Engaging with Mobile Music Retrieval

2015

Listeners have long been inspired to interact with music and create new representations of popular releases. Vinyl offered many opportunities to reappropriate chart music, from scratching and tempo manipulation to mixing multiple songs together. More recently, artists could engage their audience to interact with their music by offering mix-stems online for experimentation and sharing. With the extended processing power of mobile devices, the opportunities for interactive music are dramatically increasing.. This paper presents research that demonstrates a novel approach to interactive digital music. The research looks at the emergent format of the album app and extends existing paradigms of interactive music playback. The novel album app designed in this research presents a new opportunity for listeners to engage with recorded content by allowing them to explore alternative takes, renditions of a given song in multiple genres, and by allowing direct interaction with embedded mix-stem...

Journal of Intelligent Information System, 2013

Most Music Information Retrieval (MIR) researchers will agree that understanding users' needs and behaviors is critical for developing a good MIR system. The number of user studies in the MIR domain has been gradually increasing since the early 2000s, reflecting this growing appreciation of the need for empirical studies of users. However, despite the growing number of user studies and the wide recognition of their importance, it is unclear how great their impact has been in the field: on how systems are developed, how evaluation tasks are created, and how MIR system developers in particular understand critical concepts such as music similarity or music mood. In this paper, we present our analysis on the growth, publication and citation patterns, topics, and design of 198 user studies. This is followed by a discussion of a number of issues/challenges in conducting MIR user studies and distributing the research results.

IEICE Transactions on Information and Systems

This paper describes a public web service called Kiite Cafe that lets users get together virtually to listen to music. When users listen to music on Kiite Cafe, their experiences are enhanced by two architectures: (i) visualization of each user's reactions, and (ii) selection of songs from users' favorite songs. These architectures enable users to feel social connection with others and the joy of introducing others to their favorite songs as if they were together listening to music in person. In addition, the architectures provide three user experiences: (1) motivation to react to played songs, (2) the opportunity to listen to a diverse range of songs, and (3) the opportunity to contribute as a curator. By analyzing the behavior logs of 2,399 Kiite Cafe users over a year, we quantitatively show that these user experiences can generate various effects (e.g., users react to a more diverse range of songs on Kiite Cafe than when listening alone). We also discuss how our proposed architectures can enrich music listening experiences with others.

Proceedings of the 15th …, 2011

Currently available user interfaces for playlist generation allow creating playlists in various ways, within a spectrum from fully automatic to fully manual. However, it is not entirely clear how users interact with such systems in the field and whether different situations actually demand different interfaces. In this paper we describe Rush 2, a music interface for mobile touch-screen devices that incorporates three interaction modes with varying degrees of automation: Adding songs manually, in quick succession using the rush interaction technique or filling the playlist automatically. For all techniques various filters can be set. In a two-week diary study (with in-depth interaction logging) we gained insight into how people interact with music in their everyday lives and how much automation and interactivity are really necessary.

Popular Music and Society, 2015

Music streaming services encompass features that enable the organization of music into playlists. This article inquires how users describe and make sense of practices and experiences of creating, curating, maintaining, and using personal playlists. The analysis relies on a mixed-method study, including music-diary self-reports, online observations, and in-depth interviews with 12 heavy users of Spotify or/and WiMP Music. The findings suggest heterogeneous management of static and dynamic playlists based on structural and contextual schemes of aggregating music. User control motivates different playlist practices that demonstrate new ways of collecting music via streaming services but also derive from pre-digital collecting. Please contact me for the full version of the article!

Personalized and user-aware systems for retrieving multimedia items are becoming increasingly important as the amount of available multimedia data has been spiraling. A personalized system is one that incorporates information about the user into its data processing part (e.g., a particular user taste for a movie genre). A context-aware system, in contrast, takes into account dynamic aspects of the user context when processing the data (e.g., location and time where/when a user issues a query). Today's user-adaptive systems often incorporate both aspects. Particularly focusing on the music domain, this article gives an overview of different aspects we deem important to build personalized music retrieval systems. In this vein, we first give an overview of factors that influence the human perception of music. We then propose and discuss various requirements for a personalized, user-aware music retrieval system. Eventually, the state-of-the-art in building such systems is reviewed, ...

2015

Proceedings of International Conference on Multimedia Retrieval, 2014

The amount of music consumed while on the move has been spiraling during the past couple of years, which requests for intelligent music recommendation techniques. In this demo paper, we introduce a context-aware mobile music player named "Mobile Music Genius" (MMG), which seamlessly adapts the music playlist on the fly, according to the user context. It makes use of a comprehensive set of features derived from sensor data, spatiotemporal information, and user interaction to learn which kind of music a listeners prefers in which context. We describe the automatic creation and adaptation of playlists and present results of a study that investigates the capabilities of the gathered user context features to predict the listener's music preference.

PLOS ONE, 2020

Adults listen to music for an average of 18 hours a week (with some people reaching more than double that). With rapidly changing technology, music collections have become overwhelmingly digital ushering in changes in listening habits, especially when it comes to listening on personal devices. By using interactive visualizations, descriptive analysis and thematic analysis, this project aims to explore why people download and listen to music and which aspects of the music listening experience are prioritized when people talk about tracks on their device. Using a newly developed data collection method, Shuffled Play, 397 participants answered open-ended and closed research questions through a short online questionnaire after shuffling their music library and playing two pieces as prompts for reflections. The findings of this study highlight that when talking about tracks on their personal devices, people prioritise characterizing them using sound and musical features and associating them with the informational context around them (artist, album, and genre) over their emotional responses to them. The results also highlight that people listen to and download music because they like it-a straightforward but important observation that is sometimes glossed over in previous research. These findings have implications for future work in understanding music, its uses and its functions in peoples' everyday lives.

Marketing Science, 2009

This paper develops a music recommendation system that automates the downloading of songs into a mobile digital audio device. The system tailors the compositions of the songs to the preferences of individuals based on past behaviors. We describe and predict individual listening behaviors using a lognormal hazard function. Our recommendation system is the first to accomplish this and there is as of this moment no existing alternative. Our proposed approach provides an improvement over alternative methods that could be used for product recommendations. Our system has a number of distinct features. First, we use a Sequential Monte Carlo algorithm that enables the system to deal with massive historical datasets containing listening behavior of individuals. Second, we apply a variable selection procedure that helps to reduce the dimensionality of the problem, because in many applications the collection of songs needs to be described by a very large number of explanatory variables. Third, our system recommends a batch of products rather than a single product, taking into account the predicted utility and the uncertainty in the parameter estimates, and applying experimental design methods.