Inter- Versus Intra-singer Similarity and Variation in Vocal Performances

An Interdisciplinary Review of Music Performance Analysis

“…Existing literature reviews on the topic of MPA have not been able to shed much light on this problem, in part because researchers frequently disagree on (or conflate) the various definitions of ' expressive,' or else findings appear inconsistent across the research, likely as a result of different methodologies, types of comparisons, or data. As noted by Devaney (2016), combining computational and listening experiments could lead to a better understanding of which aspects of variation are important to observe and model. Careful experimental design and/or meta-analyses across both MPA and cognition research, as well as cross-collaboration between MIR and music cognition researchers, may therefore prove fruitful endeavors for future research.…”

“…As stated by Devaney (2016), however, not all variation is expressive: "The challenge [...] is determining which deviations are intentional, which are due to random variation, and which are due to specific physical constraints that a given performer faces, such as bio-mechanical limitations [...]. In regard to physical limitations, these deviations may be both systematic and observable in collected performance data, but may not be perceptible to listeners."…”

Encoding music performance data in Humdrum and MEI

“…The annotated note events, with their associated timings, were used as time-frequency regions of importance [12] to estimate the following frame-wise continuous performance descriptors: fundamental frequency (f 0 ), power, spectral centroid, spectral flux, spectral slope, and spectral flatness. Summary descriptors were calculated from the continuous data, using the methods described in [13] to generate four pitch-related descriptors (perceived pitch, jitter, vibrato depth, and vibrato rate), two power-related descriptors (average power and shimmer), and four timbre-related descriptors (average spectral centroid, average spectral flux, average spectral slope, and average spectral flatness). The use of transcription as a proxy for score data in AMPACT facilitated the filtering of any bleed-through in the Unmix-isolated vocal tracks.…”