This paper introduces a model-agnostic approach to study statistical synergy, a form of emergence in which patterns at large scales are not traceable from lower scales. Our framework leverages various multivariate extensions of Shannon's mutual information, and introduces the O-information as a metric that is capable of characterizing synergy- and redundancy-dominated systems. The O-information is a symmetric quantity, and can assess intrinsic properties of a system without dividing its parts into "predictors" and "targets." We develop key analytical properties of the O-information, and study how it relates to other metrics of high-order interactions from the statistical mechanics and neuroscience literature. Finally, as a proof of concept, we present an exploration on the relevance of statistical synergy in Baroque music scores.
Elizabeth Brown Vallim Brisola, Debi Maskell Graham
Abstract Objective The importance of physical, social, emotional, and spiritual well-being during the early years of life is well established, along with the profound impact of infant mental health on subsequent development. Given the rapid neuropsychological maturation of infants, early interventions are essential – yet symptoms are often overlooked. This paper highlights the use and significance of musical care and singing interventions with infants and their caregivers as a means of fostering mental health. Method Given the flourishing yet limited literature on this topic, the authors offer a combination of practical information and therapeutic applications, informed by their empirical research, professional experience and current literature, to inspire an evidence-based practice and expand options for practitioners. Results Among the various therapeutic interventions and strategies employed with infants, musical care – particularly through song and singing – can be beneficial and effect the infant-adults bond, and is gaining traction worldwide. Therapeutic interventions using songs and singing provide professionals with meaningful options for incorporating music into care, whether the focus is on caretakers, infants, or on their relationship. Conclusion Regardless of the focus, singing interventions can foster mental health by providing the care and safety that infants yearn for. They also offer a means of effectively communicating emotions and intentions at a deep and personal level. The effectiveness of these interventions can be further enhanced by valuing clients’ songs preferences, their cultural background, personal experiences, and family history.
Nicholas Meier, Kilian Sander, Anton Schreiber
et al.
Although the last two years have seen AI systems progress significantly when it comes to generating cultural products like literature, poems, or music, the jury is still out when it comes to determining whether the aesthetic quality of these products increases in tandem with the performance enhancements of underlying large language models (LLMs). We replicated the study by Schreiber et al. (2024) to test whether the creative performance of selected LLMs had improved over the past two years in the musical domain. In an online rating experiment based on a melody continuation paradigm, 75 melodic continuations generated by the AI systems Qwen 2 (Version 72B Instruct), Llama 3 (Version 70B Instruct), and ChatGPT (Version 4) were compared to 23 solutions composed by humans. The aesthetic quality of the sound examples was then evaluated by N = 54 listeners (music students) using four criteria (convincing, logical and meaningful, interesting, and liking). As the first main finding, human-based creative solutions outperformed all three AI systems on all four dependent variables (large effect sizes 1.11 ≤ dz ≤ 2.51), thus confirming the finding by Schreiber et al. (2024). The second main finding revealed a mean (and meaningful) discrimination sensitivity of d’ = 1.09 for AI- and human-based solutions. We conclude that merely boosting the volume of training of the AI systems does not guarantee correlating improvement in the creative musical output produced under controlled conditions.
Rr. Yudiswara Ayu Permatasari, Eli Irawati, Nadia Elasalama
This research examines the redefinition of education based on local wisdom through applied ethnomusicology perspectives using philosophical research methods and literature study approaches. Applied ethnomusicology offers a comprehensive theoretical framework for understanding how traditional music and arts can serve as foundations for more contextual and meaningful educational systems. This study analyses literature on local wisdom concepts, applied ethnomusicology, and alternative educational systems to construct a new understanding of local culture-based education. Through philosophical analysis, this research reveals that local wisdom-based education is not limited to learning and applying traditional objects or artistic artefacts from a particular region. The research findings demonstrate that local wisdom-based education provides a broader perspective on intellectual wealth values within cultures grounded in regional characteristics and problem-solving systems possessed by local communities. These findings theoretically contribute to developing more inclusive, contextual, and meaningful educational models for students' character development and cultural identity formation. This perspective transforms education from artefact-centred learning to value-based cultural understanding encompassing indigenous knowledge systems and community-based solutions.
This essay was inspired by a pedagogical dilemma I encountered in North American literature classes I conducted at a public university in Paraná State, Brazil. According to Menezes (2015), there are many challenges to teaching English language literature in English to non-Anglophone speakers. During my lessons on Dark Romantic literature, I realized that that content was arduous for the students, so I sought to make the subject more engaging. Integrating music into the curriculum emerged as a potential solution (Lira, 2018). Therefore, this study offers a gothic and/or dark romantic reading of Taylor Swift’s album The Tortured Poets Department.
Language. Linguistic theory. Comparative grammar, Literature (General)
The field of music generation using Large Language Models (LLMs) is evolving rapidly, yet existing music notation systems, such as MIDI, ABC Notation, and MusicXML, remain too complex for effective fine-tuning of LLMs. These formats are difficult for both machines and humans to interpret due to their variability and intricate structure. To address these challenges, we introduce YNote, a simplified music notation system that uses only four characters to represent a note and its pitch. YNote's fixed format ensures consistency, making it easy to read and more suitable for fine-tuning LLMs. In our experiments, we fine-tuned GPT-2 (124M) on a YNote-encoded dataset and achieved BLEU and ROUGE scores of 0.883 and 0.766, respectively. With just two notes as prompts, the model was able to generate coherent and stylistically relevant music. We believe YNote offers a practical alternative to existing music notations for machine learning applications and has the potential to significantly enhance the quality of music generation using LLMs.
Music-to-music-video generation is a challenging task due to the intrinsic differences between the music and video modalities. The advent of powerful text-to-video diffusion models has opened a promising pathway for music-video (MV) generation by first addressing the music-to-MV description task and subsequently leveraging these models for video generation. In this study, we focus on the MV description generation task and propose a comprehensive pipeline encompassing training data construction and multimodal model fine-tuning. We fine-tune existing pre-trained multimodal models on our newly constructed music-to-MV description dataset based on the Music4All dataset, which integrates both musical and visual information. Our experimental results demonstrate that music representations can be effectively mapped to textual domains, enabling the generation of meaningful MV description directly from music inputs. We also identify key components in the dataset construction pipeline that critically impact the quality of MV description and highlight specific musical attributes that warrant greater focus for improved MV description generation.
In the last decade, researchers have increasingly explored using biosensing technologies for music-based affective regulation and stress management interventions in laboratory and real-world settings. These systems -- including interactive music applications, brain-computer interfaces, and biofeedback devices -- aim to provide engaging, personalized experiences that improve therapeutic outcomes. In this scoping and mapping review, we summarize and synthesize systematic reviews and empirical research on biosensing systems with potential applications in music-based affective regulation and stress management, identify gaps in the literature, and highlight promising areas for future research. We identified 28 studies involving 646 participants, with most systems utilizing prerecorded music, wearable cardiorespiratory sensors, or desktop interfaces. We categorize these systems based on their biosensing modalities, music types, computational models for affect or stress detection and music prediction, and biofeedback mechanisms. Our findings highlight the promising potential of these systems and suggest future directions, such as integrating multimodal biosensing, exploring therapeutic mechanisms of music, leveraging generative artificial intelligence for personalized music interventions, and addressing methodological, data privacy, and user control concerns.
When people listen to music, they often experience rich visual imagery. We aim to externalize this inner imagery by generating images conditioned on music. We propose MESA MIG, a multi agent semantic and emotion aligned framework that first produces structured music captions and then refines them with cooperating agents specializing in scene, motion, style, color, and composition. In parallel, a Valence Arousal regression head predicts continuous affective states from music, while a CLIP based visual VA head estimates emotions from images. These components jointly enforce semantic and emotional alignment between music and synthesized images. Experiments on curated music image pairs show that MESA MIG outperforms caption only and single agent baselines in aesthetic quality, semantic consistency, and VA alignment, and achieves competitive emotion regression performance compared with state of the art music and image emotion models.
Takashi Harada, Takehiro Motomitsu, Katsuhiko Hayashi
et al.
In recent years, there has been a notable increase in research on machine learning models for music retrieval and generation systems that are capable of taking natural language sentences as inputs. However, there is a scarcity of large-scale publicly available datasets, consisting of music data and their corresponding natural language descriptions known as music captions. In particular, non-musical information such as suitable situations for listening to a track and the emotions elicited upon listening is crucial for describing music. This type of information is underrepresented in existing music caption datasets due to the challenges associated with extracting it directly from music data. To address this issue, we propose a method for generating music caption data that incorporates non-musical aspects inferred from music thumbnail images, and validated the effectiveness of our approach through human evaluations. Additionally, we created a dataset with approximately 360,000 captions containing non-musical aspects. Leveraging this dataset, we trained a music retrieval model and demonstrated its effectiveness in music retrieval tasks through evaluation.
Music, as an art form, combines rhythm and sound to form a functional melodic structure, uniquely capable of conveying emotions non-verbally. Within the domain of Music Information Retrieval (MIR), Music Emotion Classification (MEC) represents a specialized subset dedicated to the identification and labeling of emotional attributes in songs. This is achieved by extracting and comparing features from musical compositions. This research aims to discern the contemporary landscape of research and its associated research gaps in this domain. The study comprised a collection of publications found through searches conducted on Google Scholar between the years 2006 and 2023, with the search terms: Music Emotion Classification, Music Emotion Classification in Sri Lanka, Music Emotion Recognition, and Emotion Classification in Music. This study was narrowed down to the research that utilized audio files for classification. Among the initial set of 42 studies, 20 were selected for detailed analysis using the purposive sampling method. The review encompassed essential aspects, including acoustic feature analysis, emotional modeling, classification methodologies, and performance evaluation. The findings highlighted a paucity of research considering cultural, regional, and linguistic variations. The most often used acoustic features encompassed rhythm, pitch, timbre, spectral, and harmony whereas the most frequently used emotion categories for the classification were happiness, anger, sadness, and relaxation. Support Vector Machine (SVM) was the most used machine learning algorithm for classification, although regression methods, neural network-based approaches, and fuzzy classifications were also explored. Notably, the adoption of multi-modal approaches for emotion classification, as well as multi-labeled emotion classification, remained limited. These insights underscore the need for future research to address the cultural and language diversity of datasets, explore innovative classification techniques, and embrace multi-modal and multi-labeled emotional classification methodologies in the context of music emotion classification within MIR.
Background: To make a group consensus about non-pharmacological interventions of traditional Chinese medicine in treating polycystic ovary syndrome based on the previous guidelines, literature, and expert viewpoints. Methods: Organized by Chinese Integrative Medicine & Traditional Chinese Medicine Academy, Chinese Maternal and Child Health Association, China, 29 experts from 18 Chinese provinces and 2 international experts, who specialize in gynecology, obstetrics, pediatrics, endocrinology, cardiovascular, psychology, reproductive genetics, nursing, acupuncture and tuina, traditional Chinese medicine, integrative medicine, and other disciplines, discussed and revised the recommendations one by one through in-person or online communication. Each recommendation was approved by ≥90% of the experts before it could be established. The main outcome measure is an optimal clinical regimen for addressing the requirements of women with PCOS and improving their quality of life. Result(s): The writing panel drafted the initial report, following a consensus process via adequate communication, which was then reviewed and revised by the consensus panel. This consensus provides 12 non-pharmacological interventions (including acupuncture, thumbtack needle, thread-embedding therapy, TEAS, AA, acupoint hot compress, cupping, acupressure, moxibustion, five elements music, aromatherapy, traditional Chinese exercises) for 8 phenotypes of PCOS, resulting in 34 items of clinical practice recommendations. Conclusion(s): The consensus provides 12 non-pharmacological interventions of traditional Chinese medicine for 8 phenotypes of PCOS, resulting in 34 items of clinical practice recommendations, which may be improved by more high-quality multicenter clinical trials.
Ecstasy is a state of altered consciousness in which a person is in a state of trance. The person in this state experiences an introspection and returns to their essence. Such a state can also be likened to being asleep or hypnotized. But more than these states, ecstasy refers to a conventionalized state of unusualness. In other words, ecstasy can occur in societies and these moods of ecstasy can change. Therefore, ecstasy continues to exist not only in the past but also in the present. In this regard, ecstasy appears as a universal word with different meanings and different nomenclatures from culture to culture. Containing different meanings and different nomenclature, ecstasy is generally associated with music. In fact, music acts as an intermediary in the transition to the state of ecstasy. This situation allows us to speak of a relationship between ecstasy and music. Cultural differences are decisive in this relationship. The relationship between music and ecstasy is also seen in the sema ceremony and semah ceremonies, which are at the center of the subject. In this direction, sema and semah, which are used in two different ways, contain the same meaning; however, these words differ from each other in terms of application. In other words, sema is performed in Mevlevi rituals and semah is performed in Alevi erkans/rituals accompanied by music. The Mevlevi sema ceremony can be visualized as a state of ecstasy in which music and kinetic movements are together. In the sema ceremony performed for the purpose of returning to one’s essence with this state of ecstasy, music and kinetic movements contribute to the occurrence of ecstasy. In this context, music and kinetic movements can be considered as a kind of mediating elements for ecstasy. In the Mevlevi sema ceremony, the human ascension is described with both music and kinetic movements through the performance of na’t, kudüm, ney, peşrev and ayin-i şerif. The climax of the ecstasy in this ceremony is the third salute. This is why the tempo of the music, and the movements of the whirling dervishes accelerate in this salute. In addition, in the aforementioned ceremony, ney and kudüm instruments can also be mentioned as instrumental elements in the experience of ecstasy. There is a similar situation in Alevi semah ceremonies. Semah ceremonies, like sema ceremonies, can be described as a state of ecstasy. In this state of ecstasy, the person returns to his/her soul, that is, to Allah. Semah, which is performed as a part of Miraçlama in cem erkans, is performed in two or three parts with the help of music and kinetic elements. The fact that the semahs are performed in two or three parts, namely, hospitality and swaying, or hospitality, execution and swaying, indicates that the semah is directed towards ecstasy. In this sense, the kinetic movements performed in the sections of the semah accompanied by music move from slow to fast. Thus, just like in sema, the music and kinetic movements in semah mediate ecstasy by enabling the transition to a state of ecstasy. Apart from this, it is seen that the ney and kudüm instruments mediate the experience of ecstasy in sema ceremonies, as well as the baglama in semah ceremonies. In this context, it is possible to say that music, musical elements and kinetic movements are the mediators of the state of ecstasy and the state of motion experienced with ecstasy in sema ceremonies and semah ceremonies. In this context, when the literature is examined, it is realized that there are various studies on Mevlevi sema rituals and Alevi semah rituals; however, there is no study that deals with ecstasy and its elements in sema and semah rituals. In this regard, the study is important in terms of filling the gap in the field and being a source for similar studies. In this manner, the research aims to reveal the state of ecstasy in sema ceremonies and semah ceremonies. In line with this purpose, a documentary research method with a descriptive model was used in the research, the sources related to the subject were examined and the findings were revealed by interpreting the data obtained.
Hsin-Cheng Wu, Wu-Der Jeng, Long-Sheng Chen
et al.
In the transition from television to mobile devices, short videos have emerged as the primary content format, possessing tremendous potential in various fields such as marketing, promotion, education, advertising, and so on. However, from the available literature, there is a lack of studies investigating the elements necessary for the success of short videos, specifically regarding what factors need to be considered during production to increase viewership. Therefore, this study proposed the NLP-QFD model, integrating Natural Language Processing (NLP), Latent Dirichlet Allocation (LDA), and Quality Function Deployment (QFD) methods. Real short videos from mainstream Western media (CNN) and regional media (Middle East Eye) will be employed as case studies. In addition to analyzing the content of short videos and audiences’ reviews, we will utilize the NLP-QFD model to identify the key success factors (KSFs) of short videos, providing guidance for future short video creators, especially for small-scale businesses, to produce successful short videos and expand their influence through social media. The results indicate that the success factors for short videos include the movie title, promotion, reviews, and social media. For large enterprises, endorsements by famous individuals are crucial, while music and shooting are key elements for the success of short videos for small businesses.