Cognition-based Segmentation for Music Information Retrieval Systems

Abstract

Background in computer science. This paper investigates the generic problem of model selection in the specific context of Music Information Retrieval (MIR). In MIR research, similarity measures are developed for ranking musical items with respect to their relevance to a user's musical query. The application of such similarity measures in MIR systems typically requires musical works to be divided into more manageable units. This involves two tasks: melody segmentation and voice separation. For both of these tasks, several solutions have been proposed in the symbolic domain. It seems reasonable to assume that those solutions that are most in accordance with human performance will result in the best ranking of retrieval output. As a first step towards this goal, this paper describes the evaluation of ten prominent methods against human performance. Background in cognition.Human listeners generally possess two functions that allow them to process a continuous stream of music into understandable units: the ability to perceive multiple, successive tones as one coherent melodic phrase (melody segmentation) and the ability to differentiate melody notes from harmony notes (voice separation). Algorithms for mimicking these human functions have been developed from two perspectives: model-driven, taking Gestalt principles as a starting-point; and data-driven, inferring rules by learning from large amounts of data. One method excepted, this research focuses on model-driven approaches.

Multi-scale Modelling of Segmentation

“…Compared to previous work, here the target stimuli were heard for the first time in the segmentation step, rather than during previous listening only conditions or practice trials. Another novel aspect, which aimed to illuminate the difference between intuitive and more conscious boundary indications, was to thoroughly compare how the examples were segmented by the same listeners in this task and in an annotation task that resembles previous data collection methodologies (Clarke & Krumhansl, 1990;Wiering et al, 2009). In addition, we expanded previous studies on musicianship by collecting spontaneous indications from musicians and nonmusicians using diverse stimuli.…”

“…Paulus, Müller, & Klapuri, 2010;Peeters & Deruty, 2009). Bruderer (2008), Wiering, de Nooijer, Volk, and Tabachneck-Schijf (2009), and Pearce et al (2010) have compared the performance of some segmentation systems. Other work on segmentation includes a neural study on finding working memory triggers (Burunat, Alluri, Toiviainen, Numminen, & Brattico, 2014) and a performance study on improvisational structure (Dean, Bailes, & Drummond, 2014).…”

Structural Segmentation of Music Based on Repeated Harmonies

“…Still, modelling musical parallelism for inferring segment boundaries remains a challenge [3]. For a survey and comparisons of symbolic segmentation approaches we refer to [10].…”

Hooked on Music Information Retrieval

“…Some examples include: using perceptual models (Krumhansl, 2001) to search for the musical key (Temperley, 2001, Ch. 7); improving harmonic similarity by performing automatic harmonic analyses (de Haas, Rohrmeier, Veltkamp, & Wiering, 2009) or by consulting Lerdahl"s (2001) Tonal Pitch Space (de Haas, Veltkamp, & Wiering, 2008; making F0 estimation easier with a filter model based on human pitch perception (Klapuri, 2005); using Gestalt principles for grouping musical units (Wiering, de Nooijer, Volk, & Tabachneck-Schijf, 2009); or retrieving melodies on the basis of the Implication/Realization model (Grachten, Arcos, & Lopez de Mantaras, 2004;Narmour, 1990), to name a few.…”