User-Driven Techniques for the Design and Evaluation of New Musical Interfaces

Abstract

The merits of user-driven design have long been acknowledged in the field of human–computer interaction (HCI): Closely involving target users throughout the lifecyle of a project can vastly improve their experiences with the final system. Thus, it comes as no surprise that a growing number of music technology researchers are beginning to incorporate user-driven techniques into their work, particularly as a means of evaluating their designs from the perspectives of their intended users. Many, however, have faced the limitations that arise from applying the task-based, quantitative techniques typically encountered in classical HCI research to the evaluation of nonutilitarian applications. The nature of musical performance requires that designers reevaluate their definitions of user “goals,” “tasks,” and “needs.” Furthermore, within the context of performance, the importance of creativity and enjoyment naturally supersedes that of efficiency, yet these concepts are more difficult to evaluate or quantify accurately. To address these challenges, this article contributes a set of key principles for the user-driven design and evaluation of novel interactive musical systems, along with a survey of evaluation techniques offered by new directions in HCI, ludology, interactive arts, and social-science research. Our goal is to help lay the foundation for designers of new musical interfaces to begin developing and customizing their own methodologies for measuring, in a concrete and systematic fashion, those critical aspects of the user experience that are often considered too nebulous for assessment.

Research on Music Content Recognition and Recommendation Technology Based on Deep Learning

“…With the development of information network, the amount of data is increasing geometrically, and the feature dimension of things is expanding rapidly. In the face of this situation, the traditional recommendation algorithm will inevitably be unable to meet the demand [20]. In the practical application of deep learning, no matter what structure is adopted, we cannot clearly set the specific parameters at the beginning, but we need to determine them according to the situation in the training of neural network, which is also an important part of deep learning.…”

Spatial Design Considerations for Interactive Audio in Virtual Reality

“…To establish a dialogue around spatial considerations, there is a need to adopt findings from other VR HCI disciplines. But as with the adoption of HCI evaluation frameworks within new interfaces for musical expression (NIME) [78,91,98], critical understanding of the target domain (SMC) needs to be established [70,81]. For instance, making expressive systems for musical creation or sonic experiences has different design requirements than usability engineering [42], or demonstrations of interaction techniques [8].…”

Adaptive music technology using the Kinect

“…Arguably, the most important aspect of a new musical instrument is its enjoyment by the performer. According to El-Shimy and Cooperstock (2016), "Typically, musicians and artists express a greater interest in the hedonic aspects of their experience with a system than they do in the system's efficiency or practicality. "…”