Open AccessRETRACTED: Song recognition in music library based on cloud computing
Author(s) -
Lei Du
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/750/1/012167
Subject(s) - computer science , cloud computing , speech recognition , musical , feature extraction , feature (linguistics) , music information retrieval , artificial intelligence , multimedia , art , visual arts , linguistics , philosophy , operating system
There are many types of music, and due to the increase of music creators and the development of the Internet, there have been a large number of music. Identifying songs in the music library is conducive to the management and operation of songs, and helps listeners to choose their favorite music. Aiming at this problem, this paper proposes a song recognition method in a music library based on cloud computing. This paper first analyzes the advantages of cloud computing technology, and then proposes a song feature recognition method. Based on the similarity matrix of musical notes, a criterion for selecting note features is given to identify songs in a music library. Finally, the song feature recognition method is combined with cloud computing technology for song recognition. Experiments show that compared with the musical note recognition method with feature weights and the musical note recognition method based on invariant feature extraction of musical notes, the song recognition method in the cloud-based music library proposed in this paper has higher recognition accuracy and faster recognition speed.