Musical note segmentation based on the double-threshold endpoint detection and fundamental frequency curve fluctuation measure
| Autor: | Chenchen Kong, Yibiao Yu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Dynamic time warping
business.industry Computer science Feature extraction Pattern recognition Musical note 02 engineering and technology Fundamental frequency 01 natural sciences Measure (mathematics) Feature (computer vision) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence Time series 010306 general physics business |
| Zdroj: | ICSAI |
| DOI: | 10.1109/icsai.2017.8248451 |
| Popis: | For the music retrieval using query-by-humming, the correct segmentation of the humming note is an important guarantee to extract the effective music melody feature information. In this paper, a two-level note segmentation method based on double-threshold endpoint detection and fundamental frequency curve fluctuation measure is proposed, then melody is extracted after segmentation, and the humming music retrieval system with the improved dynamic time warping algorithm is constructed. Experiment results show the segmentation correct ratio reaches 90%, the retrieval correct rate is improved by 5% and the retrieval time is reduced by 12.6% compared with the existing traditional humming music retrieval system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|