Music information analysis and retrieval techniques

2005

This survey paper provides an overview of content-based music information retrieval systems, both for audio and for symbolic music notation. Matching algorithms and indexing methods are briefly presented. The need for a TREC-like comparison of matching algorithms such as MIREX at ISMIR becomes clear from the high number of quite different methods which so far only have been used on different data collections. We placed the systems on a map showing the tasks and users for which they are suitable, and we find that existing content-based retrieval systems fail to cover a gap between the very general and the very specific retrieval tasks.

2006

Abstract Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of intelligent music information retrieval. Huron points out that since the preeminent functions of music are social and psychological, the most useful characterization would be based on four types of information: genre, emotion, style, and similarity.

Data analysis, machine learning and …, 2007

We present MIRToolbox, an integrated set of functions written in Matlab, dedicated to the extraction from audio files of musical features related, among others, to timbre, tonality, rhythm or form. The objective is to offer a state of the art of computational approaches in the area of Music Information Retrieval (MIR). The design is based on a modular framework: the different algorithms are decomposed into stages, formalized using a minimal set of elementary mechanisms, and integrating different variants proposed by alternative approaches -including new strategies we have developed -, that users can select and parametrize. These functions can adapt to a large area of objects as input.

2004 IEEE Symposium on Virtual Environments, Human-Computer Interfaces and Measurement Systems, 2004. (VCIMS).

Music is a particular case of audio media that has peculiar requirements for retrieval. Its representation, parallelism and multiple features are some examples of the challenges encountered. In this paper, these challenges are characterized and the techniques commonly used for classification, indexing and searching of music content are described. Whenever possible, comparisons are drawn with Text Information Retrieval.

2006

Two main groups of Music Information Retrieval (MIR) systems for content-based searching can be distinguished, systems for searching audio data and systems for searching notated music. There are also hybrid systems that first transcribe audio signal into a symbolic description of notes and then search a database of notated music. An example of such music transcription is the work of Klapuri , which in particular is concerned with multiple fundamental frequency estimation, and musical metre estimation, which has to do with ordering the rhythmic aspects of music. Part of the work is based on known properties of the human auditory system. Content-based music search systems can be useful for a variety of purposes and audiences:

National Conference on Communications, Bombay, …, 2002

This paper describes some early attempts at developing a music indexing and retrieval system based on melody, or tune, of songs. In the envisaged system, the "query", a song fragment whistled or sung by the user into a microphone, is used to search a database of soundtracks to find the entry that is best matched to it in tune. The challenging issues that this project raises are described. Signal processing tools suitable for melody detection are presented, and finally some experimentally obtained results are discussed.

Background in musicology. Most of the time the concept of melody is associated to a monophonic sequence of pitch notes. Also, identifying the main melody line in music, monophonic sequence of notes can be further deconstructed using the melody feature selection techniques in music information retrieval. Background in computer science. Some computational research in musical structure are concerned with building information retrieval systems, defining similarity measures, and otherwise finding occurrences and variations of a musical fragment within a collection of music documents. A very few of them includes extraction of melody, which is to extract and represent the melodic content of the music data. The purpose of a melody extraction technique is to identify sequences of notes that are likely to correspond to the perceived melody, given the volumes of music available online. It is not practicable to do this by hand. In terms of the needs of the user, a user may wish to query on a distinctive musical pattern that occurs in some parts.

2017

The performance of existing search engines for retrieval of images is facing challenges resulting in inappropriate noisy data rather than accurate information searched for. The reason for this being data retrieval methodology is mostly based on information in text form input by the user. In certain areas, human computation can give better results than machines. In the proposed work, two approaches are presented. In the first approach, Unassisted and Assisted Crowd Sourcing techniques are implemented to extract attributes for the classical music, by involving users (players) in the activity. In the second approach, signal processing is used to automatically extract relevant features from classical music. Mel Frequency Cepstral Coefficient (MFCC) is used for feature learning, which generates primary level features from the music audio input. To extract high-level features related to the target class and to enhance the primary level features, feature enhancement is done. During the lea...

International Symposium/Conference on Music Information Retrieval, 2000

The origins of music information retrieval (MIR) are in manual collections of incipits, short melodic fragments obtained from the beginning of pieces of music. The collections were manually compiled and usually covered a narrow field of music. Recently, computerized content- based MIR systems have appeared. They apply standard methods from general string matching. The applied techniques are based on the

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

Journal of the American Society for Information Science and Technology, 2004

As the dimension and number of digital music archives grow, the problem of storing and accessing multimedia data is no longer confined to the database area. Specific approaches for music information retrieval are necessary to establish a connection between textual and content-based metadata. This article addresses such issues with the intent of surveying our perspective on music information retrieval. In particular, we stress the use of symbolic information as a central element in a complex musical environment. Musical themes, harmonies, and styles are automatically extracted from electronic music scores and employed as access keys to data. The database schema is extended to handle audio recordings. A score/audio matching module provides a temporal relationship between a music performance and the score played. Besides standard free-text search capabilities, three levels of retrieval strategies are employed. Moreover, the introduction of a hierarchy of input modalities assures meeting the needs and matching the expertise of a wide group of users. Singing, playing, and notating melodic excerpts is combined with more advanced musicological queries, such as querying by a sequence of chords. Finally, we present some experimental results and our future research directions.

1997

This paper describes a system designed to retrieve melodies from a database on the basis of a few notes sung into a microphone. The system first accepts acoustic input from the user, transcribes it into common music notation, then searches a database of 9400 folk tunes for those containing the sung pattern, or patterns similar to the sung pattern; retrieval is ranked according to the closeness of the match. The paper presents an analysis of the performance of the system using different search criteria involving melodic contour, musical intervals and rhythm; tests were carried out using both exact and approximate string matching. Approximate matching used a dynamic programming algorithm designed for comparing musical sequences. Current work focuses on developing a faster algorithm.

Multimodal Music Processing (Schloss Dagstuhl, Germany, 2012), M. Müller and M. Goto, Eds., vol. Seminar, 2012

The emerging field of Music Information Retrieval (MIR) has been influenced by neighboring domains in signal processing and machine learning, including automatic speech recognition, image processing and text information retrieval. In this contribution, we start with concrete examples for methodology transfer between speech and music processing, oriented on the building blocks of pattern recognition: preprocessing, feature extraction, and classification/decoding. We then assume a higher level viewpoint when describing sources of mutual inspiration derived from text and image information retrieval. We conclude that dealing with the peculiarities of music in MIR research has contributed to advancing the state-of-the-art in other fields, and that many future challenges in MIR are strikingly similar to those that other research areas have been facing.

Journal of the Association for Information Science and Technology, 2004

We have explored methods for music information retrieval for polyphonic music stored in the MIDI format. These methods use a query, expressed as a series of notes that are intended to represent a melody or theme, to identify similar pieces. Our work has shown that a three-phase architecture is appropriate for this task, in which the first phase is melody extraction, the second is standardisation, and the third is query-to-melody matching. We have investigated and systematically compared algorithms for each of these phases. To ensure that our results are robust, we have applied methodologies that are derived from text information retrieval: we developed test collections and compared different ways of acquiring test queries and relevance judgements. In this paper we review this program of work, compare to other approaches to music information retrieval, and identify outstanding issues.