14
-or- how to search for (and maybe find) music and do away with incipits Michael Fingerhut Multimedia Library and Engineering Bureau IRCAM – Centre Pompidou IAML - IASA 2004 Congress, Oslo IRCAM - Institut de Recherche et Coordination Acoustique/Musique IAML- International Association of Music Libraries IASA – International association of sound archives Presented by: Shailesh Deshpande ([email protected]) 06/28/2009

Music Information Retrieval -or- how to search for (and maybe find) music and do away with incipits Michael Fingerhut Multimedia Library and Engineering

Embed Size (px)

Citation preview

Music Information Retrieval-or-

how to search for (and maybefind) music and do away with

incipitsMichael Fingerhut

Multimedia Library andEngineering Bureau

IRCAM – Centre PompidouIAML - IASA 2004 Congress, Oslo

IRCAM - Institut de Recherche et Coordination Acoustique/MusiqueIAML- International Association of Music LibrariesIASA – International association of sound archives

Presented by: Shailesh Deshpande ([email protected])

06/28/2009

Agenda

Introduction Why MIR? Take 1: multi-disciplinary domain Take 2: schematic Take 3: typology Challenges IRCAM cataloging tool

Introduction

Music information retrieval (MIR) is the interdisciplinary science of retrieving information from music

Paper presents three views of this domain Challenges What is an incipit?

First few words or opening line of a book. In music – first few notes of a composition.

Why MIR?

Storage => increased availability of musical content in digital form (locally) CD’s, DVD’s, iPods

Computing power => faster processing of large volumes of digitized content

Networks => increased availability of musical content in digital form (remotely) Pandora, Yahoo Music, iTunes

Technological advances + demand from consumers = attention of research and industry

Take 1: multi-disciplinary domain General

Computer Science, Data Processing, AI, Pattern Recognition, Library & Information Sciences

Philosophy and Psychology Sensory Perception, Emotions & feelings, Mental processes &

intelligence Social Sciences

Sociology & Anthropology, Culture & Institutions, Law, Commerce Natural Science & Mathematics General Technology

Electric, Electronic, Magnetic, Communications & Computer Engineering

The Arts Music, Aesthetics, Composition

Take 2: schematic representation of MIR

Take 3: a typology of MIR

PreprocessingOCR, digitization, compressionEncoding, notationFeature extractionSegmentationInstrument recognitionVoice recognition

IndexingIdentificationClusteringClassification

ExtractionMelody, Key, Harmony, Rhythm

Structural analysisPolyphonyRepetitionSimilaritySummarization

OrganizationDatabases, systems, networksCompressionSynchronizationMetadata

Search Objective criteria

Metadata indices (name, title, period, genre, instrumentation)Full-text (with or without semantic tags)Query by example (audio excerpt, melody, contour, rhythm, tonality, harmony)SimilarityAcoustical characteristics

Subjective criteriaMoodTaste

Retrieve, deliver, useBrowsing Playlists Using and reusing (annotate, combine, transform) Rights management (recognition, watermarking)

UsabilityEvaluation User studies

Music terms used in MIR

Pitch – perceived fundamental frequency of a sound. Maybe different from actual frequency because of harmonics.

Timbre – the quality of a musical note that distinguishes different types of sound production, such as voices or musical instruments (saxophone vs. trumpet – with same pitch and loudness)

Rhythm (aka beat) - the variation of the length and accentuation of a series of sounds

Tempo – the speed or pace of a musical piece. Usually affects the Mood of a song.

Melody – a linear succession of musical tones which is perceived as a single entity (‘horizontal’ aspect of music)

Harmony – simultaneous use of different pitches (‘vertical’ aspect of music)

Monophony – musical texture consisting of melody without accompanying harmony

Polyphony -  is a texture consisting of two or more independent melodic voices

Common Methods

Modeling: start from a theory, look for patterns Look for melodies, harmonic progressions Attempt to find elements in data that

correspond to such entities Statistical methods: look for patterns, build

a theory Perform statistical analysis on data, find

common patterns and group them in clusters Attempt to interpret their occurrence in

musical pieces

MIR Challenges

The integration of audiovisual, symbolic and textual data

Fingerprinting - unique small set of features excerpted from a sound file, allowing to discriminate it from any other sound file

Music Summarization- how to select a representative excerpt that gives a good idea of the work (similar to thumbnails for image files)

Computing Similarity – no unique way in which two pieces may be similar Melodic, Rhythmic, Timbre, Genre, Style similarities

Indexing a musical piece by melody – to allow QBH interface

MIR Challenges contd..

Encoding of music – at acoustic, structural and semantic levels

Query-by-example – search for music by singing, humming, whistling or playing an audio excerpt

Watermarking – adding identification information to digital audio for DRM

Benchmarking - limited number of standardized test collections available for evaluation of MIR systems

A tool to catalog and extract audioCD contents for online distribution Automatic identification of CDs

Compute CDDB of the CD CDDB - a binary number reflecting the offsets

(start time) and lengths of the tracks of the CD

Metadata retrieval and correction Query Internet CDDB for metadata Allow correction

Extraction and compression Transfer to a Web server

IRCAM tool interface

When a CD is inserted in the computer:

-The tool computes its CDDB

- Retrieves the metadata if available (freedb.org, cddb.com, allmusic.com)

- Allows the librarian to correct errors, structure the tracks into works and select names from authority lists.

- When done, it adds themetadata to the catalog, and extracts the tracks, compresses them and sendsthem to the audio server.

Information sources

The International Society for Music Information Retrieval (http://www.ismir.net/)

University of Illinois’ Graduate School of Library and Information Science (http://www.music-ir.org/)

IRCAM (http://www.ircam.fr/) http://articles.ircam.fr/textes/Fingerhut04b/

The Listen Game — UCSD Computer Audition Lab MIR music ranking game (Herd It on Facebook) Multi-player game where you listen to music with lots of

other people (aka the Herd). You are asked to describe the music (genre, mood, singer etc.) and get points when the Herd agrees with you.

Innovative way to harness the power of social networking and collect metadata for MIR