An architecture for effective music information retrieval

We have explored methods for music information retrieval for polyphonic music stored in the MIDI format. These methods use a query, expressed as a series of notes that are intended to represent a melody or theme, to identify similar pieces. Our work has shown that a three-phase architecture is appropriate for this task in which the first phase is melody extraction, the second is standardization, and the third is query-to-melody matching. We have investigated and systematically compared algorithms for each of these phases. To ensure that our results are robust, we have applied methodologies that are derived from text information retrieval: We developed test collections and compared different ways of acquiring test queries and relevance judgments. In this article we review this program of work, compare it to other approaches to music information retrieval, and identify outstanding issues.

[1]  Brian Christopher Smith,et al.  Query by humming: musical information retrieval in an audio database , 1995, MULTIMEDIA '95.

[2]  Barry Vercoe,et al.  Music-listening systems , 2000 .

[3]  Ian H. Witten,et al.  Towards the digital music library: tune retrieval from acoustic input , 1996, DL '96.

[4]  Jorma Tarhio,et al.  Searching monophonic patterns within polyphonic sources , 2000 .

[5]  Jonathan Foote,et al.  ARTHUR: Retrieving Orchestral Music by Long-Term Structure , 2000, ISMIR.

[6]  S. Handel.  Listening As Introduction to the Perception of Auditory Events , 1989 .

[7]  Jonathan Foote,et al.  Visualizing music and audio using self-similarity , 1999, MULTIMEDIA '99.

[8]  Justin Zobel,et al.  Manipulation of music for melody matching , 1998, MULTIMEDIA '98.

[9]  Yosuke Takashima,et al.  Melody Retrieval with Humming , 1993, ICMC.

[10]  David Sankoff,et al.  Comparison of musical sequences , 1990, Comput. Humanit..

[11]  Justin Zobel,et al.  Music Ranking Techniques Evaluated , 2000, ISMIR.

[12]  David De Roure,et al.  A tool for content based navigation of music , 1998, MULTIMEDIA '98.

[13]  Adam Taro Lindsay,et al.  Using contour as a mid-level representation of melody , 1996 .

[14]  R. Francès.  La perception de la musique , 1958 .

[15]  Justin Zobel,et al.  Melodic matching techniques for large music databases , 1999, MULTIMEDIA '99.

[16]  Michael Clausen,et al.  PROMS: A Web-based Tool for Searching in Polyphonic Music , 2000, ISMIR.

[17]  Alan Marsden,et al.  Computer representations and models in music , 1992 .

[18]  J. Stephen Downie.  Access to Music Information: The State of the Art , 2005 .

[19]  Diana Deutsch,et al.  Grouping Mechanisms in Music , 1999 .

[20]  Jorma Tarhio,et al.  Detecting Monophonic Patterns within Polyphonic Sources , 2000, RIAO.

[21]  Donncha O Maidín.  A geometrical algorithm for melodic difference , 1998 .

[22]  Naoko Kosugi,et al.  Music retrieval by humming-using similarity retrieval over high dimensional feature vector space , 1999, 1999 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM 1999). Conference Proceedings (Cat. No.99CH36368).

[23]  W. Dowling.  Scale and contour: Two components of a theory of memory for melodies. , 1978 .

[24]  Yosuke Takashima,et al.  A Melody Retrieval Method with Hummed Melody , 1994 .

[25]  J. Stephen Downie,et al.  Evaluating a simple approach to music information retrieval : conceiving melodic n-grams as text , 1999 .