Entertainment Computing, Journal Year: 2024, Volume and Issue: 52, P. 100706 - 100706
Published: May 10, 2024
Language: Английский
Entertainment Computing, Journal Year: 2024, Volume and Issue: 52, P. 100706 - 100706
Published: May 10, 2024
Language: Английский
Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 28, 2025
Language: Английский
Citations
0Journal of Computational Methods in Sciences and Engineering, Journal Year: 2025, Volume and Issue: unknown
Published: Feb. 14, 2025
With the growth of people’s demand for personalized music, how to use AI technology achieve accurate understanding and creative transformation music styles has become an important topic. In this study, a transfer learning algorithm based on deep framework is designed automatically identify simulate different style characteristics in order break through traditional creation mode. By pre-training large-scale multi-style library then fine-tuning it specific target style, effective migration achieved. The experimental data show that method can significantly improve accuracy conversion make similarity generated works timbre, melody, rhythm, other dimensions reach more than 92% while maintaining good novelty diversity. verify audience acceptance works, study invited participants from age groups musical preferences conduct listening comparison experiment. results compared with direct non-transfer models or artificially created algorithms have achieved higher praise rates, especially two key indicators innovation emotional resonance, which improved, respectively. About 23% 16%.
Language: Английский
Citations
0Interactive Learning Environments, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 21
Published: April 11, 2025
Language: Английский
Citations
0Education and Information Technologies, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 17, 2025
Language: Английский
Citations
0International Journal of Computational Intelligence Systems, Journal Year: 2024, Volume and Issue: 17(1)
Published: Aug. 14, 2024
Personalized music teaching in universities improves students' learning and efficiency through adaptive guidance. This adaptability requires large study data intelligent decisions based on the learner's ability. article introduces a Definitive Teaching Support System (DTSS) exclusive to augment this concept. system is designed increase of student interest The powered by fuzzy decision for identifying maximum personalized processes. Low-to-high-sorted personalization provides new endorsements further sessions derivative process. Maximum target universities. differs various students from which common level monotonous recommendations identified. identified set as global solution towards personalization. defuzzification reduces chances low expelling stationary outcomes.
Language: Английский
Citations
1Entertainment Computing, Journal Year: 2024, Volume and Issue: 52, P. 100706 - 100706
Published: May 10, 2024
Language: Английский
Citations
0