Adding descriptors to melodies improves pattern matching: a study on Slovenian folk songs (original) (raw)

Pattern Based Melody Matching Approach to Music Information Retrieval

Transactions on Machine Learning and Artificial Intelligence, 2018

Digitization of music and advancements in information technology for sharing information on World Wide Web paved way for its availability in enormous quantities anywhere any time. Rather than retrieving annotated music in response to query given in terms of Metadata such as name of the composer/singer, genre etc modern researchers are challenged towards content based music information retrieval systems (CBMIR). CBMIR systems differ while representing the main melody either as a note sequence or as an analog acoustic signal; the note sequence representation is explored in this research work. Based on the observation that repeating patterns of the note sequences representing the main melody capture the essence of the music object, this research work developed a framework to investigate the feasibility and effectiveness of pattern based melody matching approach to music information retrieval. Experimentation is conducted on a real world dataset of musical objects belonging to South Indian classical music and the performance of the framework is estimated in terms of Mean Reciprocal Ranking.

Textual and Musical Invariants for Searching and Classification of Traditional Music

Springer Cham, 2019

The goal of this research is to determine whether such properties as tonality, mode, meter and tune title remain similar between different versions of the same melody. A variability in some features makes classifying and searching tasks more difficult. The author uses a corpus of traditional dance melodies on audio recordings from Macedonia (Greece), as a base for analysis. We show that, in general, none of the features-meter, mode, key and tune title-are invariable on their own, for all versions of a selected tune. At the same time, using linguistic features where the musical ones fail, and vice versa, helps to improve the chances of a correct attribution and an efficient search. It is possible now to use the examples of invariance violations to assess possible search systems for a corpus of musical works.

A symbolic dataset of Turkish makam music phrases

One of the basic needs for computational studies of traditional music is the availability of free datasets. This study presents a large machine-readable dataset of Turkish makam music scores segmented into phrases by experts of this music. The segmentation facilitates computational research on melodic similarity between phrases, and relation between melodic phrasing and meter, rarely studied topics due to unavailability of data resources.

Optimizing Measures Of Melodic Similarity For The Exploration Of A Large Folk Song Database

2004

This investigation aims at finding an optimal way of measuring the similarity of melodies. The applicability for an automated analysis and classification was tested on a folk song collection from Luxembourg that had been thoroughly analysed by an expert ethnomusicologist. Firstly a systematization of the currently available approaches to similarity measurements of melodies was done. About 50 similarity measures were implemented which differ in the way of transforming musical data and in the computational algorithms. Three listener experiments were conducted to compare the performance of the different measures to human experts' ratings. Then an optimized model was obtained by using linear regression, which combines the output of several measures representing different musical dimensions. The performance of this optimized measure was compared with the classification work of a human ethnomusicologist on a collection of 577 Luxembourg folksongs.

Melodic matching techniques for large music databases

Proceedings of the seventh ACM international conference on Multimedia (Part 1) - MULTIMEDIA '99, 1999

With the growth in digital representations of music, and of music stored in these representations, it is increasingly attractive to search collections of music. One mode of search is by similarity, but, for music, similarity search presents several difficulties: in particular, for melodic query support, deciding what part of the music is likely to be perceived as the theme by a listener, and deciding whether two pieces of music with different sequences of notes represent the same theme. In this paper we propose a three-stage framework for matching pieces of music. We use the framework to compare a range of techniques for determining whether two pieces of music are similar, by experimentally testing their ability to retrieve different transcriptions of the same piece of music from a large collection of MIDI files. These experiments show that different comparison techniques differ widely in their effectiveness; and that, by instantiating the framework with appropriate music manipulation and comparison techniques, pieces of music that match a query can be identified in a large collection.

Melodic grouping in music information retrieval: New methods and applications

Advances in Music Information …, 2010

We introduce the MIR task of segmenting melodies into phrases, summarise the musicological and psychological background to the task and review existing computational methods before presenting a new model, IDyOM, for melodic segmentation based on statistical learning and information-dynamic analysis. The performance of the model is compared to several existing algorithms in predicting the annotated phrase boundaries in a large corpus of folk music. The results indicate that four algorithms produce acceptable results: one of these is the IDyOM model which performs much better than naive statistical models and approaches the performance of the best-performing rule-based models. Further slight performance improvement can be obtained by combining the output of the four algorithms in a hybrid model, although the performance of this model is moderate at best, leaving a great deal of room for improvement on this task.

Tree-structured representation of melodies for comparison and retrieval

2002

The success of the Internet has filled the net with lots of symbolic representations of music works. Two kinds of problems arise to the user: the search for information from content and the identification of similar works. Both belong to the pattern recognition domain. In contrast to most of the existing approaches, we pose a non-linear representation of a melody, based on trees that express the metric and rhythm of music in a natural way. This representation provide a number of advantages: more musical significance, more compact representation and others. Here we have worked on the comparison of melodies and patterns, leading to motive extraction and its use for the identification of complete melodies.

Mining Melodic Patterns in Large Audio Collections of Indian Art Music

2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems, 2014

Discovery of repeating structures in music is fundamental to its analysis, understanding and interpretation. We present a data-driven approach for the discovery of shorttime melodic patterns in large collections of Indian art music. The approach first discovers melodic patterns within an audio recording and subsequently searches for their repetitions in the entire music collection. We compute similarity between melodic patterns using dynamic time warping (DTW). Furthermore, we investigate four different variants of the DTW cost function for rank refinement of the obtained results. The music collection used in this study comprises 1,764 audio recordings with a total duration of 365 hours. Over 13 trillion DTW distance computations are done for the entire dataset. Due to the computational complexity of the task, different lower bounding and early abandoning techniques are applied during DTW distance computation. An evaluation based on expert feedback on a subset of the dataset shows that the discovered melodic patterns are musically relevant. Several musically interesting relationships are discovered, yielding further scope for establishing novel similarity measures based on melodic patterns. The discovered melodic patterns can further be used in challenging computational tasks such as automatic rāga recognition, composition identification and music recommendation

Mining transposed motifs in music

Journal of Intelligent Information Systems, 2011

The discovery of frequent musical patterns (motifs) is a relevant problem in musicology. This paper introduces an unsupervised algorithm to address this problem in symbolically-represented musical melodies. Our algorithm is able to identify transposed patterns including exact matchings, i.e., null transpositions. We have tested our algorithm on a corpus of songs and the results suggest that our approach is promising, specially when dealing with songs that include non-exact repetitions.

Calculating similarity of folk song variants with melody-based features

Proceedings of ISMIR 2009, 2009

As folk songs live largely through oral transmission, there usually is no standard form of a song - each performance of a folk song may be unique. Different interpretations of the same song are called song variants, all variants of a song belong to the same variant type. In the paper, we explore how various melody-based features relate to folk song variants. Specifically, we explore whether we can derive a melodic similarity measure that would correlate to variant types in the sense that it would measure songs belonging to the same variant type as more similar, in contrast to songs from different variant types. The measure would be useful for folk song retrieval based on variant types, classification of unknown tunes, as well as a measure of similarity between variant types. We experimented with a number of melodic features calculated from symbolic representations of folk song melodies and combined them into a melodybased folk song similarity measure. We evaluated the measure on the task of classifying an unknown melody into a set of existing variant types. We show that the proposed measure gives the correct variant type in the top 10 list for 68% of queries in our data set.