Skip to main navigation Skip to search Skip to main content

Fusing Memory and Attention: A study on LSTM, Transformer and Hybrid Architectures for Symbolic Music Generation

  • Kalinga Institute of Industrial Technology

Research output: Contribution to journal › Article › peer-review

Abstract

Machine learning techniques, such as Transformers and Long Short-Term Memory (LSTM) networks, play a crucial role in Symbolic Music Generation (SMG). Existing literature indicates a difference between LSTMs and Transformers regarding their ability to model local melodic continuity versus maintaining global structural coherence. However, their specific properties within the context of SMG have not been systematically studied. This paper addresses this gap by providing a fine-grained comparative analysis of LSTMs versus Transformers for SMG, examining local and global properties in detail using 17 musical quality metrics on the Deutschl dataset. We find that LSTM networks excel at capturing local patterns but fail to preserve long-range dependencies, while Transformers model global structure effectively but tend to produce irregular phrasing. Based on this analysis and leveraging their respective strengths, we propose a Hybrid architecture combining a Transformer Encoder with an LSTM Decoder and evaluate it against both baselines. We evaluated 1000 generated melodies from each of the three architectures on the Deutschl dataset. The results show that the hybrid method achieves better local and global continuity and coherence compared to the baselines. Our work highlights the key characteristics of these models and demonstrates how their properties can be leveraged to design superior models. We also supported the experiments with ablation studies and human perceptual evaluations, which statistically support the findings and provide robust validation for this work.

Original languageEnglish
Article number131173
JournalExpert Systems with Applications
Early online date26 Jan 2026
DOIs
Publication statusE-pub ahead of print - 26 Jan 2026

Keywords

  • Deep learning LSTM
  • Musical structure analysis
  • Sequence modeling
  • Symbolic music generation
  • Transformer

Fingerprint

Dive into the research topics of 'Fusing Memory and Attention: A study on LSTM, Transformer and Hybrid Architectures for Symbolic Music Generation'. Together they form a unique fingerprint.

Cite this