With the growth in digital representations of music, and of music stored in these representations, it is increasingly attractive to search collections of music. One mode of search is by similarity, but, for music, similarity search presents several difficulties: in particular, deciding what part of the music is likely to be perceived as the theme by a listener, and deciding whether two pieces of music with different sequences of notes represent the same theme. In this paper we propose a three-stage framework for matching pieces of music. We use the framework to compare a range of techniques for determining whether two pieces of music are similar, by experimentally testing their ability to retrieve different transcriptions of the same piece of music from a large collection of MIDI files. These experiments show that different comparison techniques differ widely in their effectiveness; and

In 1975 Parsons developed his dictionary of musical themes based on a simple contour representation. The motivation was that people with little training in music would be able to identify pieces of music. We decided to test whether people of various levels of musical skill could indeed make use of a text representation to describe a simple melody query. The results indicate that the task is beyond those who are unmusical, and that a scale numeric representation is easier than a contour one for those of moderate musical skill. Further, a common error when using the scale representation still yields a more accurate contour representation than if a user is asked to enter a contour query. We observed an average query length of about seven symbols for the retrieval task.

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 standardisation, 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 judgements. In this paper we review this program of work, compare to other approaches to music information retrieval, and identify outstanding issues.