully risen. Recommender systems are known to be affected by popularity bias, the disproportionate preference towards popular items. While this bias stems from human tendencies, algorithms used in recommender systems can amplify it, resulting in unfair treatment of end-users and/or content creators. This article proposes a narrative review of the relevant literature to characterize and understand this phenomenon, both in human and algorithmic terms. The analysis of the literature highlighted the main themes and underscored the need for a multi-disciplinary approach that examines the interplay between human cognition, algorithms, and socio-economic factors. In particular, the article discusses how the overall fairness of recommender systems is impacted by popularity bias. We then describe the approaches that have been used to mitigate the harmful effects of this bias and discuss their effectiveness in addressing the issue, finding that some of the current approaches fail to face the problem in its entirety. Finally, we identify some open problems and research opportunities to help the advancement of research in the fairness of recommender systems.

In music, the interpreter manipulates the performance parameters in order to offer a sonic rendition of the piece that is capable of conveying specific expressive intentions. Since the 1980s, there has been growing interest in expressive music performance (EMP) and its computational modeling. This research field has two fundamental objectives: understanding the phenomenon of human musical interpretation and the automatic generation of expressive performances. Rule-based, statistical, machine, and deep learning approaches have been proposed, most of them devoted to the classical repertoire, in particular to piano pieces. On the contrary, we introduce the role of expressive performance within popular music and the contemporary ecology of pop music production based on the use of digital audio workstations (DAWs) and virtual instruments. After an analysis of the tools related to expressiveness commonly available to modern producers, we propose a detailed survey of research into the computational EMP field, highlighting the potential and limits of what is present in the literature with respect to the context of popular music, which by its nature cannot be completely superimposed to the classical one. In the concluding discussion, we suggest possible lines of future research in the field of computational expressiveness applied to pop music.

Making music with others is both an artistic act and a social activity. Music therapists can leverage the social aspects of music to increase the well-being of their patients by interacting with them musically, improvising rhythms and melodies together on shared musical instruments. This activity requires highly trained professionals and is therefore expensive for the clients. We propose a serious game that can help people without musical training interact by collaboratively creating a rhythm using MIDI drum pads. The gaming system analyzes the rhythm in real-time and adds musical feedback that is synchronized to what the users play, enhancing the aesthetical experience that is crucial to the musical interaction and its therapeutic effects. We assessed our system through quantitative metrics showing its capability of following a user-established tempo. Test players also completed a questionnaire, which showed they found the experience pleasant and engaging, and that the musical augmentation was helpful to their interaction.

Despite recent notable advances of AI-Education research, formal music education is still largely performed as it was at the beginning of the last century. Instrument technical practice especially is still largely performed in a classical setting with little use of modern technologies, possibly due to being a skill-based curriculum. While other researchers have argued for the potential benefits of using Artificial Intelligence for the personalization of music education, it still seems to be rare both in schools and in research. In this paper, we present a systematic literature review exploring the use of computational generation of exercises for personalized music learning, with a special interest in piano. To do so, we retrieve research papers that use AI to improve personalization in music education exploring both what computational methods can provide personalization in music teaching, and how frequently AI is actually used for generation in this context. We screened 360 papers retrieved from online repositories, selecting 40 relevant papers that would satisfy some minimal quality requirements. Analyzing the papers, we found that while there is interest from the scientific community in improving music education through AI and computational means more generally, AI is under-utilized for generation despite its potential for personalization. We found no examples of generation of piano technical exercises, and, more generally, that instrumental technique is indeed the aspect that has seen lesser use of AI enhancement, often limited to adding visualizations to normal instrumental practice.