Hasil untuk "Music"

S. Koelsch

Aäron van den Oord, S. Dieleman, B. Schrauwen

V. Salimpoor, Mitchel Benovoy, K. Larcher et al.

P. Juslin, Petri Laukka

R. Barthes, S. Heath

P. Rentfrow, S. Gosling

Keunwoo Choi, György Fazekas, Mark B. Sandler et al.

We introduce a convolutional recurrent neural network (CRNN) for music tagging. CRNNs take advantage of convolutional neural networks (CNNs) for local feature extraction and recurrent neural networks for temporal summarisation of the extracted features. We compare CRNN with three CNN structures that have been used for music tagging while controlling the number of parameters with respect to their performance and training time per sample. Overall, we found that CRNNs show a strong performance with respect to the number of parameter and training time, indicating the effectiveness of its hybrid structure in music feature extraction and feature summarisation.

J. T. van der Steen, Mirjam C. van Soest-Poortvliet, J. C. van der Wouden et al.

N. Ding, Aniruddh D. Patel, Lin Chen et al.

Speech and music have structured rhythms. Here we discuss a major acoustic correlate of spoken and musical rhythms, the slow (0.25-32Hz) temporal modulations in sound intensity and compare the modulation properties of speech and music. We analyze these modulations using over 25h of speech and over 39h of recordings of Western music. We show that the speech modulation spectrum is highly consistent across 9 languages (including languages with typologically different rhythmic characteristics). A different, but similarly consistent modulation spectrum is observed for music, including classical music played by single instruments of different types, symphonic, jazz, and rock. The temporal modulations of speech and music show broad but well-separated peaks around 5 and 2Hz, respectively. These acoustically dominant time scales may be intrinsic features of speech and music, a possibility which should be investigated using more culturally diverse samples in each domain. Distinct modulation timescales for speech and music could facilitate their perceptual analysis and its neural processing.

Aleksi J. Sihvonen, Teppo Särkämö, Vera Leo et al.

Jonathan Tang

Listening to music can be a rewarding experience for many. Research has shown that multiple factors influence musical reward including personality, age, and musical expertise. However, the role of culture in shaping musical reward remains underexplored. Most cross-cultural studies in music psychology have compared individuals from different countries. This study adopted a novel approach by examining self-construal, an individual-level explanation for cultural differences, in relation to musical rewards associated with favourite music across cultures. A cross-sectional online questionnaire was administered to 435 participants. Results from the multilevel regression analyses, using the two-dimensional model of self-construal, revealed that only within-region variation of interdependent and independent self-construals, not between-region variation of interdependence and independence, were positively associated with musical reward. Specifically, both self-construals were associated with emotion evocation and social reward, while independent self-construal was associated with musical seeking, mood regulation, and sensory-motor subtypes. When applying the eight-dimensional model of self-construal, distinct self-construal profiles emerged in relation to different musical reward subtypes, with the interdependent pole of connectedness to others positively associated with most subtypes except for emotion evocation reward. These findings provide preliminary evidence that self-construal influences the types of rewards experienced across cultures. In particular, one's sense of self, whether construed as interdependent or independent, shapes the types of rewards experienced with favourite music. This study underscores the importance of incorporating specific cultural factors in cross-cultural research on musical reward. By examining self-construal, this work contributes to a more nuanced understanding of cultural diversity in music psychology.

Nori Jacoby, E. Margulis, M. Clayton et al.

Many foundational questions in the psychology of music require cross-cultural approaches, yet the vast majority of work in the field to date has been conducted with Western participants and Western music. For cross-cultural research to thrive, it will require collaboration between people from different disciplinary backgrounds, as well as strategies for overcoming differences in assumptions, methods, and terminology. This position paper surveys the current state of the field and offers a number of concrete recommendations focused on issues involving ethics, empirical methods, and definitions of "music" and "culture."

Dipayan Biswas, Kaisa Lund, Courtney Szocs

Wafa A. Nawwab, Sultan A. Alqasim, Nada N. Alghamdi et al.

Sickle cell disease (SCD) is a genetic disorder characterized by rigid, sickle-shaped red blood cells, leading to complications such as vaso-occlusive crises (VOCs). These acute pain episodes are the most common reason for emergency visits and hospitalizations in adults with SCD. his narrative review evaluated the efficacy of pharmacological and non-pharmacological treatments for acute pain crises in adults with SCD, with secondary attention to safety outcomes, including side effects, treatment duration, hospital stay, and readmission rates. Materials and Methods: A literature search was conducted in PubMed, Cochrane Library, and Google Scholar up to August 20, 2024, focusing on randomized controlled trials (RCTs) in English involving adult patients. Relevant studies were reviewed, and findings were synthesized narratively. The result Twelve RCTs involving 576 adults were included. Most studies were of good quality, though two had high risk and two had unclear risk of bias. Interventions included L-glutamine, pregabalin, regadenoson, ketorolac, individualized opioid protocols, progressive muscle relaxation, and music therapy. L-glutamine and individualized opioid protocols consistently reduced pain intensity. Pregabalin and ketorolac showed mixed results, while non-pharmacological interventions provided modest pain relief or improved mood. Overall, individualized treatment approaches appeared more effective than uniform protocols, though variability in study design and outcomes limits generalizability. IIn conclusion Twelve RCTs involving 576 adults were included. Most studies were of good quality, though two had high risk and two had unclear risk of bias. Interventions included L-glutamine, pregabalin, regadenoson, ketorolac, individualized opioid protocols, progressive muscle relaxation, and music therapy. L-glutamine and individualized opioid protocols consistently reduced pain intensity. Pregabalin and ketorolac showed mixed results, while non-pharmacological interventions provided modest pain relief or improved mood. Overall, individualized treatment approaches appeared more effective than uniform protocols, though variability in study design and outcomes limits generalizability. TEK therapy and L-glutamine were most effective for pain reduction, while pregabalin and regadenoson were safe and promising. Non-pharmacological interventions may support standard care, but further high-quality RCTs are recommended to confirm efficacy and safety.

Emmanuel Deruty

Music information retrieval distinguishes between low- and high-level descriptions of music. Current generative AI models rely on text descriptions that are higher level than the controls familiar to studio musicians. Pitch strength, a low-level perceptual parameter of contemporary popular music, may be one feature that could make such AI models more suited to music production. Signal and perceptual analyses suggest that pitch strength (1) varies significantly across and inside songs; (2) contributes to both small- and large-scale structure; (3) contributes to the handling of polyphonic dissonance; and (4) may be a feature of upper harmonics made audible in a perspective of perceptual richness.

Francesca Ronchini, Luca Comanducci, Simone Marcucci et al.

Text-to-music models have revolutionized the creative landscape, offering new possibilities for music creation. Yet their integration into musicians workflows remains underexplored. This paper presents a case study on how TTM models impact music production, based on a user study of their effect on producers creative workflows. Participants produce tracks using a custom tool combining TTM and source separation models. Semi-structured interviews and thematic analysis reveal key challenges, opportunities, and ethical considerations. The findings offer insights into the transformative potential of TTMs in music production, as well as challenges in their real-world integration.

Atharva Mehta, Shivam Chauhan, Megha Sharma et al.

In recent years, the music research community has examined risks of AI models for music, with generative AI models in particular, raised concerns about copyright, deepfakes, and transparency. In our work, we raise concerns about cultural and genre biases in AI for music systems (music-AI systems) which affect stakeholders including creators, distributors, and listeners shaping representation in AI for music. These biases can misrepresent marginalized traditions, especially from the Global South, producing inauthentic outputs (e.g., distorted ragas) that reduces creators' trust on these systems. Such harms risk reinforcing biases, limiting creativity, and contributing to cultural erasure. To address this, we offer recommendations at dataset, model and interface level in music-AI systems.

Philip A. Ewell

For over twenty years, music theory has tried to diversify with respect to race, yet the field today remains remarkably white, not only in terms of the people who practice music theory but also in the race of the composers and theorists whose work music theory privileges. In this paper, a critical-race examination of the field of music theory, I try to come to terms with why this is so. I posit that there exists a “white racial frame” in music theory that is structural and institutionalized, and that only through a deframing and reframing of this white racial frame will we begin to see positive racial changes in music theory.

Chuang Gan, Deng Huang, Peihao Chen et al.

In this paper, we introduce Foley Music, a system that can synthesize plausible music for a silent video clip about people playing musical instruments. We first identify two key intermediate representations for a successful video to music generator: body keypoints from videos and MIDI events from audio recordings. We then formulate music generation from videos as a motion-to-MIDI translation problem. We present a Graph$-$Transformer framework that can accurately predict MIDI event sequences in accordance with the body movements. The MIDI event can then be converted to realistic music using an off-the-shelf music synthesizer tool. We demonstrate the effectiveness of our models on videos containing a variety of music performances. Experimental results show that our model outperforms several existing systems in generating music that is pleasant to listen to. More importantly, the MIDI representations are fully interpretable and transparent, thus enabling us to perform music editing flexibly. We encourage the readers to watch the demo video with audio turned on to experience the results.

D. Camlin, T. Lisboa

ABSTRACT The global COVID-19 pandemic has disrupted music education across the world, resulting in radical changes to the field of practice, accelerating a ‘turn’ toward online digital musical experiences. This digital ‘turn’ is likely to influence the future of music education in a variety of complex and inter-connected ways. In this special issue, we explore the implications of such a ‘turn’ for music educators and their students / participants, and highlight some of the ways in which music researchers and educators have responded to the crisis. We hope these narratives will help illuminate some of the ways in which music education might recover its equilibrium, as well as make a contribution more generally to the complex business of human recovery in a post-COVID world.