Query by humming: musical information retrieval in an audio database
Proceedings of the third ACM international conference on Multimedia
Melodic matching techniques for large music databases
MULTIMEDIA '99 Proceedings of the seventh ACM international conference on Multimedia (Part 1)
Evaluation of a simple and effective music information retrieval method
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Transposition invariant pattern matching for multi-track strings
Nordic Journal of Computing
Evaluating text-based similarity measures for musical content
WEDELMUSIC'02 Proceedings of the Second international conference on Web delivering of music
Hi-index | 0.00 |
The problem of musical query processing can be envisioned as a substring- matching problem when the melody is represented as a sequence of notes associated with a set of attributes. In comparison of two musical sequences, one of the important problems is to determine the weights of each operation. This paper presents an alternate weighting-scheme which is based on diatonic distinctions on melody perception. To achieve this, we run a cognitive experimentation applying Probe-Tone method. The results showed that perceptional hierarchy of pitches changes according to the interval distinction on melody, whether it has more disjunt interval than conjunct intervals, vice versa. Consequently, if the new weighting-scheme created in this study are used in sequenced- based melody comparison, melodies retrieved to user would have a more credible ranking. The details of experimentations and the results we reach are also presented in detail.