We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Learning Experience of University Music Course Based on Emotional Computing.
- Authors
Liying Huang
- Abstract
The university music course provided a comprehensive exploration of music theory, history, and performance, offering a multifaceted approach to understanding the art form. From delving into the intricacies of musical composition to honing practical skills through instrument or vocal training, the course provided a well-rounded education. This study explores the learning experience of a university music course enhanced by emotional computing, specifically focusing on the application of recurrent neural networks (RNNs) in creating a multimedia identification and analysis method for Music Course in universities performance music. Leveraging RNNs, particularly Long Short-Term Memory (LSTM) architecture, enables the capturing of temporal relationships and dynamics inherent in musical performances. The project involves compiling an extensive dataset of Music Course in universities performance recordings spanning various genres, performers, and techniques. Through preprocessing the audio and video components, relevant information is extracted. The RNN, trained on these features, identifies patterns and traits associated with diverse Music Course in universities performances. Similarity measures, such as Euclidean distance, gauge the resemblance between performance representations. The RNNbased system can evolve to perform tasks like score following, expressive performance analysis, and stylistic variation creation, contributing to comprehensive performance analysis. This method, RNN-LSTM, boasts impressive accuracy (99%), precision (97%), recall (98.9%), and an F1 Score of 97.6%, offering valuable insights into timing accuracy, dynamics, phrasing, and other expressive qualities of Music Course in universities performances through the correlation with related musical scores.
- Subjects
RECURRENT neural networks; MUSICAL composition; MUSICAL performance; MUSICAL analysis; MUSIC scores; COMPUTER workstation clusters; SOUND recordings
- Publication
Journal of Electrical Systems, 2024, Vol 20, Issue 1, p313
- ISSN
1112-5209
- Publication type
Article
- DOI
10.52783/jes.684