Music processing
The goal is to make music, or information about music, easier to find. To support this goal, most MIR research has been focused on automatic music description and evaluation of the proposed methods.
The field is organized around use cases which define a type of query, the sense of match, and the form of the output. Queries and output can be textual information (metadata), music fragments, recordings, scores, or music features.
The match can be exact, retrieving music with specific content, or approximate, retrieving near neighbors in a musical space where proximity encodes musical similarity,
for example. The main components of an MIR system are detailed in Fig. 1. These are query formation, description extraction, matching and, finally, music document retrieval. The scope of an MIR system can be situated on a scale of specificity for which the query type and choice of exact or approximate matching define the characteristic specificity of the system. Those systems that identify exact content of individual recordings, for example, are called high-specificity systems; those employing broad descriptions of music, such as genre, have low specificity: that is, a search given a query track will return tracks having little content directly in common with the query, but with some global characteristics that match. Hence, we divide specificity into three broad categories: high-specificity systems match instances of audio signal content; mid-specificity systems match high-level music features, such as melody, but do not match audio content; and low-specificity systems match global (statistical) properties of the query. Table 1 enumerates some of the MIR use cases and their specificities (high, mid, or low).
A more comprehensive list of tasks and their specificities is given in.
