This study proposes the preservation of traditional Javanese musical instruments known as Gamelan using an immersive and challenging approach in a virtual reality game format. In an effort to achieve a challenging experience, the gamification is designed by observing musical instrument games selected based on their popularity in the Google Play and the App Store. Oculus Quest 2 which is a stand-alone Head Mounted Displays that provides a high-quality immersive display and more flexibility for users to move is chosen to present the game. Overall, the research target can be achieved based on the evaluation using Mean Opinion Scores. The degree of immersion, presence, likeable, challenging, and the value of cultural preservation contained in the game reaches a range of values between good and excellent. Meanwhile, cybersickness still seems to be a chore for developers to make Head Mounted Displays devices more comfortable.
A Multiplayer Virtual Reality Game (MVRG) was developed in order to support experiences in learning and playing orchestral music through a virtual world called the Gamelan Land (GL) game. The GL game was aimed as a virtual place to support interaction between musicians and Gamelan enthusiasts who are spread all over the world. It supports them carrying out Gamelan community activities in the real world into a virtual world through immersive virtual experiences. The story developed in the GL game reflects the real life of the Gamelan community. Oculus Quest 2 which is a Head Mounted Displays (HMD) device that can deliver highly immersive 3D environments was selected as the platform to run the Gamelan music MVRG provided in the GL game. The performance of the Gamelan music MVRG shows promising results. Improvement of audio and visual latency in playing music in orchestra is still a problem to be solved. The problem can be caused by differences in internet network speed and device specifications. So far, low poly 3D models can be an alternative solution. Moreover, although it still requires testing involving more users and longer time, the social presence approach in the GL game can be implemented well and has promising prospects for further development.
A novel approach was proposed to develop a composition generation system for creating note sequences representing question-and-answer phrases (QAPs) in melodic phrases. Using a small dataset containing fewer than 10 compositions, the system is expected to generate new melodies that extend beyond the limitations of the original dataset. The modeling of note sequence data and selecting appropriate notes in specific sequences within the melody were chosen for gamelan skeletal melody generation using the Genetic Algorithm (GA) method. Gamelan, a traditional musical ensemble from Java, was selected as the focus of this research, with experiments centered on the gamelan skeletal melody, which plays a role similar to chord progressions in Western music. The evaluation was conducted by statistically analyzing the sequence of notations generated from the dataset and through expert testing. The experimental results demonstrate that the proposed method can generate compositions with well-formed melodic phrases through a small dataset containing varying lengths, data mapping, feature selection based on QAP patterns. GA can enhance creativity in creating note sequences and new QAP patterns, including novel patterns.
This research proposes an explanatory deep learning-based music generation approach, where the output of a deep learning model is validated through a set of predefined musical rules, with a refinement process applied when inaccuracies are detected. The study focuses on gamelan, a traditional form of Indonesian music. A Long Short-Term Memory (LSTM) network is used to generate musical compositions, while a modified Genetic Algorithm (GA), omitting the selection and crossover operators, performs validation and, when necessary, refinement via mutation. The LSTM network produces initial compositions, and the GA module ensures compliance with musical rules, enhancing both explainability and creativity. The model successfully generates new bars and lines with notation sequences not found in the original dataset, indicating creative variation. Whether produced directly by the LSTM or refined through GA, the generated output demonstrates the system’s ability to innovate while preserving core musical characteristics. Furthermore, the GA-based validation allows the generated music to be interpreted in terms of the underlying rule constraints. Statistical analysis, including correlation and regression tests using the t-test, reveals a near-perfect relationship between the original and generated compositions. These findings support the effectiveness of the proposed Automatic Music Generation (AMG) model in fostering creative exploration of new tonal patterns aligned with the target genre.