Hasil untuk "Music"

Daniel Müllensiefen, B. Gingras, J. Musil et al.

Musical skills and expertise vary greatly in Western societies. Individuals can differ in their repertoire of musical behaviours as well as in the level of skill they display for any single musical behaviour. The types of musical behaviours we refer to here are broad, ranging from performance on an instrument and listening expertise, to the ability to employ music in functional settings or to communicate about music. In this paper, we first describe the concept of ‘musical sophistication’ which can be used to describe the multi-faceted nature of musical expertise. Next, we develop a novel measurement instrument, the Goldsmiths Musical Sophistication Index (Gold-MSI) to assess self-reported musical skills and behaviours on multiple dimensions in the general population using a large Internet sample (n = 147,636). Thirdly, we report results from several lab studies, demonstrating that the Gold-MSI possesses good psychometric properties, and that self-reported musical sophistication is associated with performance on two listening tasks. Finally, we identify occupation, occupational status, age, gender, and wealth as the main socio-demographic factors associated with musical sophistication. Results are discussed in terms of theoretical accounts of implicit and statistical music learning and with regard to social conditions of sophisticated musical engagement.

Thierry Bertin-Mahieux, D. Ellis, B. Whitman et al.

Derek Bailey

R. E. Milliman

Dvorovenko Olga

Children’s art schools use virtual accounts to promote their activities, teachers’ achievements, curriculum, services, and events. The author studied twelve accounts of children’s art schools located in the Irkutsk Region to evaluate the advertising options that virtual space offers to this category of education establishments. The research covered publications made in VKontakte social network between September 18 and October 18, 2024. It revealed a set of statistical indicators that demonstrated subscribers’ engagement and the most relevant topics, e.g., news, upcoming events, curriculum, local culture, etc. The most popular publications included information about teachers, students’ achievements, and art school projects. Most accounts owed their high engagement rates to diverse content and high subscribers’ activity. The communities of the Tulun children’s art school and children’s music school showed very high levels of engagement. The highest engagement levels belonged to the children’s art and music schools in Tulun. These schools used social nets to promote their education programs and broadcast achievements of theirstudents and teachers. The accounts with high engagement rates became involved in social media recommendation algorithms.

Xinjin Li, Xinjin Li, Shiya Wang et al.

IntroductionParkinson's disease (PD) patients experience a wide variety of gait and posture problems that significantly impair their functional mobility and quality of life. Auditory cue-based training has been shown to improve gait performance in PD patients. However, most of the current methods target gains in bilateral spatiotemporal variables, whereas in the early-stages of PD, symptoms are usually unilateral.MethodsTo address the effects of unilateral onset and heterogeneity of early-stage PD on patients' gait performance, we propose a personalized training method based on auditory cues to reduce gait asymmetry between patients' right and left feet. The method targets patients' gait performance through personalized music (auditory cues) and dynamically adjusts the music based on real-time gait data to ensure synchronization with the patient's walking rhythm. Specifically, gait data are acquired in real time via Inertial Measurement Units (IMUs) attached to the ankles of the patient's right and left feet, which are used to calculate the gait cycles of the patient's right and left feet. Personalized music is then generated based on the patient's gait cycle. During the training process, the music is dynamically updated by continuously assessing the synchronization between the patient's gait cycle and the music beats.ResultsFifteen early-stage PD patients(H&Y ≤ 2.5) were initially recruited to compare and analyze the effects of training with and without auditory cues. Gait symmetry improved in all patients who received auditory cues (t = 4.9166, p = 0.0002), with a maximum improvement of 17.685%, and gait variables also showed significant enhancement. Eleven early-stage patients were then recruited for a 7-day intervention, with a mean improvement in gait symmetry of 11.803% (t = 4.391, p = 0.001). There were significant improvements in left-foot velocity (t = 4.613, p = 0.001), right-foot velocity (t = 6.250, p = 0.0001), and right-foot stride length (t = 4.004, p = 0.0025), and the average improvement rate of gait variables reached 37.947%. This indicates that the personalized training method proposed in this paper for the unilateral onset characteristics of early-stage PD is effective. It not only enhances the symmetry of walking in patients with early-stage PD, but also improves motor performance.DiscussionThe proposed method can serve as a complementary approach to pharmacological treatment in the rehabilitation of PD patients, demonstrating its effectiveness in clinical application.

Athanase Papadopoulos

Vincenzo Galilei and Constantijn Huygens were both humanists and eminent musicians, the former from the late Renaissance and the latter from the early Modern era. Their respective sons, Galileo and Christiaan, were scientists whose importance cannot be overestimated. My aim in this chapter is to set the scene for a parallel presentation of the legacy of the Galilei on the one hand, and the Huygens on the other. This will give us an opportunity to talk about mathematics, music and acoustics, but also about science in general, at this time of birth of the Modern era.

Ken O'Hanlon, Basil Woods, Lin Wang et al.

In this paper we propose a conditioned UNet for Music Source Separation (MSS). MSS is generally performed by multi-output neural networks, typically UNets, with each output representing a particular stem from a predefined instrument vocabulary. In contrast, conditioned MSS networks accept an audio query related to a stem of interest alongside the signal from which that stem is to be extracted. Thus, a strict vocabulary is not required and this enables more realistic tasks in MSS. The potential of conditioned approaches for such tasks has been somewhat hidden due to a lack of suitable data, an issue recently addressed with the MoisesDb dataset. A recent method, Banquet, employs this dataset with promising results seen on larger vocabularies. Banquet uses Bandsplit RNN rather than a UNet and the authors state that UNets should not be suitable for conditioned MSS. We counter this argument and propose QSCNet, a novel conditioned UNet for MSS that integrates network conditioning elements in the Sparse Compressed Network for MSS. We find QSCNet to outperform Banquet by over 1dB SNR on a couple of MSS tasks, while using less than half the number of parameters.

Tadahiro Taniguchi

Music and language are structurally similar. Such structural similarity is often explained by generative processes. This paper describes the recent development of probabilistic generative models (PGMs) for language learning and symbol emergence in robotics. Symbol emergence in robotics aims to develop a robot that can adapt to real-world environments and human linguistic communications and acquire language from sensorimotor information alone (i.e., in an unsupervised manner). This is regarded as a constructive approach to symbol emergence systems. To this end, a series of PGMs have been developed, including those for simultaneous phoneme and word discovery, lexical acquisition, object and spatial concept formation, and the emergence of a symbol system. By extending the models, a symbol emergence system comprising a multi-agent system in which a symbol system emerges is revealed to be modeled using PGMs. In this model, symbol emergence can be regarded as collective predictive coding. This paper expands on this idea by combining the theory that ''emotion is based on the predictive coding of interoceptive signals'' and ''symbol emergence systems,'' and describes the possible hypothesis of the emergence of meaning in music.

Federico Simonetta

This paper presents the first comprehensive systematic review of literature on style-based composer identification and authorship attribution in symbolic music scores. Addressing the critical need for improved reliability and reproducibility in this field, the review rigorously analyzes 58 peer-reviewed papers published across various historical periods, with the search adapted to evolving terminology. The analysis critically assesses prevailing repertoires, computational approaches, and evaluation methodologies, highlighting significant challenges. It reveals that a substantial portion of existing research suffers from inadequate validation protocols and an over-reliance on simple accuracy metrics for often imbalanced datasets, which can undermine the credibility of attribution claims. The crucial role of robust metrics like Balanced Accuracy and rigorous cross-validation in ensuring trustworthy results is emphasized. The survey also details diverse feature representations and the evolution of machine learning models employed. Notable real-world authorship attribution cases, such as those involving works attributed to Bach, Josquin Desprez, and Lennon-McCartney, are specifically discussed, illustrating the opportunities and pitfalls of applying computational techniques to resolve disputed musical provenance. Based on these insights, a set of actionable guidelines for future research are proposed. These recommendations are designed to significantly enhance the reliability, reproducibility, and musicological validity of composer identification and authorship attribution studies, fostering more robust and interpretable computational stylistic analysis.

Maximos Kaliakatsos-Papakostas, Gregoris Bastas, Dimos Makris et al.

Guitar tablature transcription consists in deducing the string and the fret number on which each note should be played to reproduce the actual musical part. This assignment should lead to playable string-fret combinations throughout the entire track and, in general, preserve parsimonious motion between successive combinations. Throughout the history of guitar playing, specific chord fingerings have been developed across different musical styles that facilitate common idiomatic voicing combinations and motion between them. This paper presents a method for assigning guitar tablature notation to a given MIDI-based musical part (possibly consisting of multiple polyphonic tracks), i.e. no information about guitar-idiomatic expressional characteristics is involved (e.g. bending etc.) The current strategy is based on machine learning and requires a basic assumption about how much fingers can stretch on a fretboard; only standard 6-string guitar tuning is examined. The proposed method also examines the transcription of music pieces that was not meant to be played or could not possibly be played by a guitar (e.g. potentially a symphonic orchestra part), employing a rudimentary method for augmenting musical information and training/testing the system with artificial data. The results present interesting aspects about what the system can achieve when trained on the initial and augmented dataset, showing that the training with augmented data improves the performance even in simple, e.g. monophonic, cases. Results also indicate weaknesses and lead to useful conclusions about possible improvements.

Jing Luo, Xinyu Yang, Dorien Herremans

Conditional music generation offers significant advantages in terms of user convenience and control, presenting great potential in AI-generated content research. However, building conditional generative systems for multitrack popular songs presents three primary challenges: insufficient fidelity of input conditions, poor structural modeling, and inadequate inter-track harmony learning in generative models. To address these issues, we propose BandCondiNet, a conditional model based on parallel Transformers, designed to process the multiple music sequences and generate high-quality multitrack samples. Specifically, we propose multi-view features across time and instruments as high-fidelity conditions. Moreover, we propose two specialized modules for BandCondiNet: Structure Enhanced Attention (SEA) to strengthen the musical structure, and Cross-Track Transformer (CTT) to enhance inter-track harmony. We conducted both objective and subjective evaluations on two popular music datasets with different sequence lengths. Objective results on the shorter dataset show that BandCondiNet outperforms other conditional models in 9 out of 10 metrics related to fidelity and inference speed, with the exception of Chord Accuracy. On the longer dataset, BandCondiNet surpasses all conditional models across all 10 metrics. Subjective evaluations across four criteria reveal that BandCondiNet trained on the shorter dataset performs best in Richness and performs comparably to state-of-the-art models in the other three criteria, while significantly outperforming them across all criteria when trained on the longer dataset. To further expand the application scope of BandCondiNet, future work should focus on developing an advanced conditional model capable of adapting to more user-friendly input conditions and supporting flexible instrumentation.

S. Johanan Joysingh, P. Vijayalakshmi, T. Nagarajan

Datasets are essential for any machine learning task. Automatic Music Transcription (AMT) is one such task, where considerable amount of data is required depending on the way the solution is achieved. Considering the fact that a music dataset, complete with audio and its time-aligned transcriptions would require the effort of people with musical experience, it could be stated that the task becomes even more challenging. Musical experience is required in playing the musical instrument(s), and in annotating and verifying the transcriptions. We propose a method that would help in streamlining this process, making the task of obtaining a dataset from a particular instrument easy and efficient. We use predefined guitar exercises and hidden Markov model(HMM) based forced viterbi alignment to accomplish this. The guitar exercises are designed to be simple. Since the note sequence are already defined, HMM based forced viterbi alignment provides time-aligned transcriptions of these audio files. The onsets of the transcriptions are manually verified and the labels are accurate up to 10ms, averaging at 5ms. The contributions of the proposed work is two fold, i) a well streamlined and efficient method for generating datasets for any instrument, especially monophonic and, ii) an acoustic plectrum guitar dataset containing wave files and transcriptions in the form of label files. This method will aid as a preliminary step towards building concrete datasets for building AMT systems for different instruments.

Isabella Mazzarolo, Kim Burwell, Emery Schubert

Performance anxiety is a widespread issue that can affect musicians across their education and career. It can develop in musicians from a young age leading to short-term and long-term impacts on not only their performance, but also their wellbeing. There is potentially a significant role that music educators hold in the development of their students and how they handle performance anxiety, though it is not clear how, or how often, teachers support their students in this way. Through a PRISMA-based systematic review, this paper explores what is known about the strategies used by music educators to help manage their students' performance anxiety. The paper also discusses the role that instrumental/vocal tutors and school classroom teachers might hold in this area. The findings show that music educators are implementing multiple strategies to assist their students with MPA, with the most common being simulated performance, positive outlook, preparation and breathing. It was found that there is a role for teachers to address MPA management with their students. While some students prefer to receive MPA support from experts in the field of psychology, students still expressed a need to have this support come from their teacher. Though many teachers felt a need for additional training for them to help their students cope with MPA, many of the strategies were found to be multifunctional and embedded into the regular teaching practices or teaching styles of the educator. Although these strategies might be implicit rather than explicit, the findings suggest that music educators could represent a valuable source of support for MPA management.

Sultan Almuhammadi, Abdullatif Alnajim, Mohammed Ayub

The Quick UDP Internet Connections (QUIC) protocol provides advantages over traditional TCP, but its encryption functionality reduces the visibility for operators into network traffic. Many studies deploy machine learning and deep learning algorithms on QUIC traffic classification. However, standalone machine learning models are subject to overfitting and poor predictability in complex network traffic environments. Deep learning on the other hand requires a huge dataset and intensive parameter fine-tuning. On the contrary, ensemble techniques provide reliability, better prediction, and robustness of the trained model, thereby reducing the chance of overfitting. In this paper, we approach the QUIC network traffic classification problem by utilizing five different ensemble machine learning techniques, namely: Random Forest, Extra Trees, Gradient Boosting Tree, Extreme Gradient Boosting Tree, and Light Gradient Boosting Model. We used the publicly available dataset with five different services such as Google Drive, YouTube, Google Docs, Google Search, and Google Music. The models were trained using a different number of features on different scenarios and evaluated using several performance metrics. The results show that Extreme Gradient Boosting Tree and Light Gradient Boosting Model outperform the other models and achieve one of the highest results among the state-of-the-art models found in the literature with a simpler model and features.

Liu Xizhi

Nowadays, with the continuous development of the times, multimedia technology(MT) is rapidly infiltrating people's lives, and people are paying more and more attention to multimedia teaching, which has been well applied in vocal music(VM) teaching. Since VM is a highly practical and relatively abstract subject, it is necessary to organically combine theory with practice. In addition, nowadays people have higher and higher requirements for music aesthetics, and the enrollment scale of VM majors is increasing, making traditional teaching methods no longer able to meet the needs of vocal talents. Because the network MT can well solve the problems in the traditional classroom and make up for the shortcomings, it has played an important role in improving classroom efficiency, improving the quality of teaching and teaching effects. At the same time, the use of modern methods for VM teaching can also provide teachers with more convenience. Therefore, under this background, it is necessary to combine modern education methods with VM teaching mode(VMTM) to realize the transformation of VMTM. This article uses questionnaire survey method and data analysis method to make use of the advantages of computer network MT to make VM teaching simpler and more intuitive, so as to achieve better VM teaching effects. According to the survey results, most interviewees believe that the application of computer network MT in the VMTM has certain effects and brings a lot of vitality to the development of the course.

Alexandre Popoff, Corentin Guichaoua, Moreno Andreatta

The `colored Cube Dance' is an extension of Douthett's and Steinbach's Cube Dance graph, related to a monoid of binary relations defined on the set of major, minor, and augmented triads. This contribution explores the automorphism group of this monoid action, as a way to transform chord progressions. We show that this automorphism group is of order 7776 and is isomorphic to $({\mathbb{Z}_3}^4 \rtimes D_8) \rtimes (D_6 \times \mathbb{Z}_2)$. The size and complexity of this group makes it unwieldy: we therefore provide an interactive tool via a web interface based on common HTML/Javascript frameworks for students, musicians, and composers to explore these automorphisms, showing the potential of these technologies for math/music outreach activities.

Giuseppe Clemente, Arianna Crippa, Karl Jansen et al.

We explore ideas for generating sounds and eventually music by using quantum devices in the NISQ era using quantum circuits. In particular, we first consider a concept for a "qeyboard", i.e. a quantum keyboard, where the real-time behaviour of expectation values using a time evolving quantum circuit can be associated to sound features like intensity, frequency and tone. Then, we examine how these properties can be extracted from physical quantum systems, taking the Ising model as an example. This can be realized by measuring physical quantities of the quantum states of the system, e.g. the energies and the magnetization obtained via variational quantum simulation techniques.

M. Hul, L. Dubé, J. Chébat

Chitralekha Gupta, Purnima Kamath, Lonce Wyse

Generative Adversarial Networks (GANs) currently achieve the state-of-the-art sound synthesis quality for pitched musical instruments using a 2-channel spectrogram representation consisting of log magnitude and instantaneous frequency (the "IFSpectrogram"). Many other synthesis systems use representations derived from the magnitude spectra, and then depend on a backend component to invert the output magnitude spectrograms that generally result in audible artefacts associated with the inversion process. However, for signals that have closely-spaced frequency components such as non-pitched and other noisy sounds, training the GAN on the 2-channel IFSpectrogram representation offers no advantage over the magnitude spectra based representations. In this paper, we propose that training GANs on single-channel magnitude spectra, and using the Phase Gradient Heap Integration (PGHI) inversion algorithm is a better comprehensive approach for audio synthesis modeling of diverse signals that include pitched, non-pitched, and dynamically complex sounds. We show that this method produces higher-quality output for wideband and noisy sounds, such as pops and chirps, compared to using the IFSpectrogram. Furthermore, the sound quality for pitched sounds is comparable to using the IFSpectrogram, even while using a simpler representation with half the memory requirements.