This review examines the new edition of what is Palestrina’s only authentic Requiem Mass, together with the Responsory sung with it as part of the liturgy in Rome’s Cappella Giulia. The edition includes a large-scale study of both Palestrina’s compositional technique as well as a detailed study of the other Roman Requiem repertory that he could have known.
This monograph introduces a novel approach to polyphonic music generation by addressing the "Missing Middle" problem through structural inductive bias. Focusing on Beethoven's piano sonatas as a case study, we empirically verify the independence of pitch and hand attributes using normalized mutual information (NMI=0.167) and propose the Smart Embedding architecture, achieving a 48.30% reduction in parameters. We provide rigorous mathematical proofs using information theory (negligible loss bounded at 0.153 bits), Rademacher complexity (28.09% tighter generalization bound), and category theory to demonstrate improved stability and generalization. Empirical results show a 9.47% reduction in validation loss, confirmed by SVD analysis and an expert listening study (N=53). This dual theoretical and applied framework bridges gaps in AI music generation, offering verifiable insights for mathematically grounded deep learning.
Ioannis Prokopiou, Ioannis Sina, Agisilaos Kounelis
et al.
The advancement of Machine learning (ML), Large Audio Language Models (LALMs), and autonomous AI agents in Music Information Retrieval (MIR) necessitates a shift from static tagging to rich, human-aligned representation learning. However, the scarcity of open-source infrastructure capable of capturing the subjective nuances of audio annotation remains a critical bottleneck. This paper introduces \textbf{LabelBuddy}, an open-source collaborative auto-tagging audio annotation tool designed to bridge the gap between human intent and machine understanding. Unlike static tools, it decouples the interface from inference via containerized backends, allowing users to plug in custom models for AI-assisted pre-annotation. We describe the system architecture, which supports multi-user consensus, containerized model isolation, and a roadmap for extending agents and LALMs. Code available at https://github.com/GiannisProkopiou/gsoc2022-Label-buddy.
Benno Weck, Pablo Puentes, Andrea Poltronieri
et al.
The evaluation of music understanding in Large Audio-Language Models (LALMs) requires a rigorously defined benchmark that truly tests whether models can perceive and interpret music, a standard that current data methodologies frequently fail to meet. This paper introduces a meticulously structured approach to music evaluation, proposing a new dataset of 320 hand-written questions curated and validated by experts with musical training, arguing that such focused, manual curation is superior for probing complex audio comprehension. To demonstrate the use of the dataset, we benchmark six state-of-the-art LALMs and additionally test their robustness to uni-modal shortcuts.
Laura Marqués-Martínez, Jorge Andrés, Esther García-Miralles
et al.
<b>Background:</b> Dental anxiety is a common challenge in paediatric dentistry, often leading to avoidance of treatment and compromised oral health. Non-pharmacological interventions such as music therapy have gained increasing attention as safe and cost-effective alternatives to pharmacological approaches. Although several clinical studies have examined the impact of music on children’s dental anxiety, the evidence has not yet been systematically summarised with quantitative synthesis. <b>Objective:</b> This systematic review and meta-analysis aimed to evaluate the effectiveness of music therapy in reducing dental anxiety and fear among paediatric patients. <b>Methods</b>: A comprehensive literature search was conducted in PubMed, Scopus, Web of Science, and Cochrane Library from inception to August 2025. Randomised controlled trials (RCTs) evaluating music therapy for dental anxiety in children were included. Primary outcomes were self-reported dental anxiety/fear scales and physiological measures (heart rate, blood pressure, oxygen saturation). Risk of bias was assessed using the revised Cochrane risk of bias tool (RoB 2, version 2019; Cochrane Collaboration, London, UK) Meta-analyses were performed using a random-effects model with Review Manager (RevMan, version 5.4; Cochrane Collaboration, London, UK). <b>Results:</b> Seven randomized controlled trials (RCTs) involving 476 children aged 4–14 years were included. Music therapy significantly reduced self-re-ported dental anxiety compared with control groups (SMD = −0.48, 95% CI: −0.72 to −0.25, <i>p</i> < 0.001). Heart rate was also significantly reduced (SMD = −0.42, 95% CI: −0.68 to −0.16, <i>p</i> = 0.002), whereas changes in blood pressure and oxygen saturation were not statistically significant. The overall risk of bias was moderate, with most concerns related to blinding. <b>Conclusions:</b> Music therapy is an effective non-pharmacological intervention to reduce dental anxiety in children, particularly improving subjective anxiety and physiological arousal as measured by heart rate. Its integration into paediatric dental practice may enhance cooperation and treatment outcomes, offering a safe, inexpensive, and child-friendly approach.
Marc Niering, Benedikt Zirkel, Paul Munkelt
et al.
Abstract Objective This meta-analysis examined the effects of preferred music listening (PML) versus non-preferred music listening (NPML) and no music listening (NML) on psychological and physical performance outcomes in adolescent and adult athletes. Methods A systematic literature search was conducted in Embase, PubMed, PsycInfo, and MEDLINE. After screening 3146 records and applying predefined eligibility criteria, 41 studies were included in the meta-analysis. Data were synthesized for psychological parameters (perceived exertion, motivation, affective response) and physical parameters (strength endurance, power output, maximal strength, aerobic endurance, speed). Meta-regression analyses were performed to identify potential moderating effects of age, sex, music choice, and timing. Results Statistically significant overall effects favoring PML were found for psychological outcomes, including a reduction in perceived exertion (SMD = − 0.36, 95% CI [− 0.65, − 0.08]), an increase in motivation (SMD = 0.85, 95% CI [0.60, 1.10]), and a more positive affective response (SMD = 1.16, 95% CI [0.13, 2.20]). For physical outcomes, significant between-condition differences were observed for strength endurance (SMD = 0.72, 95% CI [0.42, 1.01]), maximal strength (SMD = 0.53, 95% CI [0.20, 0.85]), and power output (SMD = 0.47, 95% CI [0.12, 0.81]), however subgroup comparisons with NPML were less consistent due to high heterogeneity. NPML showed slightly higher values than NML in some psychological and physical parameters, while no advantage was observed for speed or aerobic endurance. Conclusion PML was associated with higher motivation, more positive affective responses, lower perceived exertion, and superior strength- and power-related performance compared to non-preferred and no music conditions. These findings reflect between-condition comparisons and emphasize the importance of individual preference in optimizing exercise experiences. Trial registration PROSPERO registration number: CRD420251083551.
Music is a powerful medium for influencing listeners' emotional states, and this capacity has driven a surge of research interest in AI-based affective music generation in recent years. Many existing systems, however, are a black box which are not directly controllable, thus making these systems less flexible and adaptive to users. We present \textit{AffectMachine-Pop}, an expert system capable of generating retro-pop music according to arousal and valence values, which can either be pre-determined or based on a listener's real-time emotion states. To validate the efficacy of the system, we conducted a listening study demonstrating that AffectMachine-Pop is capable of generating affective music at target levels of arousal and valence. The system is tailored for use either as a tool for generating interactive affective music based on user input, or for incorporation into biofeedback or neurofeedback systems to assist users with emotion self-regulation.
Binaural audio remains underexplored within the music information retrieval community. Motivated by the rising popularity of virtual and augmented reality experiences as well as potential applications to accessibility, we investigate how well existing music source separation (MSS) models perform on binaural audio. Although these models process two-channel inputs, it is unclear how effectively they retain spatial information. In this work, we evaluate how several popular MSS models preserve spatial information on both standard stereo and novel binaural datasets. Our binaural data is synthesized using stems from MUSDB18-HQ and open-source head-related transfer functions by positioning instrument sources randomly along the horizontal plane. We then assess the spatial quality of the separated stems using signal processing and interaural cue-based metrics. Our results show that stereo MSS models fail to preserve the spatial information critical for maintaining the immersive quality of binaural audio, and that the degradation depends on model architecture as well as the target instrument. Finally, we highlight valuable opportunities for future work at the intersection of MSS and immersive audio.
Francisco Zmekhol Nascimento de Oliveira, Max Packer
Em publicação recente, apresentamos um procedimento analítico destinado ao reconhecimento e à evidenciação de relações tonais-funcionais (tanto locais como de larga escala) latentes em obras geralmente tidas como pós-tonais, ou limítrofes de uma tonalidade expandida. Fundado poética e metodologicamente sobre a prática do comentário composicional – noção que tem origem na obra de Luciano Berio e que temos desenvolvido em trabalhos anteriores –, tal procedimento consiste, basicamente, em acrescentar à obra analisada (de resto intacta) uma linha melódica que opere, em cada formação harmônica dissonante, preparações e resoluções que busquem demonstrar como tal formação poderia ter ocorrido ainda no seio de uma tonalidade pré-1908 (i. e., anterior a uma emancipação generalizada da dissonância). Assumindo que, de uma perspectiva tonal-funcional, o repertório de interesse de nossa abordagem seja inerentemente ambíguo e tendo já anteriormente reconhecido que as interpretações ressaltadas por nossas linhas acrescentadas não são nem podem ser unívocas, objetivamos, no presente trabalho, explorar diferentes maneiras como possamos assimilar nos próprios comentários composicionais por nós produzidos – e não apenas em um plano verbal e hipotético – as ambiguidades que reconheçamos ao longo do processo analítico. Para tanto, tomamos aqui por objeto de análise a pequena peça para piano intitulada Masque, Op. 63/1 (1912) de Scriabin, a qual em boa medida se estrutura a partir de um jogo de ambiguidades harmônicas. No comentário que produzimos sobre a obra em questão, integralmente reproduzido ao fim do artigo, nós não apenas evidenciamos relações funcionais locais e de larga escala latentes em Masque, como, cumprindo com nosso objetivo, demonstramos ao menos cinco diferentes maneiras como nosso procedimento analítico pode contemplar e trazer à tona ambiguidades harmônicas das peças sobre as quais nos debruçamos.
This review examines the transformative impact creativity has on mental health. Creative expression has the potential to promote the cognitive, emotional, physical, and social well-being of individuals of all ages. Drawing from various scholarly sources, including empirical studies and theoretical frameworks, this review synthesizes the current knowledge on the relationship between creativity and mental health. The review elucidates how creativity influences emotional regulation, cognitive flexibility, and social connectedness. Through a detailed literature search utilizing databases such as PubMed, PsycINFO, PsychARTICLES, and Google Scholar, research findings from articles across different creative activities, including visual arts, writing, music, and crafts/DIY projects, are discussed in conjunction with reported benefits on mental health and well-being. Furthermore, the review discusses the practical implications of the positive link between creative expression and mental health, emphasizing the relevance of this for therapeutic interventions and community programs. The findings highlight the need for further research to explore the underlying mechanisms, long-term effects, and potential cultural variations of the creativity-mental health relationship. This review provides a comprehensive overview of the positive influences, inviting researchers, practitioners, and policymakers to harness the healing power of creative expression.
Despite significant recent progress across multiple subtasks of audio source separation, few music source separation systems support separation beyond the four-stem vocals, drums, bass, and other (VDBO) setup. Of the very few current systems that support source separation beyond this setup, most continue to rely on an inflexible decoder setup that can only support a fixed pre-defined set of stems. Increasing stem support in these inflexible systems correspondingly requires increasing computational complexity, rendering extensions of these systems computationally infeasible for long-tail instruments. In this work, we propose Banquet, a system that allows source separation of multiple stems using just one decoder. A bandsplit source separation model is extended to work in a query-based setup in tandem with a music instrument recognition PaSST model. On the MoisesDB dataset, Banquet, at only 24.9 M trainable parameters, approached the performance level of the significantly more complex 6-stem Hybrid Transformer Demucs on VDBO stems and outperformed it on guitar and piano. The query-based setup allows for the separation of narrow instrument classes such as clean acoustic guitars, and can be successfully applied to the extraction of less common stems such as reeds and organs. Implementation is available at https://github.com/kwatcharasupat/query-bandit.
This paper presents an innovative exploration into the integration of interactive robotic musicianship within a commercial retail environment, specifically through a three-week-long in-store installation featuring a UR3 robotic arm, custom-built frame drums, and an adaptive music generation system. Situated in a prominent storefront in one of the world's largest cities, this project aimed to enhance the shopping experience by creating dynamic, engaging musical interactions that respond to the store's ambient soundscape. Key contributions include the novel application of industrial robotics in artistic expression, the deployment of interactive music to enrich retail ambiance, and the demonstration of continuous robotic operation in a public setting over an extended period. Challenges such as system reliability, variation in musical output, safety in interactive contexts, and brand alignment were addressed to ensure the installation's success. The project not only showcased the technical feasibility and artistic potential of robotic musicianship in retail spaces but also offered insights into the practical implications of such integration, including system reliability, the dynamics of human-robot interaction, and the impact on store operations. This exploration opens new avenues for enhancing consumer retail experiences through the intersection of technology, music, and interactive art, suggesting a future where robotic musicianship contributes meaningfully to public and commercial spaces.
Entre los elementos musicales más característicos del flamenco se encuentra el modo frigio, máximo responsable a nivel auditivo del carácter exótico que se suele atribuir al género. Este modo, en algunas publicaciones puntuales, pero muy influyentes desde la segunda mitad del siglo XX, fue re-bautizado como “modo dórico” o “modo dórico flamenco”. El presente articulo pretende arrojar luz sobre las referencias de esta re-interpretación en fuentes de la Antigüedad clásica, donde se encuentran las raíces de la relación entre la estructura musical y el uso terminológico. Mediante un análisis de carácter semiótico se esbozará un conjunto de denotaciones y connotaciones que reflejan dicotomías fundamentales en la construcción de identidades occidentales y orientales. Estas dicotomías se encuentran también en la creación de un imaginario español y, por extensión, del flamenco desde la segunda mitad del siglo XVIII. Desde las primeras consideraciones del flamenco por parte de la intelectualidad española a finales del siglo XIX, se aprecia una voluntad de relativizar sus asociaciones incómodas y enfatizar sus aspectos tradicionales, artísticos y especialmente históricos. Éstas, a su vez, servían de fundamento para que una parte de la flamencología realizase la descrita re-interpretación del modo frigio como dórico. Finalmente se situará la re-interpretación en su contexto ideológico de la segunda mitad del siglo XX, con respecto tanto a la estética flamenca como al trasfondo histórico-político.
Palabras clave: flamenco, frigio, dórico, semiótica, ideología
Abstract
The Phrygian mode appears amongst flamenco’s most characteristic musical elements, responsible for the exotic character often attributed to the genre. This mode was re-named “Dorian mode” or “Dorian flamenco mode” in some of the most influential publications since the second half of the 20th century. The present article pretends to shed some light on the references of this re-interpretation in the classical Antiquity, where the roots of the link between musical structure and terminology can be found. By means of a semiotical analysis, a sketch of a group of connotations and denotations will be made which reflect fundamental dichotomies for the construction of Western and Eastern identities. These dichotomies can also be found in the creation of a Spanish and, by extension, flamenco imagery since the second half of the 18th century. Beginning at flamenco’s first mention by Spanish intellectuals at the end of the 19th century, a will to play down embarrassing associations and emphasize traditional, artistic and especially historical aspects can be observed. These, in turn, served a part of modern flamencology as a basis for the above described re-interpretation of the Phrygian mode as Dorian. Finally, the resulting discourse is explained in the ideological context of the second half of the 20th century, with respect to flamenco aesthetics as well as the historical-political background.
Keywords: flamenco, Phrygian, Dorian, semiotics, ideology
Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks. With the push to acquire larger datasets to improve MSS performance, the inevitability of encountering mislabeled individual instrument tracks becomes a significant challenge to address. This paper introduces an automated technique for refining the labels in a partially mislabeled dataset. Our proposed self-refining technique, employed with a noisy-labeled dataset, results in only a 1% accuracy degradation in multi-label instrument recognition compared to a classifier trained on a clean-labeled dataset. The study demonstrates the importance of refining noisy-labeled data in MSS model training and shows that utilizing the refined dataset leads to comparable results derived from a clean-labeled dataset. Notably, upon only access to a noisy dataset, MSS models trained on a self-refined dataset even outperform those trained on a dataset refined with a classifier trained on clean labels.
A long tradition of research including classical rhetoric, esthetics and poetics theory, formalism and structuralism, as well as current perspectives in (neuro)cognitive poetics has investigated structural and functional aspects of literature reception. Despite a wealth of literature published in specialized journals like Poetics, however, still little is known about how the brain processes and creates literary and poetic texts. Still, such stimulus material might be suited better than other genres for demonstrating the complexities with which our brain constructs the world in and around us, because it unifies thought and language, music and imagery in a clear, manageable way, most often with play, pleasure, and emotion (Schrott and Jacobs, 2011). In this paper, I discuss methods and models for investigating the neuronal and cognitive-affective bases of literary reading together with pertinent results from studies on poetics, text processing, emotion, or neuroaesthetics, and outline current challenges and future perspectives.
The focus of this mini-review is on rhythm objects, defined as strongly coherent chunks of combined sound and body motion in music, typically in the duration range of a few seconds, as may for instance be found in a fragment of dance music, in an energetic drum fill, in a flute ornament, or in a cascade of sounds of a rapid harp glissando. Although there has been much research on rhythm in continuous musical sound and its links with behavior, including the neurocognitive aspects of periodicity, synchrony, and entrainment, there has been much less focus on the generation and perception of singular coherent rhythm objects. This mini-review aims to enhance our understanding of such rhythm objects by pointing to relevant literature on coherence-enhancing elements such as coarticulation, i.e., the fusion of motion events into more extended rhythm objects, and intermittent motor control, i.e., the discontinuous, instant-by-instant control and triggering of rhythm objects.
With increasing amounts of music being digitally transferred from production to distribution, automatic means of determining media quality are needed. Protection mechanisms in digital audio processing tools have not eliminated the need of production entities located downstream the distribution chain to assess audio quality and detect defects inserted further upstream. Such analysis often relies on the received audio and scarce meta-data alone. Deliberate use of artefacts such as clicks in popular music as well as more recent defects stemming from corruption in modern audio encodings call for data-centric and context sensitive solutions for detection. We present a convolutional network architecture following end-to-end encoder decoder configuration to develop detectors for two exemplary audio defects. A click detector is trained and compared to a traditional signal processing method, with a discussion on context sensitivity. Additional post-processing is used for data augmentation and workflow simulation. The ability of our models to capture variance is explored in a detector for artefacts from decompression of corrupted MP3 compressed audio. For both tasks we describe the synthetic generation of artefacts for controlled detector training and evaluation. We evaluate our detectors on the large open-source Free Music Archive (FMA) and genre-specific datasets.