Autors: Kostov K., Pleshkova, S. G.
Title: Neural Network–Driven Markov Chain Model Development for Adaptive Digital Audio Effects
Keywords: Adaptive digital audio effects, Generative artificial intelligence, Markov chain, Neural networks

Abstract: This paper introduces a neural network-driven Markov chain model for optimizing a digital transformation model. The proposed model generates adaptive and dynamic delay state transitions by integrating a neural network’s predictive capabilities with the stochastic properties of Markov chains. Trained on modified audio samples with multiple delayed segments, it preserves the original signal’s timbre and dynamics while introducing musically coherent variations, enabling creative and versatile audio processing.

References

  1. Verfaille, V., Zölzer, U., & Arfib, D. (2006). Adaptive digital audio effects (A-DAFx): A new class of sound transformations. IEEE Transactions on Speech and Audio Processing, 14(5), 1817–1831. https://doi.org/10.1109/TSA.2005.858531
  2. Zölzer, U. (2011). DAFX: Digital Audio Effects. John Wiley & Sons.
  3. Corchado, J. M., F, S. L., V, J. M. N., S, R. G., & Chamoso, P. (2023). Generative Artificial Intelligence: Fundamentals. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 12, e31704–e31704. https://doi.org/10.14201/adcaij.31704
  4. Pleshkova, S., & Kostov, K. (2025). Development of a Model for Digital Transformation in Music Production Using Audio Effects Algorithms Based on Generative AI with Markov Chains (p. 4). https://doi.org/10.1109/ICEST66328.2025.11098448
  5. Pedroza, H., Meza, G., & Roman, I. (2022). EGFxSet: Electric guitar tones processed through real effects of distortion, modulation, delay and reverb. ISMIR Late Breaking Demo.
  6. Weber, A., Alegre, L. N., & Torresen, J. (n.d.). Parameterized Melody Generation with Autoencoders and Temporally-Consistent Noise.
  7. Woldegiorgis, B. H., Mequanint, K., Bitew, M. A., Beza, T. B., & Yibre, A. M. (2023). Artificial Intelligence and Digitalization for Sustainable Development: 10th EAI International Conference, ICAST 2022, Bahir Dar, Ethiopia, November 4-6, 2022, Proceedings. Springer Nature.
  8. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.

Issue

National Conference with International Participation, TELECOM, 2026, Bulgaria, https://doi.org/10.1109/TELECOM66943.2025.11304052

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus