Use Case Scenario: Composer Influence (Appropriation) Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set and data set preparation ...
Use Case Scenario: Find a (given) 'core' passage of music known to recur at least once in each of a collection of recordings of the Bach/Gounod 'Ave Maria'. Short ...
Use Case Scenario: Composer Classifier (Same Composer Different Work) Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set and ...
Use Case Scenario: Different Performer Same Work Classifier (cover song) Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set ...
Embedding Earth Mover's Distance in L1 metric space for LSH indexing Background " The low distortion embedding of EMD given in 1 pro vides a way to map weighted ...
Use Case Scenario: Folk Song Matching (Symbolic Audio Hybrid) Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set and data ...
AudioDB UNIX man Page Attached to this page. Generated using "help2man audioDB" Use man l audioDB.man1 to view MichaelCasey 18 Sep 2008 audioDB.man1: AudioDB ...
Use Case Scenario: Music Kernels Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set and data set preparation Ground Truth ...
Use Case Scenario: Near Duplicate Elimination Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set and data set preparation ...
Use Case Scenario: Near Neighbour Recommender Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set and data set preparation ...
Use Case Scenario: Performer Classifier (same as ADBSameArtistDifferentWork) Short Description Beneficiaries Task Description using fftExtract and AudioDB Data ...
Use Case Scenario: Performer Influence (Appropriation) Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set and data set preparation ...
Use Case Scenario: Same Performer Same Work (different recording) Classifier Short Description Beneficiaries Task Description using fftExtract and AudioDB Data ...
Use Case Scenario: Same Performer Different Work Classifier (Artist Identification) Short Description Beneficiaries Task Description using fftExtract and AudioDB ...
Use Case Scenario: Find similar/same passage(s) Short Description Given a user selection in a track, identify the same passage, or those which are very similar, elsewhere ...
Use Case Scenario: Identifying Themes and Variations Short Description Given a group of tracks representing a theme and a set of variations, using either the theme ...
Use Case Scenario: Near Duplicate Elimination Short Description Beneficiaries Task Description using fftExtract and AudioDB Data Set and data set preparation ...
A new tool for social networking Whilst ChallengingTheLongTail, the tool opens up new possibilities for social networking. If a social network develops around similar ...
Like many of these higher level tasks there are a number perspectives on how to solve this problem (and what exactly this problem is). Here are a couple examples ...
AudioDB What is AudioDB ? AudioDB is a feature vector database management system that is optimized for passage level retrieval from very large collections (1M tracks ...
AudioDB Bug Reporting This page is an attempt to log known issues and bugs in the current development (trunk) version of AudioDB. Please add to this page so that ...
AudioDB Developer Discussion Page This page is for current AudioDB development discussion: to let others know what you are working on to inform of recent ...
AudioDBGroup Member list: Set GROUP MichaelCasey, ChristopheRhodes, BenFields, MalcolmSlaney, IanKnopke, MichelaMagas, PolinaProutskova, TimCrawford, MickGrierson ...
development of functionality exposure of all non write functions over Web Services radius query type over SOAP. DONE matrix of possible queries Three major ...
Audio Features Ontology working document This Wiki page aims to capture some requirements for a more expressive version of the Audio features ontology. The current ...
The following mHashup user case scenarios have been compiled based on UserFeedback from SIGGRAPH 2008 and SORTED SOUNDS at the DANA CENTRE: New music discovery ...
Cepstral Coefficients are a set of coefficients that represent the cepstrum of a signal. Cepstrum is the result of taking the fournier transform of a signal's db ...
Challenging the 'Long Tail' When the concept of The Long Tail was published by Chris Anderson in October 2004 in Wired Magazine, it immediately hit a nerve. It addressed ...
Composers' test ground During SIGGRAPH 2008 several composers working with the film and advertising industries approached me in view of testing their compositions ...
Comments, suggestions, and questions brought up during the Sorted Sounds event at the Dana Centre Soundbite DJs want a more rhythm centric version, perhaps ...
Eliminating the generic 'World Music' classification One of the fruits of restrictive marketing tactics has been the creation of the misleading genre of 'World Music ...
Environmental sound analysis One of the potential uses of mHashup is to match different types of environmental sound. Research has already been conducted by Oliver ...
Common evaluation suite for search tools, etc. Evaluation at the higher levels, especially is closely related to use scenarios. We will need a way to know, for ...
Searching through film and video A movie scene can be detected via a piece of dialogue or a melody. Introducing a moving image library into the search may, therefore ...
'Find the riff' for musicians' practice A professional or amateur musician may be able to practice a particular technique by finding examples of that same technique ...
First Musings on Usage This is about usage of the working OMRAS2 system that is our goal, rather than about the individual components of the system. Users In principle ...
LSH Hashtable core format The doubly linked lists that represent the LSH hash tables have high overhead due to being heap allocated. Instead we are making a compressed ...
AUDIODB INDEXING AudioDB uses locality sensitive hashing to speed up queries. This is especially important for large databases ( 2000 tracks) The INDEX must reside ...
WP1 OMRAS2 System Infrastructure This topic discusses specification and development of the core OMRAS2 system infrastructure, such as how to support plugin tools ...
Some Interesting Sites This page is intended to provide a useful survey of what is currently being done in internet music as well as a list of resources that could ...
Preliminary Discussion leading to the January 31 meeting as this meeting will focus on WP1 InfrastructureDev these idea should focus there What should the primary ...
The Knowledge Machine framework has been developed in the Centre for Digital Music, QMUL, over the past few years. It aims to create a workspace for multimedia analysis ...
Language based versus graphical interfaces (Sorry this is not a use case but I didn't know where else to put it.) I just came across an essay ( http://www.acm ...
LARGE AUDIODB SUPPORT AudioDB now has the option to leave features on the filesystem Only works with INDEXING, assumes large number of tracks make brute ...
Why LARGE ADB ? Normally, AudioDB makes a database by copying feature files into a large table so that they can be accessed conveniently and efficiently at QUERY time ...
Leitmotif What is a leitmotif? Certain musical motives (short melodic/rhythmic/harmonic patterns) are very often used by composers as 'signposts' to the musical unfolding ...
Locality Sensitive Hashing for Low Level Feature Indexing Audio Fingerprinting systems use hashing to perform fast lookup of song signatures in large databases. However ...
mHashup mHashup is a dynamic user interface developed by Michela Magas for use with the AudioDB database management system. mHashup in the press mHashup ...
Managing large scale audio libraries Often large scale audio libraries contain duplicates, tagging errors and missing metadata. An instant feedback visual tool can ...
Matching Schubert to Shakespeare An easily recognizable melody from a Schubert aria is a good starting point to detect same or similar melodies in a large music library ...
New music discovery The majority of users at SIGGRAPH 2008 were interested in ways of finding new music. In order to test vast quantities of music files, an agreement ...
WP3 OMRAS2 Collaborators The user communities that will benefit from OMRAS2 and its applications Collaborators who will be joining in from the beginning Musicologists ...
WP4 OMRAS2 Evaluation This topic covers Unit, Functional and User Testing of OMRAS2 components, infrastructure, user interfaces and applications SIGGRAPH 2008 ...
DominiqueL 24 Jan 2007 A key part of both navigation and search is creating a solid, flexible, and organic taxonomy. A taxonomy acts as a backbone for both the search ...
OMRAS2 Summary Statement Imagine you've just been given a gift subscription to a 2 million song online music store. You can choose 10,000 songs to download onto your ...
Compatibility layer Here, we define some axioms to link the Music Ontology and the Music Production Ontology @prefix dc: . @prefix rdf: . @prefix rdfs: . @prefix ...
Ontology Examples This is a working document, trying to make the following efforts compatible: Music Ontology Music Production Ontology For these examples ...
@prefix dc: . @prefix mo: . @prefix foaf: . @prefix all: . # Description of the "Mass Nerder" album, from ALL all:all a mo:MusicGroup; foaf:name "ALL"; foaf ...
Open Issues Multityping for identifying format/medium/etc. djmixed and other "shortcut" properties Expressiveness of domain specific ontologies (key ...
OMRAS2 Research Workshops For OMRAS2 and Goldsmiths Digital Studios researchers. ResearchWorkshopTimeAndLocation Professor Michael Casey Syllabus Oct 9th Introduction ...
PRAAT: Phonetic Analysis Software http://www.fon.hum.uva.nl/praat/ (good for vocal performance) SPAN: Software for the Analysis of Music in Performance, for the Matlab ...
TWiki Contributor Not an actual user of this site, but a person devoting some of his/her time to contribute to the Open Source TWiki project. TWikiContributor lists ...