- Tytuł:
- Artificial Intelligence on the Identification of Beiguan Music
- Autorzy:
-
Chang, Yu-Hsin
Yao, Shu-Nung - Powiązania:
- https://bibliotekanauki.pl/articles/1945644.pdf
- Data publikacji:
- 2021
- Wydawca:
- Polska Akademia Nauk. Czasopisma i Monografie PAN
- Tematy:
-
artificial neural network
Beiguan music
music information retrieval
social tagging - Opis:
- This research determines an identification system for the types of Beiguan music – a historical, non-classical music genre – by combining artificial neural network (ANN), social tagging, and music information retrieval (MIR). Based on the strategy of social tagging, the procedure of this research includes: evaluating the qualifying features of 48 Beiguan music recordings, quantifying 11 music indexes representing tempo and instrumental features, feeding these sets of quantized data into a three-layered ANN, and executing three rounds of testing, with each round containing 30 times of identification. The result of ANN testing reaches a satisfying correctness (97% overall) on classifying three types of Beiguan music. The purpose of this research is to provide a general attesting method, which can identify diversities within the selected non-classical music genre, Beiguan. The research also quantifies significant musical indexes, which can be effectively identified. The advantages of this method include improving data processing efficiency, fast MIR, and evoking possible musical connections from the high-relation result of statistical analyses.
- Źródło:
-
Archives of Acoustics; 2021, 46, 3; 471-478
0137-5075 - Pojawia się w:
- Archives of Acoustics
- Dostawca treści:
- Biblioteka Nauki