Towards the digital music library

Abstract

Music is traditionally retrieved by title, composer or subject classification. It is possible, with current technology, to retrieve music from a database on the basis of a few notes sung or hummed into a microphone. This paper describes the implementation of such a system, and discusses several issues pertaining to music retrieval. We first describe an interface that transcribes acoustic input into standard music notation. We then analyze string matching requirements for ranked retrieval of music and present the results of an experiment which tests how accurately people sing well known melodies. The performance of several string matching criteria are analyzed using two folk song databases. Finally, we describe a prototype system which has been developed for retrieval of tunes from acoustic input.

Research and developments of a multi‐modal MIR engine for commercial applications in East Asia1

“…Some heuristics (such as end-point detection, pitch continuity check, and pitch range check) are also employed to eliminate unwanted/false pitch points which might result from either unvoiced segments of the acoustic input or undesirable effects of pitch doubling/halving. As opposed to some previous work (Ghias et al, 1995;McNab, Smith, Witten, Henderson, & Cunningham, 1996;McNab, Smith, Witten, & Henderson, 2000) reported in the literature, we do not perform note segmentation. The reasons are twofold:…”

“…McNab et al McNab, Smith, Witten, Henderson, & Cunningham, 1996;McNab, Smith, Witten, & Henderson, 2000), in collaboration with the New Zealand Digital Library, have published several papers on their experiments of query by singing. They applied Gold-Rabiner algorithm (Gold & Rabiner, 1969) for pitch tracking, and the pitch vector was then cut into notes based on energy levels and transition amounts.…”

“…As a common practice in the literature, the transformation is usually accomplished by using the difference operator on the extracted notes (Ghias et al, 1995;McNab, Smith, Witten, Henderson, & Cunningham, 1996;McNab, Smith, Witten, & Henderson, 2000). We have tried the difference operator on the pitch vector and found that the operator tends to amplify noises and deteriorate the system's performance.…”

Effective Results Ranking for Mobile Query by Singing/Humming Using a Hybrid Recommendation Mechanism

“…The similarities of the user string with strings in the library are used for retrieval. McNab et al [5] conducted further research where beats are used to improve the search accuracy. Systems that query by singing/humming use human voice as the input for the query.…”

“…The music class for which is maximized is called the maximum posteriori hypothesis. Using Bayes theorem (5) As is constant for all classes of music, only requires computation. The class prior probabilities can be estimated by (6) where is the number of samples of class in the users' search table and is the total number of samples in the users' search table.…”