Synthetic symbolic music generation, the process of creating new musical pieces using symbolic representations, has gained significant traction in the field of music informatics and computational creativity. It holds immense potential for various applications, ranging from music education and composition assistance to music therapy and personalized music recommendation systems. Classical Turkish music (CTM) exhibit distinct characteristics regarding Western Tonal Classical Music (WCM) such as melodic organization, formation of rhythmic structure or melodic expressions. This study tackles the challenge of symbolic music composition, focusing on CTM. Unlike WCM, CTM incorporates microtonal intervals. These intervals are smaller than the semitones in Western music, allowing for a more nuanced expression of pitch. This leads to a more diverse set of pitch ranges. The proposed method employs a combination of self-attention and long-short term memory (LSTM) networks to capture long-term relational information and generate realistic CTM compositions. LSTMs effectively model sequential dependencies and improve local relations within musical structures and self-attention improves the context vector, allowing the model to attend to different aspects of the musical context simultaneously. This combination enables the proposed method to generate compositions that are both musically coherent and stylistically consistent with distinct features of CTM. The proposed method was evaluated on two datasets, the CTM dataset and Classical Music Piano (CPM) dataset. The assessment of musical contents is evaluated through melodic similarity and stylistic consistency metrics. The results demonstrate that the proposed method is able to generate musical content that is coherent and produce music that is pleasing-to-hear. Overall, the article presents a novel and effective approach to symbolic music composition, focusing on CTM.
self-attention deep learning musical information retrieval turkish classical music music generation
The hyperparameter optimization has been conducted at the B.T.U. High-Performance Clustering Laboratory (HPCLAB).
Birincil Dil | İngilizce |
---|---|
Konular | Derin Öğrenme, Yapay Zeka (Diğer) |
Bölüm | Research Articles |
Yazarlar | |
Erken Görünüm Tarihi | 19 Nisan 2024 |
Yayımlanma Tarihi | 7 Haziran 2024 |
Gönderilme Tarihi | 19 Aralık 2023 |
Kabul Tarihi | 1 Şubat 2024 |
Yayımlandığı Sayı | Yıl 2024Cilt: 8 Sayı: 1 |
The works published in Journal of Innovative Science and Engineering (JISE) are licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.