Tune Retrieval in the Multimedia Library

Abstract

Musical scores are traditionally retrieved by title, composer or subject classification. Just as multimedia computer systems increase the range of opportunities available for presenting musical information, so they also offer new ways of posing musically-oriented queries. This paper shows how scores can be retrieved from a database on the basis of a few notes sung or hummed into a microphone. The design of such a facility raises several interesting 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 and evaluate its performance.

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:…”

“…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.…”

“…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.…”

An overview of audio information retrieval

“…The Waikato system uses flexible string-matching algorithms to locate similar melodies located anywhere in a piece. Figure 5 (after McNab et al [50]) shows the recognized tune sung by the user on the top staff, and the retrieved musical tunes 15 . …”

Creating data resources for designing usercentric frontends for query-by-humming systems

“…Coarse melodic contour has been widely used and discussed in several QBH systems that followed. McNab et al [7,8] improved this framework by introducing the concept of a duration contour for rhythm representation. Blackburn et al [9], Roland et al [10], and Shih et al [11] extended McNab's system by using tree-based database searching.…”