Music Corpora Research Articles

Mining Characteristic Patterns for Comparative Music Corpus Analysis

A core issue of computational pattern mining is the identification of interesting patterns. When mining music corpora organized into classes of songs, patterns may be of interest because they are characteristic, describing prevalent properties of classes, or because they are discriminant, capturing distinctive properties of classes. Existing work in computational music corpus analysis has focused on discovering discriminant patterns. This paper studies characteristic patterns, investigating the behavior of different pattern interestingness measures in balancing coverage and discriminability of classes in top k pattern mining and in individual top ranked patterns. Characteristic pattern mining is applied to the collection of Native American music by Frances Densmore, and the discovered patterns are shown to be supported by Densmore’s own analyses.

Steven MacGregor Demorest (1959-2019)

Steven Demorest, as both a scholar and a singer, had a voice that was strong and resonant. Steve’s passion for singing grew as an undergraduate in the Luther College choirs under the inspiring direction of Weston Noble, as a graduate student at Westminster Choir College, and through his doctoral work at the University of Wisconsin, where he encountered the choral artistry of Robert Fountain. His value for and pursuit of rigorous research and musical accomplishment—pairing the two while maintaining the integrity of each—characterized his contribution to the fields of choral music, music education, and music psychology. Rather than viewing musical excellence as exclusive, Steve saw musical achievement as something everyone could and should experience. He also believed that those responsible for guiding such experiences should be skilled as musicians and as teachers. Through a career that began at the University of North Texas, then at the University of Washington, and finally at Northwestern University, Steve worked tirelessly to bring about the best in music-making …

Machine learning of symbolic compositional rules with genetic programming: dissonance treatment in Palestrina.

We describe a method for automatically extracting symbolic compositional rules from music corpora. Resulting rules are expressed by a combination of logic and numeric relations, and they can therefore be studied by humans. These rules can also be used for algorithmic composition, where they can be combined with each other and with manually programmed rules. We chose genetic programming (GP) as our machine learning technique, because it is capable of learning formulas consisting of both logic and numeric relations. GP was never used for this purpose to our knowledge. We therefore investigate a well understood case in this study: dissonance treatment in Palestrina's music. We label dissonances with a custom algorithm, automatically cluster melodic fragments with labelled dissonances into different dissonance categories (passing tone, suspension etc.) with the DBSCAN algorithm, and then learn rules describing the dissonance treatment of each category with GP. Learning is based on the requirement that rules must be broad enough to cover positive examples, but narrow enough to exclude negative examples. Dissonances from a given category are used as positive examples, while dissonances from other categories, melodic fragments without dissonances, purely random melodic fragments, and slight random transformations of positive examples, are used as negative examples.

Identification and Description of Outliers in the Densmore Collection of Native American Music

This paper presents a method for outlier detection in structured music corpora. Given a music collection organised into groups of songs, the method discovers contrast patterns which are significantly infrequent in a group. Discovered patterns identify and describe outlier songs exhibiting unusual properties in the context of their group. Applied to the collection of Native American music collated by Frances Densmore (1867–1957) during fieldwork among several North American tribes, and employing Densmore’s music content descriptors, the proposed method successfully discovers a concise set of patterns and outliers, many of which correspond closely to observations about tribal repertoires and songs presented by Densmore.

Evaluating Hierarchical Structure in Music Annotations.

Music exhibits structure at multiple scales, ranging from motifs to large-scale functional components. When inferring the structure of a piece, different listeners may attend to different temporal scales, which can result in disagreements when they describe the same piece. In the field of music informatics research (MIR), it is common to use corpora annotated with structural boundaries at different levels. By quantifying disagreements between multiple annotators, previous research has yielded several insights relevant to the study of music cognition. First, annotators tend to agree when structural boundaries are ambiguous. Second, this ambiguity seems to depend on musical features, time scale, and genre. Furthermore, it is possible to tune current annotation evaluation metrics to better align with these perceptual differences. However, previous work has not directly analyzed the effects of hierarchical structure because the existing methods for comparing structural annotations are designed for “flat” descriptions, and do not readily generalize to hierarchical annotations. In this paper, we extend and generalize previous work on the evaluation of hierarchical descriptions of musical structure. We derive an evaluation metric which can compare hierarchical annotations holistically across multiple levels. sing this metric, we investigate inter-annotator agreement on the multilevel annotations of two different music corpora, investigate the influence of acoustic properties on hierarchical annotations, and evaluate existing hierarchical segmentation algorithms against the distribution of inter-annotator agreement.

Improved Methods for Statistical Modelling of Monophonic Music

N-Gram based models have been used for a variety of musical tasks including computer-assisted composition, machine improvisation, music information retrieval, stylistic analysis and cognitive modelling. We present an application-independent evaluation of some recent techniques for improving the performance of a subclass of n-gram models on a range of monophonic music data. We have applied these techniques incrementally to eight melodic datasets using cross entropy computed by 10-fold cross-validation on each dataset as our performance metric. The results demonstrate that significant and consistent improvements in performance are afforded by several of the evaluated techniques. We discuss the results in terms of previous research carried out in the field of data compression and with natural language and music corpora and conclude by presenting some important directions for future research.