2003 · 23 citations · 7 references
HumanitiesData ScienceMusic AnalysisGenre TaxonomyInstrument ClassificationMusic AcousticsMusic Information RetrievalMusic TechnologyMusical GenresAudio Music AnalysisMusic ClassificationMusic Feature ExtractionMusic Genre IndexingMusic Pattern DiscoveryMusic Similarity ModelingMusical OntologyMusical Pattern Recognition
Musical audio-mining technology allows users to search and retrieve music by means of content-based text and audio queries. Though these systems are promising, there is a need for a better understanding of the role of user preferences and user profiles. The development of taxonomies for different aspects of a musical audio-mining system aims at bridging the gap between system development and user interactive interfacing. In the first part of this paper, the need for user-dependent taxonomy development is addressed and an experiment in spontaneous user behavior is described, based on 72 users and 1148 vocal queries. Statistical analysis provides insight into the characteristics of vocal querying and possible useful concepts. In the second part of the paper, it is described how categories and concepts from the statistical analysis have been used for the refinement of taxonomies that address user interactive interfacing and feature extraction.
7
J. Stephen Downie · Annual Review of Information Science and Technology · 2003 · 376 citations
The New Zealand Digital Library MELody inDEX
Rodger J. McNab, Lloyd A. Smith, David Bainbridge et al. · D-Lib Magazine · 1997 · 133 citations · Full text
Cubyhum: A Fully Operational "Query By Humming" System.
Steffen Pauws · 2002 · 92 citations · Full text