Affiliation:
1. 1 Dance College , Chengdu Vocational University of the Arts , Chengdu , Sichuan , , China .
Abstract
Abstract
In this paper, we first use CNNS to collect rich samples of folk dance music, establish a model framework and a functional system framework, and conduct a comprehensive process analysis of the music. Then, the instrumental features, frequency features, and timbre features are extracted to obtain the spectral information. In the stage of chord analysis and encoding, a multivariate chord encoding model is established based on the acquired spectral information, including two parts: chord representation preprocessing and chord encoding. By utilizing this model, the chord structure of music was successfully and accurately encoded, allowing for analysis with up to 98% accuracy. Furthermore, significant recall results were achieved, reaching over 0.9, which suggests that the extracted chord features are highly reliable and accurate in recognizing musical chord information.
Reference22 articles.
1. Hong, X., & Wu, Y. H. (2022). The use of AR to preserve and popularize traditional Chinese musical instruments as part of the formation of the tourist attractiveness of the national art of Guizhou province. Digital Scholarship in the Humanities, 37(2), 426-440.
2. Gibson, S. J. (2021). Shifting from offline to online collaborative music-making, teaching and learning: perceptions of ethno artistic mentors. Music Education Research, 23(2), 1-16.
3. Wang, J., Miao, Z., Xie, N., Xu, W., & Li, A. (2020). Labanotation generation from motion capture data for protection of folk dance. IEEE Access, PP(99), 1-1.
4. Li, J. (2019). The inheritance form of Chinese traditional music under college music education system. Educational Research and Reviews, 1(2), 6-9.
5. Chung, J., & Lee, S. S. (2019). Methodology for music analysis from structural perspective: focusing on tv animation theme songs. Asia Life Sciences(3), 1335-1343.