Dataset Information

Evaluating Hierarchical Structure in Music Annotations.

ABSTRACT: 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.

SUBMITTER: McFee B

PROVIDER: S-EPMC5541043 | biostudies-other | 2017

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:BackgroundIndividuals with Alzheimer disease or related dementia represent a significant and growing segment of the older adult (aged 65 years and above) population. In addition to physical health concerns, including comorbid medical conditions, these individuals often exhibit behavioral and psychological symptoms of dementia (BPSD). The presence of BPSD in long-term care residential facilities can disrupt resident's care and impact staff. Nonpharmacological interventions such as personalized music and tablet engagement maintain cognitive function, improve quality of life (QOL), and mitigate BPSD for older adults with dementia. Evidence of the impact of such interventions in assisted living communities (ALCs) is needed for widespread adoption and sustainment of these technologies.ObjectiveThe aim of this study was to assess the impact of Music & Memory's personalized music and tablet engagement (PMATE) program on QOL, agitation, and medication use for residents living in 6 Wisconsin ALCs.MethodsThe data collected were on the utilization of iPods and iPads by the residents. Residents' outcomes were assessed using the Pittsburgh Agitation Scale, the Quality of Life in Late Stage Dementia scale, and self-reported medication use. A mixed-methods approach was utilized to examine the impact of the PMATE program on these outcomes. Descriptive statistics were calculated. A paired t test explored changes in residents' QOL. A 1-way analysis of variance was utilized to examine changes in resident's agitation and QOL based on the resident's utilization of the PMATE program. Qualitative interviews were conducted with the individuals responsible for PMATE implementation in the ALC. Residents excluded from the analysis were those who passed away, were discharged, or refused to participate.ResultsA total of 5 apps, based on average times used by residents, were identified. In all, 4 of the 5 apps were rated as being useful to promote residents' engagement. PMATE utilization was not associated with changes in the residents' agitation levels or antipsychotic medication use over time. Over a 3-month period, the change in residents' QOL was significant (P=.047), and the differences across ALCs were also significant (F25=3.76, P=.02). High utilizers of the PMATE program (>2500 min over 3 months) showed greater improvements in QOL as compared with low utilizers (a change of -5.90 points vs an increase of 0.43 points). The difference was significant (P=.03). Similar significant findings were found between the high- and midutilizers.ConclusionsThe study is one of the first to explore the impact of Music & Memory's PMATE program on residents living in ALCs. Findings suggest that higher utilization over time improves residents' QOL. However, a more comprehensive study with improved data collection efforts across multiple ALCs is needed to confirm these preliminary findings.

Dataset Information

Evaluating Hierarchical Structure in Music Annotations.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets