Hasil untuk "Music"

R. E. Milliman

L. Green

I. Peretz, M. Coltheart

M. Casey, R. Veltkamp, Masataka Goto et al.

S. Saarikallio, Jaakko Erkkilä

Xiaofei Zhang, Lingyun Xu, Le Xu et al.

A. Maratos, C. Gold, X. Wang et al.

Ron Taieb, Yoel Greenberg, Barak Sober

Motifs often recur in musical works in altered forms, preserving aspects of their identity while undergoing local variation. This paper investigates how such motivic transformations occur within their musical context in symbolic music. To support this analysis, we develop a probabilistic framework for modeling motivic transformations and apply it to Beethoven's piano sonatas by integrating multiple datasets that provide melodic, rhythmic, harmonic, and motivic information within a unified analytical representation. Motif transformations are represented as multilabel variables by comparing each motif instance to a designated reference occurrence within its local context, ensuring consistent labeling across transformation families. We introduce a multilabel Conditional Random Field to model how motif-level musical features influence the occurrence of transformations and how different transformation families tend to co-occur. Our goal is to provide an interpretable, distributional analysis of motivic transformation patterns, enabling the study of their structural relationships and stylistic variation. By linking computational modeling with music-theoretical interpretation, the proposed framework supports quantitative investigation of musical structure and complexity in symbolic corpora and may facilitate the analysis of broader compositional patterns and writing practices.

P. Keller, P. Janata

Zhouyu Fu, Guojun Lu, K. Ting et al.

C. Karageorghis, D. Priest

Since a 1997 review by Karageorghis and Terry, which highlighted the state of knowledge and methodological weaknesses, the number of studies investigating musical reactivity in relation to exercise has swelled considerably. In this two-part review paper, the development of conceptual approaches and mechanisms underlying the effects of music are explicated (Part I), followed by a critical review and synthesis of empirical work (spread over Parts I and II). Pre-task music has been shown to optimise arousal, facilitate task-relevant imagery and improve performance in simple motoric tasks. During repetitive, endurance-type activities, self-selected, motivational and stimulative music has been shown to enhance affect, reduce ratings of perceived exertion, improve energy efficiency and lead to increased work output. There is evidence to suggest that carefully selected music can promote ergogenic and psychological benefits during high-intensity exercise, although it appears to be ineffective in reducing perceptions of exertion beyond the anaerobic threshold. The effects of music appear to be at their most potent when it is used to accompany self-paced exercise or in externally valid conditions. When selected according to its motivational qualities, the positive impact of music on both psychological state and performance is magnified. Guidelines are provided for future research and exercise practitioners.

Mohammad Shokri, Alexandra C. Salem, Gabriel Levine et al.

In this paper, we introduce Story2MIDI, a sequence-to-sequence Transformer-based model for generating emotion-aligned music from a given piece of text. To develop this model, we construct the Story2MIDI dataset by merging existing datasets for sentiment analysis from text and emotion classification in music. The resulting dataset contains pairs of text blurbs and music pieces that evoke the same emotions in the reader or listener. Despite the small scale of our dataset and limited computational resources, our results indicate that our model effectively learns emotion-relevant features in music and incorporates them into its generation process, producing samples with diverse emotional responses. We evaluate the generated outputs using objective musical metrics and a human listening study, confirming the model's ability to capture intended emotional cues.

Seungheon Doh, Keunwoo Choi, Juhan Nam

While the recent developments in large language models (LLMs) have successfully enabled generative recommenders with natural language interactions, their recommendation behavior is limited, leaving other simpler yet crucial components such as metadata or attribute filtering underutilized in the system. We propose an LLM-based music recommendation system with tool calling to serve as a unified retrieval-reranking pipeline. Our system positions an LLM as an end-to-end recommendation system that interprets user intent, plans tool invocations, and orchestrates specialized components: boolean filters (SQL), sparse retrieval (BM25), dense retrieval (embedding similarity), and generative retrieval (semantic IDs). Through tool planning, the system predicts which types of tools to use, their execution order, and the arguments needed to find music matching user preferences, supporting diverse modalities while seamlessly integrating multiple database filtering methods. We demonstrate that this unified tool-calling framework achieves competitive performance across diverse recommendation scenarios by selectively employing appropriate retrieval methods based on user queries, envisioning a new paradigm for conversational music recommendation systems.

Angelos-Nikolaos Kanatas, Charilaos Papaioannou, Alexandros Potamianos

Recent advances in music foundation models have improved audio representation learning, yet their effectiveness across diverse musical traditions remains limited. We introduce CultureMERT-95M, a multi-culturally adapted foundation model developed to enhance cross-cultural music representation learning and understanding. To achieve this, we propose a two-stage continual pre-training strategy that integrates learning rate re-warming and re-decaying, enabling stable adaptation even with limited computational resources. Training on a 650-hour multi-cultural data mix, comprising Greek, Turkish, and Indian music traditions, results in an average improvement of 4.9% in ROC-AUC and AP across diverse non-Western music auto-tagging tasks, surpassing prior state-of-the-art, with minimal forgetting on Western-centric benchmarks. We further investigate task arithmetic, an alternative approach to multi-cultural adaptation that merges single-culture adapted models in the weight space. Task arithmetic performs on par with our multi-culturally trained model on non-Western auto-tagging tasks and shows no regression on Western datasets. Cross-cultural evaluation reveals that single-culture models transfer with varying effectiveness across musical traditions, whereas the multi-culturally adapted model achieves the best overall performance. To support research on world music representation learning, we publicly release CultureMERT-95M and CultureMERT-TA-95M, fostering the development of more culturally aware music foundation models.

Hugo Chateau-Laurent, Tara Vanhatalo, Wei-Tung Pan et al.

Generative artificial intelligence raises concerns related to energy consumption, copyright infringement and creative atrophy. We show that randomly initialized recurrent neural networks can produce arpeggios and low-frequency oscillations that are rich and configurable. In contrast to end-to-end music generation that aims to replace musicians, our approach expands their creativity while requiring no data and much less computational power. More information can be found at: https://allendia.com/

Brandon James Carone, Iran R. Roman, Pablo Ripollés

Multimodal Large Language Models (LLMs) claim "musical understanding" via evaluations that conflate listening with score reading. We benchmark three SOTA LLMs (Gemini 2.5 Pro, Gemini 2.5 Flash, and Qwen2.5-Omni) across three core music skills: Syncopation Scoring, Transposition Detection, and Chord Quality Identification. Moreover, we separate three sources of variability: (i) perceptual limitations (audio vs. MIDI inputs), (ii) exposure to examples (zero- vs. few-shot manipulations), and (iii) reasoning strategies (Standalone, CoT, LogicLM). For the latter we adapt LogicLM, a framework combining LLMs with symbolic solvers to perform structured reasoning, to music. Results reveal a clear perceptual gap: models perform near ceiling on MIDI but show accuracy drops on audio. Reasoning and few-shot prompting offer minimal gains. This is expected for MIDI, where performance reaches saturation, but more surprising for audio, where LogicLM, despite near-perfect MIDI accuracy, remains notably brittle. Among models, Gemini Pro achieves the highest performance across most conditions. Overall, current systems reason well over symbols (MIDI) but do not yet "listen" reliably from audio. Our method and dataset make the perception-reasoning boundary explicit and offer actionable guidance for building robust, audio-first music systems.

Lukáš Samuel Marták, Patricia Hu, Gerhard Widmer

Automatic Music Transcription (AMT) -- the task of converting music audio into note representations -- has seen rapid progress, driven largely by deep learning systems. Due to the limited availability of richly annotated music datasets, much of the progress in AMT has been concentrated on classical piano music, and even a few very specific datasets. Whether these systems can generalize effectively to other musical contexts remains an open question. Complementing recent studies on distribution shifts in sound (e.g., recording conditions), in this work we investigate the musical dimension -- specifically, variations in genre, dynamics, and polyphony levels. To this end, we introduce the MDS corpus, comprising three distinct subsets -- (1) Genre, (2) Random, and (3) MAEtest -- to emulate different axes of distribution shift. We evaluate the performance of several state-of-the-art AMT systems on the MDS corpus using both traditional information-retrieval and musically-informed performance metrics. Our extensive evaluation isolates and exposes varying degrees of performance degradation under specific distribution shifts. In particular, we measure a note-level F1 performance drop of 20 percentage points due to sound, and 14 due to genre. Generally, we find that dynamics estimation proves more vulnerable to musical variation than onset prediction. Musically informed evaluation metrics, particularly those capturing harmonic structure, help identify potential contributing factors. Furthermore, experiments with randomly generated, non-musical sequences reveal clear limitations in system performance under extreme musical distribution shifts. Altogether, these findings offer new evidence of the persistent impact of the Corpus Bias problem in deep AMT systems.

Yifei Zhang

With the rapid development of artificial intelligence and the Internet of Things technology, the automatic music composition system has become a hot topic of research. This paper presents the TransVAE-Music composition system to achieve efficient multimodal data perception and fusion. Through the introduction of the Internet of Things technology, the system can collect and process audio, video and other data in real time, and improve the diversity and artistry of music generation. At the same time, the Bayesian optimization mechanism is used to finely adjust the hyperparameters in the system to further improve the model performance. Experimental results show that TransVAE-Music has 1.10 and 1.12 reconstruction errors on the POP909 and FMA datasets, respectively, which significantly outperforms other mainstream automatic music generation models. In addition, the model reached 4.8 and 4.9 in perceived quality score (PQS), and 4.4 and 4.5 in user satisfaction score (USS), respectively. These results demonstrate that the proposed system has significant advantages in terms of the accuracy of music generation and the user experience. This study not only provides an effective method for automatic music generation, but also provides important references for future studies on multimodal data fusion and high-quality music generation.

Jing Zhao, Kun Cheng

This study investigates the synchronization of real-time music generation with visual elements in Virtual Reality (VR) environments, leveraging Artificial Intelligence (AI) to create immersive, interactive music experiences for performance, education, and therapy. By leveraging deep learning techniques, specifically Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, the study investigates real-time music generation and synchronization with VR environments. The optimization of music-visual alignment was achieved through Genetic Algorithms (GAs), enhancing the overall coherence and responsiveness of the system. Key findings include significant improvements in user engagement, learning outcomes, and audience satisfaction in educational and performance contexts. The system achieved a high degree of musical coherence, with sequence prediction accuracy of 92.3% and sub-50ms latency, providing a seamless VR music experience. Case studies focused on interactive music education, immersive performance, and personalized music therapy demonstrated the system’s potential in diverse settings, with improvements in user retention, stress reduction, and overall satisfaction. This study highlights the transformative potential of combining VR and AI in music, paving the way for innovative applications in music education, performance, and therapy. The findings offer a foundation for future research and development in immersive music technologies.

Mathias Rose Bjare, Stefan Lattner, Gerhard Widmer

In recent years, the quality and public interest in music generation systems have grown, encouraging research into various ways to control these systems. We propose a novel method for controlling surprisal in music generation using sequence models. To achieve this goal, we define a metric called Instantaneous Information Content (IIC). The IIC serves as a proxy function for the perceived musical surprisal (as estimated from a probabilistic model) and can be calculated at any point within a music piece. This enables the comparison of surprisal across different musical content even if the musical events occur in irregular time intervals. We use beam search to generate musical material whose IIC curve closely approximates a given target IIC. We experimentally show that the IIC correlates with harmonic and rhythmic complexity and note density. The correlation decreases with the length of the musical context used for estimating the IIC. Finally, we conduct a qualitative user study to test if human listeners can identify the IIC curves that have been used as targets when generating the respective musical material. We provide code for creating IIC interpolations and IIC visualizations on https://github.com/muthissar/iic.