Content-based organization and visualization of music archives

Pampalk, Elias; Rauber, Andreas; Merkl, Dieter

doi:10.1145/641007.641121

Cited by 193 publications

(86 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The literature on using geo-visualizations to understand music collections has focused on personal libraries (Leitich & Topf, 2007;Torrens, Hertzog, & Arcos, 2004) or commercial applications (Pampalk, Rauber, & Merkl, 2002). The literature on data visualizations for use in cultural heritage institutions has been less saturated, though it is growing in recent years.…”

Section: Geo-visualizations and Digital Librariesmentioning

confidence: 99%

Connecting Music and Place: Exploring Library Collection Data Using Geo-visualizations

Doi

2017

EBLIP

View full text Add to dashboard Cite

Objectives -This project had two stated objectives: 1) to compare the location and concentration of Saskatchewan-based large ensembles (bands, orchestras, choirs) within the province, with the intention to draw conclusions about the history of community-based musical activity within the province; and 2) to enable location-based browsing of Saskatchewan music materials through an interactive search interface.Methods -Data was harvested from MARC metadata found in the library catalogue for a special collection of Saskatchewan music at the University of Saskatchewan. Microsoft Excel and OpenRefine were used to screen, clean, and enhance the dataset. Data was imported into ArcGIS software, where it was plotted using a geo-visualization showing location and concentrations of musical activity by large ensembles within the province. The geo-visualization also allows users to filter results based on the ensemble type (band, orchestra, or choir).Results -The geo-visualization shows that albums from large community ensembles appear across the province, in cities and towns of all sizes. The ensembles are concentrated in the southern portion of the province and there is a correlation between population density and ensemble location. Choral ensembles are more prevalent than bands and orchestras, and appear more widely across the province, whereas bands and orchestras are concentrated around larger centres.Evidence Based Library and Information Practice 2017, 12.2 37 Conclusions -Library catalogue data contains unique information for research based on special collections, though additional cleaning is needed. Using geospatial visualizations to navigate collections allows for more intuitive searching by location, and allow users to compare facets. While not appropriate for all kinds of searching, maps are useful for browsing and for locationbased searches. Information is displayed in a visual way that allows users to explore and connect with other platforms for more information.

show abstract

Section: Geo-visualizations and Digital Librariesmentioning

confidence: 99%

Connecting Music and Place: Exploring Library Collection Data Using Geo-visualizations

Doi

2017

EBLIP

View full text Add to dashboard Cite

show abstract

“…It can be computed by the frequency domain or Mel-bands. The estimation of pitch is usually based on spectrum and auto-correlation [10]. Computing the cross-correlation of its pitch class distribution, with the distribution we can associate to each possible tonality can estimate the tonality of a musical piece.…”

Section: Musical Feature Extractionmentioning

confidence: 99%

Analysis of FLAC Music Pieces Recovery

Jin¹,

Kim²

2014

JACN

View full text Add to dashboard Cite

Abstract-In this paper, we propose a method of recovering the music piece of FLAC file downloaded by BitTorrent. It was decoded the split FLAC file via getting the complete frames from piece of FLAC file and adding the temporary header to decode. The percentage of successfully decoding is all above 90%. From the partial audio signal we extract the musical feature and calculate the cross-correlation with the features in database. The feature in database is extract from the complete music file. The Musical feature is detected by chromagram to get the key strength. The percentage of audio identification is growing tendency with the increase of piece size. It experiment shows probability of identify audio with getting the part of FLAC file distributed by BitTorrent.

show abstract

“…Models of the human auditory system are frequently included in such derived features. High-level features usually aim at capturing either timbral aspects of music, which are commonly modeled via MFCCs [2], or rhythmic aspects, for example described via beat histograms [75] or fluctuation patterns [63,56]. Recent work addresses more specific high-level concepts, such as melodiousness and aggressiveness [57,52].…”

Section: Examplesmentioning

confidence: 99%

“…A fairly popular visualization and browsing technique employs the "Islands of Music" [53,50] metaphor, which uses Self-Organizing Maps (SOM) [28], i.e., a non-linear, topology-preserving transform of a highdimensional feature space to usually two dimensions. There exist also various extensions to the basic "Island of Music" approach.…”

Section: Categorizing Music Retrieval Systemsmentioning

confidence: 99%

Personalization in Multimodal Music Retrieval

Schedl

Knees

2013

Adaptive Multimedia Retrieval. Large-Scale Multimedia Retrieval and Evaluation

View full text Add to dashboard Cite

Abstract. This position paper provides an overview of current research endeavors and existing solutions in multimodal music retrieval, where the term "multimodal" relates to two aspects. The first one is taking into account the music context of a piece of music or an artist, while the second aspect tackled is that of the user context. The music context is introduced as all information important to the music, albeit not directly extractable from the audio signal (such as editorial or collaboratively assembled meta-data, lyrics in textual form, cultural background of an artists, or images of album covers). The user context, in contrast, is defined by various external factors that influence how a listener perceives music. It is therefore strongly related to user modeling and personalization, both facets of music information research that have not gained large attention by the MIR community so far. However, we are confident that adding personalization aspects to existing music retrieval systems (such as playlist generators, recommender systems, or visual browsers) is key to the future of MIR. In this vein, this contribution aims at defining the foundation for future research directions and applications related to multimodal music information systems.

show abstract

Content-based organization and visualization of music archives

Cited by 193 publications

References 24 publications

Connecting Music and Place: Exploring Library Collection Data Using Geo-visualizations

Connecting Music and Place: Exploring Library Collection Data Using Geo-visualizations

Analysis of FLAC Music Pieces Recovery

Personalization in Multimodal Music Retrieval

Contact Info

Product

Resources

About