Hasil untuk "Music"

Claudia Scheimbauer

This lecture covers several basic methods for standard tasks in data analysis and image processing. A non-exclusive and non-exhaustive list of meth-ods: histograms, dimension reduction, clustering, filters, frequency analysis, morphological methods. . . We will develop the mathematical theory that underlies these methods which is the basis for thorough understanding and proper execution of the method. Moreover, we will deal with the practical implementation of the methods and apply them to solve problems such as image denoising, image deblurring, or music identification. This lecture should enable you to take a deeper dive into image and data analysis and prepares you to follow recent developments in the field. If you want to understand the inner working of image compression with JPEG or music recognition with tools like Shazam, come to this lecture!

P. Lauren

performance of her original music at Sant’Ignazio Basilica in Rome. In the same year her passage “Cammini” was programmed at the F.I.M. Fiera Internazionale della Musica in Erba (Como) (International Music Exhibition). From 2015 she has been Director of the Coro P.A.C.A.O Choir belonging to the Primaria Associazione Artistica Operaia; from 2012 Director of the Ensemble e Corale Laurentum San Romualdo Abate. In addition to her activities as a concert performer, composer and conductor, for over 20 years she has been teaching music, she is the Artistic and Musical Director of cultural associations, choirs and music academies in Rome. The PWA is a non-profit networking organization that supports and promotes the interests of professional women of different nationalities, from diverse cultural environments. We believe in sharing information, ideas and resources to create mutual opportunities and since 1992 PWA provides a “friendly forum” for women who want to expand their world for personal and professional growth. We welcome women from various professions at different levels and from different sectors. We meet on the 1st Wednesday of the month (Sep-tember-June) for cocktails dedicated to networking and on 3rd Wednesday for conferences conducted by international speakers. In addition, we carry out seminars on women’s empowerment, and organize events of cultural interest and social development.

K. Rayner

Upendra Shardanand, P. Maes

Matteo Pettenó, Alessandro Ilic Mezza, Alberto Bernardini

Recent advances in latent diffusion models have demonstrated state-of-the-art performance in high-dimensional time-series data synthesis while providing flexible control through conditioning and guidance. However, existing methodologies primarily rely on musical context or natural language as the main modality of interacting with the generative process, which may not be ideal for expert users who seek precise fader-like control over specific musical attributes. In this work, we explore the application of denoising diffusion processes as plug-and-play latent constraints for unconditional symbolic music generation models. We focus on a framework that leverages a library of small conditional diffusion models operating as implicit probabilistic priors on the latents of a frozen unconditional backbone. While previous studies have explored domain-specific use cases, this work, to the best of our knowledge, is the first to demonstrate the versatility of such an approach across a diverse array of musical attributes, such as note density, pitch range, contour, and rhythm complexity. Our experiments show that diffusion-driven constraints outperform traditional attribute regularization and other latent constraints architectures, achieving significantly stronger correlations between target and generated attributes while maintaining high perceptual quality and diversity.

Chen-Gia Tsai, Chia-Wei Li

Groove sensations arise from rhythmic structures that evoke an urge to move in response to music. While syncopation has been extensively studied in groove perception, the neural mechanisms underlying low-frequency groove remain underexplored. This fMRI study examines the role of the mirror neuron system and associated brain regions in processing low-frequency groove. Region-of-interest analysis revealed that amplifying drum and bass components in K-pop songs significantly increased activity in the right posterior inferior frontal gyrus, right inferior/superior parietal lobules, left dorsolateral prefrontal cortex, and bilateral posterior middle/inferior temporal gyrus. These findings suggest that low-frequency grooves engage sensorimotor, executive, and rhythm semantics networks, reinforcing their role in action-related processing. Building on these insights, we propose an enhanced rhythmic auditory stimulation paradigm for Parkinson's disease, incorporating amplified low-frequency rhythmic cues to improve gait synchronization.

Katharina Hoedt, Arthur Flexer, Gerhard Widmer

One of the desired key properties of deep learning models is the ability to generalise to unseen samples. When provided with new samples that are (perceptually) similar to one or more training samples, deep learning models are expected to produce correspondingly similar outputs. Models that succeed in predicting similar outputs for similar inputs are often called robust. Deep learning models, on the other hand, have been shown to be highly vulnerable to minor (adversarial) perturbations of the input, which manage to drastically change a model's output and simultaneously expose its reliance on spurious correlations. In this work, we investigate whether inherently interpretable deep models, i.e., deep models that were designed to focus more on meaningful and interpretable features, are more robust to irrelevant perturbations in the data, compared to their black-box counterparts. We test our hypothesis by comparing the robustness of an interpretable and a black-box music emotion recognition (MER) model when challenged with adversarial examples. Furthermore, we include an adversarially trained model, which is optimised to be more robust, in the comparison. Our results indicate that inherently more interpretable models can indeed be more robust than their black-box counterparts, and achieve similar levels of robustness as adversarially trained models, at lower computational cost.

A. Suprun-Zhyvodrova

У статті проаналізовано особливості часопросторової організації українського аудіовізуального наративу доби Незалежності. Розмежовано поняття «історії» (дієгезису) як послідовності подій і «сюжету» як драматургічної та темпоральної структури твору. Визначено основні часові категорії наративу й класифіковано їх. Розглянуто роль невербальних засобів — монтажу, звуку, кольору — у позначенні часових переходів. Установлено, що для українського аудіовізуального мистецтва характерна лінійна структура з флешбеками, пов’язаними з теперішнім, тоді як пролепсиси трапляються переважно у фантастичних творах. Уперше здійснено системний аналіз часової організації українського аудіовізуального наративу з позицій сучасної наратології, запропоновано типологію часових зсувів і засобів їхнього вираження, що виявляє зв’язок між структурою оповіді та національно-культурними особливостями кінематографу.

Oluseun Sunday Odusanya, Zacchaeus Adelere Adesokan, Damaris T’Oluwalope Aremu et al.

The paper addresses women's participation in church choral ministries, focusing on women as conductors. Despite the growing recognition of women leaders, women's involvement in music ministries is often challenged by gender- and tradition-based barriers. The study examines how women overcome these barriers, shape worship styles, and enrich the church's spiritual and musical life. This study employs a qualitative research method, utilising in-depth interviews with 15 women choral conductors, surveys of 30 church music directors across various denominations, and a critical analysis of historical and contemporary literature. Thematic analysis was used to interpret qualitative data, identifying key themes related to gender dynamics, leadership experiences, and musical influence within church settings. The research is guided by feminist theory, as outlined by Hooks (2000), and ecclesiological theory proposed by Johnson (2015). The paper outlines how women have shaped worship experiences and congregations' spiritual and artistic identity through historical examples, personal narratives, and contemporary practice. By juxtaposing their leadership within the discourses of religion and art, this article pays tribute to women conductors who employ their batons to glorify God and inspire others in the sacred domain of church ministries. The paper concludes that to tap the full potential of women in church music, there needs to be a deconstruction of the gendered barriers that continue to constrain their leadership opportunities. Churches must proactively offer mentorship, professional training, and equal leadership roles for women. Future research should explore the impact of cultural and denominational variations on women's leadership equality in church music, investigate the long-term career trajectories of women conductors, and examine the role of theological education in shaping gender-inclusive music ministries.

Michael Buehlmann, Lukas Winkler, Oliver Hahn et al.

We present the online service cosmICweb (**COSM**ological **I**nitial **C**onditions on the **WEB**) - the first database and web interface to store, analyze, and disseminate initial conditions for zoom simulations of objects forming in cosmological simulations: from galaxy clusters to galaxies and more. Specifically, we store compressed information about the Lagrangian proto-halo patches for all objects in a typical simulation merger tree along with properties of the halo/galaxy across cosmic time. This enables a convenient web-based selection of the desired zoom region for an object fitting user-specified selection criteria. The information about the region can then be used with the MUSIC code to generate the zoom ICs for the simulation. In addition to some other simulations, we currently support all objects in the EAGLE simulation database, so that for example the Auriga simulations are easily reproduced, which we demonstrate explicitly. The framework is extensible to include other simulations through an API that can be added to an existing database structure and with which cosmICweb can then be interfaced. We make the web portal and database publicly available to the community.

P. Stoica, A. Nehorai

K. Bruscia

Shahan Nercessian, Johannes Imort, Ninon Devis et al.

In this paper, we propose and investigate the use of neural audio codec language models for the automatic generation of sample-based musical instruments based on text or reference audio prompts. Our approach extends a generative audio framework to condition on pitch across an 88-key spectrum, velocity, and a combined text/audio embedding. We identify maintaining timbral consistency within the generated instruments as a major challenge. To tackle this issue, we introduce three distinct conditioning schemes. We analyze our methods through objective metrics and human listening tests, demonstrating that our approach can produce compelling musical instruments. Specifically, we introduce a new objective metric to evaluate the timbral consistency of the generated instruments and adapt the average Contrastive Language-Audio Pretraining (CLAP) score for the text-to-instrument case, noting that its naive application is unsuitable for assessing this task. Our findings reveal a complex interplay between timbral consistency, the quality of generated samples, and their correspondence to the input prompt.

Yifu Sun, Xulong Zhang, Monan Zhou et al.

Music emotion recognition (MER) aims to identify the emotions conveyed in a given musical piece. However, currently, in the field of MER, the available public datasets have limited sample sizes. Recently, segment-based methods for emotion-related tasks have been proposed, which train backbone networks on shorter segments instead of entire audio clips, thereby naturally augmenting training samples without requiring additional resources. Then, the predicted segment-level results are aggregated to obtain the entire song prediction. The most commonly used method is that the segment inherits the label of the clip containing it, but music emotion is not constant during the whole clip. Doing so will introduce label noise and make the training easy to overfit. To handle the noisy label issue, we propose a semi-supervised self-learning (SSSL) method, which can differentiate between samples with correct and incorrect labels in a self-learning manner, thus effectively utilizing the augmented segment-level data. Experiments on three public emotional datasets demonstrate that the proposed method can achieve better or comparable performance.

Kyle Robinson, Dan Brown

Running live music recommendation studies without direct industry partnerships can be a prohibitively daunting task, especially for small teams. In order to help future researchers interested in such evaluations, we present a number of struggles we faced in the process of generating our own such evaluation system alongside potential solutions. These problems span the topics of users, data, computation, and application architecture.

Silvan David Peter

Symbolic Music Alignment is the process of matching performed MIDI notes to corresponding score notes. In this paper, we introduce a reinforcement learning (RL)-based online symbolic music alignment technique. The RL agent - an attention-based neural network - iteratively estimates the current score position from local score and performance contexts. For this symbolic alignment task, environment states can be sampled exhaustively and the reward is dense, rendering a formulation as a simplified offline RL problem straightforward. We evaluate the trained agent in three ways. First, in its capacity to identify correct score positions for sampled test contexts; second, as the core technique of a complete algorithm for symbolic online note-wise alignment; and finally, as a real-time symbolic score follower. We further investigate the pitch-based score and performance representations used as the agent's inputs. To this end, we develop a second model, a two-step Dynamic Time Warping (DTW)-based offline alignment algorithm leveraging the same input representation. The proposed model outperforms a state-of-the-art reference model of offline symbolic music alignment.

Sara Adkins, Pedro Sarmento, Mathieu Barthet

Despite their impressive offline results, deep learning models for symbolic music generation are not widely used in live performances due to a deficit of musically meaningful control parameters and a lack of structured musical form in their outputs. To address these issues we introduce LooperGP, a method for steering a Transformer-XL model towards generating loopable musical phrases of a specified number of bars and time signature, enabling a tool for live coding performances. We show that by training LooperGP on a dataset of 93,681 musical loops extracted from the DadaGP dataset, we are able to steer its generative output towards generating 3x as many loopable phrases as our baseline. In a subjective listening test conducted by 31 participants, LooperGP loops achieved positive median ratings in originality, musical coherence and loop smoothness, demonstrating its potential as a performance tool.

S. Frith

Axel Marmoret, Jérémy E. Cohen, Frédéric Bimbot

Music Structure Analysis (MSA) consists in segmenting a music piece in several distinct sections. We approach MSA within a compression framework, under the hypothesis that the structure is more easily revealed by a simplified representation of the original content of the song. More specifically, under the hypothesis that MSA is correlated with similarities occurring at the bar scale, this article introduces the use of linear and non-linear compression schemes on barwise audio signals. Compressed representations capture the most salient components of the different bars in the song and are then used to infer the song structure using a dynamic programming algorithm. This work explores both low-rank approximation models such as Principal Component Analysis or Nonnegative Matrix Factorization and "piece-specific" Auto-Encoding Neural Networks, with the objective to learn latent representations specific to a given song. Such approaches do not rely on supervision nor annotations, which are well-known to be tedious to collect and possibly ambiguous in MSA description. In our experiments, several unsupervised compression schemes achieve a level of performance comparable to that of state-of-the-art supervised methods (for 3s tolerance) on the RWC-Pop dataset, showcasing the importance of the barwise compression processing for MSA.

Geoffroy Peeters, Florian Angulo

In this paper, we propose a new paradigm to learn audio features for Music Structure Analysis (MSA). We train a deep encoder to learn features such that the Self-Similarity-Matrix (SSM) resulting from those approximates a ground-truth SSM. This is done by minimizing a loss between both SSMs. Since this loss is differentiable w.r.t. its input features we can train the encoder in a straightforward way. We successfully demonstrate the use of this training paradigm using the Area Under the Curve ROC (AUC) on the RWC-Pop dataset.