Finding Musical InformationReview: Basic Representations of Music & AudioReview: Basic & Specific Representations vs. EncodingsWays of Finding Music (1)Ways of Finding Music (2)Ways of Finding Music (3)Searching: Metadata (the old and new way) vs. Content (in the middle)Audio-to-Audio Music “Retrieval” (1)Audio-to-Audio Music “Retrieval” (2)A Similarity Spectrum for Content-Based Music IRSearching vs. BrowsingReview: How People Find InformationReview: How Computers Find InformationMusic IR as Music UnderstandingContent-based Retrieval Systems: Exact MatchContent-based Retrieval Systems: Best MatchLuck in Searching (1)Luck in Searching (2)Nightingale Search DialogNightingaleSearch: OverviewBach: “St. Anne” Fugue, with Search PatternIR Evaluation: Precision and Recall (1)Result Lists for Search of the “St. Anne” FuguePrecision and Recall with a Fugue SubjectIR Evaluation: Precision and Recall (2)Precision and Recall (3)What’s Wrong with NightingaleSearch?String vs. Geometric MatchingNightingaleSearch & Extra Notes (Problem 2)Nightingale and Independent Voices (Problem 2)2-D Pattern Matching in JMS and Extra Notes2-D Pattern Matching in JMS and Parallel VoicesRelevance, Queries, and Information NeedsPrecision and Recall (4)Foote: ARTHUROMRAS Audio-degraded Music IR Experiments (1)OMRAS Audio-degraded Music IR Experiments (2)OMRAS Audio-degraded Music IR Experiments (3)OMRAS Audio-degraded Music IR Experiments (4)Musical Ideas and “Relevance” (1)Musical Ideas and “Relevance” (2)Musical Ideas and “Relevance” (3)More on IR Evaluation: The Cranfield Model and TRECA Typical TREC Information Need and QueryTREC Relevance JudgmentsWhat if you don’t have relevance judgments?Music IR Evaluation: MIREX, etc.Data Quality in the Real WorldCase Study: OMRAS 1Case Study: OMRAS 2Music IR in the Real World 2: EfficiencyHofstadter on indexing (and “aboutness”) in textEfficiency in Simple Music SearchesExample: Indexing Monophonic MusicEfficiency in More Complex Music Searches (1)Efficiency in More Complex Music Searches (2)Downie’s View of Music IR: Facets 1Note Parameters (Review)Downie’s View of Music IR: Facets 2Downie’s View of Music IR: Other “Multi”sDownie’s View of Music IR: Types of SystemsIntellectual Property Rights (IPR) 1Intellectual Property Rights (IPR) 2Intellectual Property Rights (IPR) 3Building Symbolic Music CollectionsOMR at Its BestMusic Collections: Current and Prospective 1Music Collections: Current and Prospective 2Music Not Written in CMN by Dead European Men of the Last Few Centuries 1Music Not Written in CMN by Dead European Men of the Last Few Centuries 2Music Not Written in CMN by Dead European Men of the Last Few Centuries 31Finding Musical InformationDonald ByrdSchool of Informatics & Jacobs School of MusicIndiana University5 April 2008Copyright © 2006-08, Donald Byrd27 Jan.2Review: Basic Representations of Music & AudioAudio Time-stamped Events Music Notation Common examples CD, MP3 file Standard MIDI File Sheet musicUnit Sample Event Note, clef, lyric, etc.Explicit structure none little (partial voicing much (complete information) voicing information)Avg. rel. storage 2000 1 10Convert to left - easy OK job: easyConvert to right 1 note: pretty easy OK job: fairly hard - other: hard or very hard Ideal for music music music bird/animal sounds sound effects speechrev. 15 Feb.3Review: Basic & Specific Representations vs. EncodingsAudio Time-stamped Events Music NotationCMN Mensural not.Gamelan not.SMFCsound scoreNotelistMusicXMLFinaleETFexpMIDI FileTime-stamped MIDITime-stamped expMIDICsound scoreWaveformRed Book (CD)Tablature.WAVBasic and Specific Representations (above the line)Encodings (below the line)6 Mar. 064Ways of Finding Music (1)•How can you identify information/music you’re interested in?–You know some of it–You know something about it–“Someone else” knows something about your tastes–=> Content, Metadata, and “Collaboration”•Metadata–“Data about data”: information about a thing, not thing itself (or part)–Includes the standard library idea bibliographic information, plus information about structure of the content–Metadata is the traditional library way–Also basis for iTunes, etc.: iTunes Music Library.xml–Winamp, etc., use ID3 tags in MP3’s•Content (as in content-based retrieval)–The main thing we’ve talked about: cf. tasks in Music Similarity Scale•Collaborative–“People who bought this also bought…”8 Mar. 065Ways of Finding Music (2)•Do you just want to find the music now, or do you want to put in a “standing order”?•=> Searching and Filtering•Searching: data stays the same; information need changes•Filtering: information need stays the same; data changes–Closely related to recommender systems–Sometimes called “routing”•Collaborative approach to identifying music makes sense for filtering, but not for searching(?)6 Mar. 086Ways of Finding Music (3)•Most combinations of searching/filtering and the three ways of identifying desired music both make sense and seem useful•ExamplesSearching FilteringBy contentShazam, NightingaleSearch, ThemefinderFOAFing the Music, Pandora, Last.fmBy metadataiTunes, Amazon.com, Variations2, etc. etc.iTunes RSS feed generator, FOAFing the MusicCollaborativelyN/A(?) Amazon.com22 March 077Searching: Metadata (the old and new way) vs. Content (in the middle)•To librarians, “searching” means of metadata–Has been around as long as library catalogs (c. 300 B.C.?)•To IR experts, it means of content–Only since advent of IR: started with experiments in 1950’s•Ordinary people don’t distinguish–Expert estimate: 50% of real-life information needs involve both•The two approaches are slowly coming together–Exx: Variations2 with MusArt VocalSearch; FOAFing the Music–Metadata creating “games” (Van Ahn) promise to help a lot–Need ways to manage both together•Content-based was more relevant to this course in 2003•Now, both are important26 Mar. 078Audio-to-Audio Music “Retrieval” (1)•“Shazam - just hit 2580 on your mobile phone and identify music” (U.K. slogan in 2003)•Query (music & voices): •Match:•Query (7 simultaneous music streams!):–Includes Brahms & Ravel as well as pop•Avery Wang’s ISMIR 2003 paper•Example of audio fingerprinting•Uses combinatorial hashing•Other systems developed by Fraunenhofer, Phillips;