Abstract
With recent advances in the field of music informatics, approaches to audio-based music structural analysis have matured considerably, allowing researchers to reassess the challenges posed by the task, and reimagine potential applications. We review the latest breakthroughs on this topic and discuss the challenges that may arise when applying these techniques in real-world applications. Specifically, we argue that it could be beneficial for these systems to be application-dependent in order to increase their usability. Moreover, in certain scenarios, a user may wish to decide which version of a structure to use, calling for systems with multiple outputs, or where the output adapts in a user-dependent fashion. In reviewing the state of the art and discussing the current challenges on this timely topic, we highlight the subjectivity, ambiguity, and hierarchical nature of musical structure as essential factors to address in future work.
Highlights
The field of Music Informatics Research (MIR) has exper ienced significant advances in recent years, helped by more powerful machine learning techniques (Humphrey et al, 2012), greater computation (Dieleman et al, 2018), larger and richer datasets (Gemmeke et al, 2017), and increased interest in applications (Schedl et al, 2014; Murthy and Koolagudi, 2018)
One must rely on any music structure analysis metric with certain skepticism given the degree of subjectivity and ambiguity in this task and the perceptual preferences on different types of segmentations (Nieto et al, 2014)
2.6 Performance we discuss the state-of-the-art performances reported by MIR evaluation exchange (MIREX) during the years 2012 to 2017.15 This MIREX task is centered on flat segmentations exclusively, and we focus on this publicly available evaluation exchange due to the challenges that originate with independently reported results mostly due to operating on different versions of audio content and annotations
Summary
The field of Music Informatics Research (MIR) has exper ienced significant advances in recent years, helped by more powerful machine learning techniques (Humphrey et al, 2012), greater computation (Dieleman et al, 2018), larger and richer datasets (Gemmeke et al, 2017), and increased interest in applications (Schedl et al, 2014; Murthy and Koolagudi, 2018). 2. The Music Structure Analysis Problem Audio-based MSA aims to identify the contiguous, nonoverlapping musical segments that compose a given audio signal, and to label them according to their musical similarity. The Music Structure Analysis Problem Audio-based MSA aims to identify the contiguous, nonoverlapping musical segments that compose a given audio signal, and to label them according to their musical similarity These segments may be identified at different time scales: a short motive may only last a few seconds, while a large-scale section encompassing several long fragments may last longer than a minute. Boundaries of homogeneous segments may be straight forward to identify if sudden musical changes are present in the track to be analyzed These differences in terms of continuation of a given musical attribute might appear as blocks in the SSM. Homogeneous blocks can be hard to subdivide unless one makes use of recurrence sequences, as described
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Transactions of the International Society for Music Information Retrieval
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
