EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Effects of Temperature Sampling and Tempo Variation on LSTM-Based Music Generation

Imam Fathurrahman, Muhammad Djamaluddin, Ramli Ahmad, Hariman Bahtiar, Muhamad Sadali, Zulkipli Mansyur

Jurnal Masyarakat Informatika · 19.11.2026 · 17 (2) · 229-249

DOI: 10.14710/jmasif.17.2.78593 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal Masyarakat Informatika, online erschienen am 19.11.2026. Verfasst von Imam Fathurrahman und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Long Short-Term Memory (LSTM) models for symbolic music generation may produce repetitive sequences under deterministic decoding. This study examines how sampling temperature and externally imposed tempo variation affect the statistical characteristics of generated MIDI music. A factorial experiment combined four decoding settings (Argmax and temperature sampling at T = 0.6, 0.7, and 1.0) with fixed- and dynamic-tempo rendering. Using one trained LSTM checkpoint and controlled seeds, 40 MIDI files were generated across eight conditions, with five runs per condition. The dataset was split by MIDI file before sequence construction to reduce data leakage. Generated outputs were assessed using pitch entropy, repetition ratios, N-gram overlap, pitch-class distribution similarity, rhythmic diversity, and tempo statistics. At T = 1.0, mean pitch entropy was highest (5.57 ± 0.13 bits), immediate repetition lowest (0.10 ± 0.01), and Chroma Jensen-Shannon Divergence lowest (0.0244 ± 0.0163). Higher temperatures also reduced trigram overlap with the validation corpus, indicating a diversity-similarity trade-off. Dynamic-tempo rendering introduced timing variation without changing pitch-based metrics under matched sampling conditions. These results distinguish effects of token sampling from tempo rendering but do not establish perceptual musical quality.

Zitieren

APA

Fathurrahman, I., Djamaluddin, M., Ahmad, R., Bahtiar, H., Sadali, M., & Mansyur, Z. (2026). Effects of Temperature Sampling and Tempo Variation on LSTM-Based Music Generation. Jurnal Masyarakat Informatika, 17(2), 229-249. https://doi.org/10.14710/jmasif.17.2.78593

Vancouver

Fathurrahman I, Djamaluddin M, Ahmad R, Bahtiar H, Sadali M, Mansyur Z. Effects of Temperature Sampling and Tempo Variation on LSTM-Based Music Generation. Jurnal Masyarakat Informatika. 2026;17(2):229-249. doi:10.14710/jmasif.17.2.78593

BibTeX
@article{Fathurrahman2026,
  author = {Fathurrahman, Imam and Djamaluddin, Muhammad and Ahmad, Ramli and Bahtiar, Hariman and Sadali, Muhamad and Mansyur, Zulkipli},
  title = {Effects of Temperature Sampling and Tempo Variation on LSTM-Based Music Generation},
  journal = {Jurnal Masyarakat Informatika},
  year = {2026},
  volume = {17},
  number = {2},
  pages = {229--249},
  doi = {10.14710/jmasif.17.2.78593}
}
Kostenlos starten →