A comparison of melodic database retrieval techniques using sung queries

Abstract

Query-by-humming systems search a database of music for good matches to a sung, hummed, or whistled melody. Errors in transcription and variations in pitch and tempo can cause substantial mismatch between queries and targets. Thus, algorithms for measuring melodic similarity in query-byhumming systems should be robust. We compare several variations of search algorithms in an effort to improve search precision. In particular, we describe a new frame-based algorithm that significantly outperforms note-by-note algorithms in tests using sung queries and a database of MIDI-encoded music.

Melodic Similarity and Applications Using Biologically-Inspired Techniques

“…Alignment, despite being considered an ill-posed problem for strongly deviating versions of a musical piece [33], has proven to be very useful for identification or classification tasks where strong similarities are present [1,34] and high scoring alignment has been shown to correlate well with human judgements [35,36]. It has been used for cover song detection [37], pattern mining [38], extensively for query-by-humming [14,39] and in other MIR tasks. Interestingly, DTW has been extended to align items that cannot be naturally represented as single sequences, such as polyphonic music [40] or audio [41,42].…”

A system for automatically annotating traditional Irish music field recordings

“…To overcome transcription errors several applications use a pitch contour representation (up, down, or repeat) to give a representation of the direction of the pitch intervals [23, 22,21]. Many systems also use hummed or sung queries as input [22,24,25]. Hu & Dannenberg [24] compare a number of approaches to MIR and conclude that MIR systems must deal with many difficult problems, including robustness in the face of transcription errors, transposition invariance and tempo variance (rubatto).…”

Recent studies on music information processing

“…The use of such search keys raises some issues, however, such as how to deal with errors when singing off key and how to absorb differences in key and tempo. Specific methods differ in terms of the database used, which may consist of melodies only [1][2][3][4][5], standard MIDI files (SMF) of entire musical pieces [6][7][8], or audio signals of entire musical pieces [9,10]. If we use a melodyonly database, similarity with a search key can be directly computed, but for SMF, the track containing a melody must be identified before computing similarity.…”