DROPS

Document

Audio Content-Based Music Retrieval

Authors: Peter Grosche, Meinard Müller, and Joan Serrà

Published in: Dagstuhl Follow-Ups, Volume 3, Multimodal Music Processing (2012)

Abstract

The rapidly growing corpus of digital audio material requires novel retrieval strategies for exploring large music collections. Traditional retrieval strategies rely on metadata that describe the actual audio content in words. In the case that such textual descriptions are not available, one requires content-based retrieval strategies which only utilize the raw audio material. In this contribution, we discuss content-based retrieval strategies that follow the query-by-example paradigm: given an audio query, the task is to retrieve all documents that are somehow similar or related to the query from a music collection. Such strategies can be loosely classified according to their "specificity", which refers to the degree of similarity between the query and the database documents. Here, high specificity refers to a strict notion of similarity, whereas low specificity to a rather vague one. Furthermore, we introduce a second classification principle based on "granularity", where one distinguishes between fragment-level and document-level retrieval. Using a classification scheme based on specificity and granularity, we identify various classes of retrieval scenarios, which comprise "audio identification", "audio matching", and "version identification". For these three important classes, we give an overview of representative state-of-the-art approaches, which also illustrate the sometimes subtle but crucial differences between the retrieval scenarios. Finally, we give an outlook on a user-oriented retrieval system, which combines the various retrieval strategies in a unified framework.

Cite as

Peter Grosche, Meinard Müller, and Joan Serrà. Audio Content-Based Music Retrieval. In Multimodal Music Processing. Dagstuhl Follow-Ups, Volume 3, pp. 157-174, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2012)

Copy BibTex To Clipboard

@InCollection{grosche_et_al:DFU.Vol3.11041.157,
  author =	{Grosche, Peter and M\"{u}ller, Meinard and Serr\`{a}, Joan},
  title =	{{Audio Content-Based Music Retrieval}},
  booktitle =	{Multimodal Music Processing},
  pages =	{157--174},
  series =	{Dagstuhl Follow-Ups},
  ISBN =	{978-3-939897-37-8},
  ISSN =	{1868-8977},
  year =	{2012},
  volume =	{3},
  editor =	{M\"{u}ller, Meinard and Goto, Masataka and Schedl, Markus},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DFU.Vol3.11041.157},
  URN =		{urn:nbn:de:0030-drops-34711},
  doi =		{10.4230/DFU.Vol3.11041.157},
  annote =	{Keywords: music retrieval, content-based, query-by-example, audio identification, audio matching, cover song identification}
}

Document

DOI: 10.4230/DagSemProc.09051.7

Towards Automated Processing of Folk Song Recordings

Authors: Meinard Müller, Peter Grosche, and Frans Wiering

Published in: Dagstuhl Seminar Proceedings, Volume 9051, Knowledge representation for intelligent music processing (2009)

Abstract

Folk music is closely related to the musical culture of a specific nation or region. Even though folk songs have been passed down mainly by oral tradition, most musicologists study the relation between folk songs on the basis of symbolic music descriptions, which are obtained by transcribing recorded tunes into a score-like representation. Due to the complexity of audio recordings, once having the transcriptions, the original recorded tunes are often no longer used in the actual folk song research even though they still may contain valuable information. In this paper, we present various techniques for making audio recordings more easily accessible for music researchers. In particular, we show how one can use synchronization techniques to automatically segment and annotate the recorded songs. The processed audio recordings can then be made accessible along with a symbolic transcript by means of suitable visualization, searching, and navigation interfaces to assist folk song researchers to conduct large scale investigations comprising the audio material.

Cite as

Meinard Müller, Peter Grosche, and Frans Wiering. Towards Automated Processing of Folk Song Recordings. In Knowledge representation for intelligent music processing. Dagstuhl Seminar Proceedings, Volume 9051, pp. 1-15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2009)

Copy BibTex To Clipboard

@InProceedings{muller_et_al:DagSemProc.09051.7,
  author =	{M\"{u}ller, Meinard and Grosche, Peter and Wiering, Frans},
  title =	{{Towards Automated Processing of Folk Song Recordings}},
  booktitle =	{Knowledge representation for intelligent music processing},
  pages =	{1--15},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{9051},
  editor =	{Eleanor Selfridge-Field and Frans Wiering and Geraint A. Wiggins},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.09051.7},
  URN =		{urn:nbn:de:0030-drops-19666},
  doi =		{10.4230/DagSemProc.09051.7},
  annote =	{Keywords: Folk songs, audio, segmentation, music synchronization, annotation, performance analysis}
}

Search Results

Documents authored by Grosche, Peter

Audio Content-Based Music Retrieval

Abstract

Cite as

Towards Automated Processing of Folk Song Recordings

Abstract

Cite as

Thanks for your feedback!

Could not send message