Existing research tools and vocabularies
From SOVARR Wiki
- The Music Ontology (MO) was created to solve a more general problem regarding interoperability between music related data sources. The music ontology is the core of a harmonised library of modular ontologies. See also Music Ontology at GitHub.
- The audio features ontology was created within the framework of the Music Ontology. It provides a model for describing acoustical and musicological data and allows for publishing content-derived information about audio recordings. Its aim is to provide a framework for communication. Therefore it is free from deep taxonomical organisation, and focuses on representational issues, including the data density of audio features (i.e. dense or sparse), and their temporal relation to audio signals (i.e. onset like events perceived as instantaneous, and segments with known duration, for instance, keys, chords and elements of musical structure). See also Audio Features Ontology at MO wiki, Audio Features Ontology at GitHub).
- The Chord Ontology is an ontology for describing chords (see also Chord Ontology at MO wiki, Chord Ontology at GitHub)
- The Keys Ontology is designed for describing keys (see also Keys Ontology at MO wiki, Keys Ontology at GitHub)
- The Symbolic Notation Ontology is designed for describing (western) musical notations (see also Symbolic Notation Ontology at MO wiki, Symbolic Notation Ontology at GitHub)
- The Instrument Taxonomy is a SKOS version of the Instrument Taxonomy developed by MusicBrainz (see als Instrument Taxonomy at MO wiki)
- The Media Format Ontology is for describing media types as sub classes of mo:Medium (i.e. on the "item level"; see also Media Type modelling at MO wiki)
- Media Types is a SKOS scheme for describing media types as sub classes of [purl.org/dc/terms/MediaType dcterms:MediaType] (or sub classes of dcterms:MediaType) on the "manifestation level" by using the property mo:media_type (see also Media Type modelling at MO wiki, Media Types at GitHub)
- The Similarity Ontology (MuSim) aims to describe the associations between musical items and is motivated by a variety of use cases. (see also MuSim at MO wiki)
- The Play Back Ontology is a specification provides basic concepts and properties for describing a concepts that are related to the play back domain, e.g. an playlist, play back counter and skip counter, on/ for the Semantic Web (see also Play Back Ontology at MO wiki, Play Back Ontology at GitHub)
- The Association Ontology is a specification provides basic concepts and properties for describing specific associations to something, e.g. an occasion, a genre or a mood, and enables furthermore, a mechanism to like/rate and feedback these associations in context to something on/ for the Semantic Web (see also Association Ontology at MO wiki, Association Ontology at GitHub)
- The Cognitive Characteristics Ontology can be utilized to describe e.g., music preferences or user profiles that include descriptions of e.g., related skills, expertises and interests (see also Cognitive Characteristics Ontology at MO wiki, Cognitive Characteristics Ontology at GitHub)
- The Recommendation Ontology can be utilized natural testosterone boosters to describe music recommendations in a simple or extended form (see also Recommendation Ontology at MO wiki, Recommendation Ontology at GitHub)
- The Info Service Ontology can be used to create web music information service descriptions e.g., of MusicBrainz that can be associated to resources that would be delivered by such an information service. Furthermore, such a description provides an entry point for information service quality descriptions. Information service description and information service quality descriptions can be provided by several agencies, so that an information consumer can select descriptions from preferred agencies. See also Info Service Ontology at MO wiki, Info Service Ontology at GitHub)
- The Vamp plugin ontology supports the use of Vamp audio feature extraction plugins within the context of semantic web data.
- The Segment Ontology framework is the backbone of an approach that models properties from the musicological domain independently from Music Information Retrieval (MIR) implementations and their signal processing foundations, whilst maintaining an accurate and complete description of the relationships linking them.
Feature extraction software
There are a number of existing software libraries and packages that offer sets of tools for audio feature extraction.