Musical Sequences Research Articles

Virtual Instrument Performances (VIP): A Comprehensive Review

AbstractDriven by recent advancements in Extended Reality (XR), the hype around the Metaverse, and real‐time computer graphics, the transformation of the performing arts, particularly in digitizing and visualizing musical experiences, is an ever‐evolving landscape. This transformation offers significant potential in promoting inclusivity, fostering creativity, and enabling live performances in diverse settings. However, despite its immense potential, the field of Virtual Instrument Performances (VIP) has remained relatively unexplored due to numerous challenges. These challenges arise from the complex and multi‐modal nature of musical instrument performances, the need for high precision motion capture under occlusions including the intricate interactions between a musician's body and fingers with instruments, the precise synchronization and seamless integration of various sensory modalities, accommodating variations in musicians' playing styles, facial expressions, and addressing instrument‐specific nuances. This comprehensive survey delves into the intersection of technology, innovation, and artistic expression in the domain of virtual instrument performances. It explores musical performance multi‐modal databases and investigates a wide range of data acquisition methods, encompassing diverse motion capture techniques, facial expression recording, and various approaches for capturing audio and MIDI data (Musical Instrument Digital Interface). The survey also explores Music Information Retrieval (MIR) tasks, with a particular emphasis on the Musical Performance Analysis (MPA) field, and offers an overview of various works in the realm of Musical Instrument Performance Synthesis (MIPS), encompassing recent advancements in generative models. The ultimate aim of this survey is to unveil the technological limitations, initiate a dialogue about the current challenges, and propose promising avenues for future research at the intersection of technology and the arts.

Pentatonic sequences and monaural beats to facilitate relaxation: an EEG study.

In two studies we investigated if specific acoustic stimulations could be more effective to induce a relaxation response in comparison to silence. Acoustic stimulations included monaural beats and musical sequences based on a pentatonic scale. In the first study, 47 participants evaluated monaural beats and pentatonic sequences presented through loudspeakers and varying along three frequencies (0.2, 2, 4 Hz). In the second study, 31 participants relaxed with their eyes closed for 10 min during a passive listening of monaural beats and a pentatonic sequence presented through loudspeakers. A silence condition was introduced as control. All auditory stimuli were designed with a temporal modulation of 0.2 Hz. Concomitant EEG was recorded with a 64-channel system and spectral analysis was performed on delta, theta, alpha, beta, and gamma oscillations to test if each of the three auditory stimulations had a significant effect on EEG spectral power in comparison to silence. In the first study, pentatonic sequences were evaluated as more pleasant and more relaxing than monaural beats. Pleasantness and relaxation were inversely related to frequency. Visual imagery and emotion induction had higher frequency and were rated with a more positive valence in pentatonic sequences than in monaural beats. In the second study monaural beats in comparison to silence strongly decreased beta and gamma oscillations in the first three minutes and strongly increased theta oscillations in the last three minutes. Pentatonic sequences increased delta, theta, and alpha oscillations in the last three minutes while decreasing beta, and gamma oscillations for the whole auditory stimulation. The results show that auditory signals with a very low temporal modulation (0.2 Hz) could be more effective than silence in inducing a relaxation response. Although 0.2 Hz monaural beats were effective in inducing a relaxation response, they tended to be perceived as unpleasant. Pentatonic sequences could be considered as a better alternative to promote relaxation by auditory stimulation.

Design and Implementation of Automatic Music Composition System Based on Deep Learning

Recently, there has been a notable increase in interest surrounding the utilization of Deep Learning Approaches for AMCS in recent times. However, current methods often lack coherence and authenticity in the generated music. This study proposes a new approach that utilizes RNNs to bridge the gap between traditional compositional methods and modern deep learning techniques. The goal is to produce expressive and coherent musical pieces. Our methodology involves designing and implementing a customized RNN architecture that can effectively capture the complex temporal dependencies present in musical sequences. We experiment with different types of including LSTM networks, RNNs, and GRUs, to overcome challenges such as vanishing gradients and better model longer-term dependencies in music. To train the neural network efficiently and improve model convergence, various deep learning optimizers are utilized in our system. Specifically, we use SGD optimizer to improve the hyper parameters of LSTM and GRUs. The data for training is converted into MIDI format and analyzed, with music lines being identified through a similarity matrix technique. The MIDI data is then prepared for use in the LSTM and GRUs networks. The resulting music is assessed using both objective measures, such as mean squared error, and subjective approaches. This research adds to the advancements in automatic music composition by demonstrating the capability of RNNs in capturing and producing complex musical arrangements.

Impact of Native Language on Musical Working Memory

Music and language share similar sound features and cognitive processes, which may lead to bidirectional transfer effects of training in one domain on the processing in the other domain. We investigated the impact of native language on musical working memory by comparing nontonal language (Finnish) speakers and tonal language (Chinese) speakers. For both language backgrounds, musicians and nonmusicians were recruited. In an experimenter-monitored online paradigm, participants performed a forward-memory task measuring the maintenance of musical sequences, and a backward-memory task measuring the manipulation of musical sequences. We found that maintenance of music sequences was facilitated in Chinese participants compared with Finnish participants, with musicians outperforming nonmusicians. However, performance in the backward-memory task did not differ between Chinese and Finnish participants, independently of music expertise. The presence or absence of tonal structure in the musical sequences did not affect the advantage of Chinese over Finnish participants in either maintenance or manipulation of the musical sequences. Overall, these findings suggest that Mandarin Chinese speakers have facilitated maintenance of musical sounds, compared with Finnish speakers, regardless of musical expertise and the presence of tonal structure. Our study furthers the understanding of language-to-music transfer and provides insights into cross-cultural differences in music cognition.

Use of Technologies in Music Therapy Clinical Practice

Abstract Music therapy, an innovative treatment, is a proven complementary therapy that incorporates the nature and potential of music to promote individuals’ health and recovery from disease at emotional, superfluous, cognitive, and physiological levels. The objective of this literature review is to examine the adoption of technologies in music therapy starting with easy use and moving to improved benefits. A narrative review method was used in this study recognizing a broad range of scholarly articles, product literature and research papers adopting systematic method while stressing on the applicability of the technological solutions in clinical care settings. The review shows that it is possible to use musical instrument digital interface devices, speech-based emotion recognition, room acoustic measurement software, as well as applications for interactive music composing to increase the effectiveness of music therapy. For example, interactive audio visual (AV) systems and music identification (MID) will enable the clinicians to create patient’s profile; on the other hand, adaptive musical instruments and motion sensing interface will allow patients with physical impairment to play an active role in musical performance. The conclusions underline the possibilities of using applications for training metronome for gait, a speech-emotion recognition tool for monitoring patients’ states, and video analysis for assessing session effectiveness. However, these developments clearly depict some impediments which hinder the entrance of these technologies in areas such as India due to ignorance, high costs, and op tilting towards resistance. In conclusion, one can state that although the new technologies are the valuable potential in changing the stream of music therapy where effective and efficient therapeutic approaches are in high demand, further intensity of efforts and actions to spread awareness, make therapies affordable and integrate into the clinical and educational practice is needed. The consequent of this review is to provide for further programs in research toward formation of more cultured and easily reachable technicalities of the musical therapy so as to improve the medical benefits of music therapy.

N-gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding

The first step to apply deep learning techniques for symbolic music understanding is to transform musical pieces (mainly in MIDI format) into sequences of predefined tokens like note pitch, note velocity, and chords. Subsequently, the sequences are fed into a neural sequence model to accomplish specific tasks. Music sequences exhibit strong correlations between adjacent elements, making them prime candidates for N-gram techniques from Natural Language Processing (NLP). Consider classical piano music: specific melodies might recur throughout a piece, with subtle variations each time. In this paper, we propose a novel method, NG-Midiformer, for understanding symbolic music sequences that leverages the N-gram approach. Our method involves first processing music pieces into word-like sequences with our proposed unsupervised compoundation, followed by using our N-gram Transformer encoder, which can effectively incorporate N-gram information to enhance the primary encoder part for better understanding of music sequences. The pre-training process on large-scale music datasets enables the model to thoroughly learn the N-gram information contained within music sequences, and subsequently apply this information for making inferences during the fine-tuning stage. Experiment on various datasets demonstrate the effectiveness of our method and achieved state-of-the-art performance on a series of music understanding downstream tasks. The code and model weights will be released at https://github.com/CinqueOrigin/NG-Midiformer.

Chinghiz Aitmatov’s Mythopoetic Picture of the World through the Context of Modern Stage Interpretations (In Russian)

The theatrical process in Central Asia is characterized by a common history of formation and development, basic principles and at the same time the originality and artistic heterogeneity of national theaters. A theater festival that is currently acquiring important significance as a space for dialogue between cultures serves as an indicator of its transformation in the region. Using the example of the winning performances of the VI International Theater Festival “Aitmatov and Theater” (2023), the mythopoetic picture of the world of Chinghiz Aitmatov is studied in the context of modern stage interpretations.The festival featured productions of prose rather than drama. This determined the features of the aesthetic structure of performances created within logocentric oriental cultures. The article analyzes the performances of Ulanmyrzha Karypbayev, one of the leading young directors in Central Asia. His productions such as “Borandy becket” (Station under Storm) and “Ak keme” (White Steamship) were among the best. They reveal the most characteristic features of U. Karypbayev as a director: a rich metaphorical system, theatrical polyphony, ritualization, grotesque, complex mise-en-scène. A large-scale play “Zhan pida” (Scaffold) directed by Nurkanat Zhakypbai current open the topics of historical memory, national identity and essential issues of existence. His stage interpretation is characterized by multi-layered visuals, exquisite plastic solutions, picturesque crowd scenes, a complex musical score, and a monologue principle in the acting performance. The directors Bair Badmayev and Gafur Mardanov created the story of Mother’s life path in the context of the national picture of the world in the stage versions of Mother Earth.The festival demonstrated a modern theatrical interpretation of Aitmatov’s works in Central Asia, characterized by leaving a usual path of words on stage and turning to more deeper interpretations. It is obvious that compositionally complex stage works are created with all components existing on an equal basis: words, stage action, scenography, rich plastic score, authentic musical sequence with performers on stage. Directors raise current issues, artistically comprehend reality and embody it in ideas, images, stage solutions that reflect the richness and diversity of the theatrical art in Central Asia.

Grey wolf optimizer based deep learning mechanism for music composition with data analysis

Music composition using artificial intelligence has gained increasing research attention recently. However, existing methods often generate music that needs more coherence and authenticity. This paper proposes an evolutionary computation-based deep learning approach for music composition with data analysis. Specifically, we utilize long short-term memory (LSTM) networks for generating melodic sequences and adopt a grey wolf optimizer to optimize LSTM hyperparameters. The training data is first converted to musical instrument digital interface (MIDI) format for data analysis, and melody lines are extracted using a similarity matrix method. The MIDI data is then encoded for input into the LSTM networks. The generated music is evaluated using objective metrics like mean squared error and subjective methods, including surveys of music professionals. Comparisons made to benchmark algorithms like generative adversarial networks demonstrate the advantages of our approach in accurately capturing tone, rhythm, artistic conception, and other attributes of high-quality music. The proposed mechanism provides a practical framework for AI-based music generation while ensuring authenticity.

SDMuse: Stochastic Differential Music Editing and Generation via Hybrid Representation

While deep generative models have empowered music generation, it remains a challenging and under-explored problem to edit an existing musical piece at fine granularity. In this paper, we propose SDMuse, a unified Stochastic Differential Music editing and generation framework, which can not only compose a whole musical piece from scratch, but also modify existing musical pieces in many ways, such as combination, continuation, inpainting, and style transferring. The proposed SDMuse follows a two-stage pipeline to achieve music generation and editing on top of a hybrid representation including pianoroll and MIDI-event. In particular, SDMuse first generates/edits pianoroll by iteratively denoising through a stochastic differential equation (SDE) based on a diffusion model generative prior, and then refines the generated pianoroll and predicts MIDI-event tokens auto-regressively. We evaluate the generated music of our method on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ailabs1k7</i> pop music dataset in terms of quality and controllability on various music editing and generation tasks. Experimental results demonstrate the effectiveness of our proposed stochastic differential music editing and generation process, as well as the hybrid representations.

Ilustrace v hudebninách a literatuře o hudbě pro děti první poloviny 20. století jako symptom multimediality

At the beginning of the 21st century, it seems to be normal for children’s books to be accompanied not only by illustrations but often also by sounds. They are in electronic form, stimulate tactile sensations and, within a certain space, step into the realm of augmented reality. Nevertheless, pictures made their way to books for children’s readers only slowly, and their application in professionally oriented literature, in the case of this study focused on music, was even more complicated. A more obvious interconnection between music and image in culture and especially in art can be traced in relation to social, political and cultural development. Illustrations of sheet music and music-related literature reacted to changes in practical, pedagogical and theoretical education without initially taking into account the needs of child development. The study highlights reforms in pedagogical principles and the initiatives of numerous publishers of specialised music editions. It examines works leading to a one-sided view of children’s music literature with respect to the assessment of the overall artistic level in the general context of book illustration as well as the scope from low to high art while taking into account theoretical reflections on mass and popular culture. Its aim is to indicate a direction foreshadowing multidisciplinary concepts, which have become a natural expression of contemporary art.

EmoMusicTV: Emotion-Conditioned Symbolic Music Generation With Hierarchical Transformer VAE

Emotion is one of the most crucial attributes of music. However, due to the scarcity of emotional music datasets, emotion-conditioned symbolic music generation using deep learning techniques has not been investigated in depth. In particular, no study explores conditional music generation with the guidance of emotion, and few studies adopt time-varying emotional conditions. To address these issues, first, we endow three public lead sheet datasets with fine-grained emotions by automatically computing the valence labels from the chord progressions. Second, we propose a novel and effective encoder-decoder architecture named EmoMusicTV to explore the impact of emotional conditions on multiple music generation tasks and to capture the rich variability of musical sequences. EmoMusicTV is a transformer-based variational autoencoder (VAE) that contains a hierarchical latent variable structure to model holistic properties of the music segments and short-term variations within bars. The piece-level and bar-level emotional labels are embedded in their corresponding latent spaces to guide music generation. Third, we pretrain EmoMusicTV with the lead sheet continuation task to further improve its performance on conditional melody or harmony generation. Experimental results demonstrate that EmoMusicTV outperforms previous methods on three tasks, i.e., melody harmonization, melody generation given harmony, and lead sheet generation. Ablation studies verify the significant roles of emotional conditions and hierarchical latent variable structure on conditional music generation. Human listening shows that the lead sheets generated by EmoMusicTV are closer to the ground truth (GT) and perform slightly worse than the GT in conveying emotional polarity.

Changes in Music Curriculum Education in Colleges and Universities Based on Cloud Classroom Assistive Technology

Abstract With the rapid development of science and technology, cloud classroom teaching has gradually become a trend. The cloud-based music teaching aid training system designed in this paper learns to map rhythmic and pitch features through music sequence generation technology. The onset detection algorithm of spectral flux detects the onset of the note. The Bezier curve is introduced into the melodic line feature generation algorithm to construct a polynomial function for interpolation between the first and the last endpoints, and the emotion is utilized to guide fractal music creation. Finally, the effectiveness of this auxiliary teaching system in college music teaching has been verified. The results show that the optimal Hamming distance of the system is 0.353 in the music melody generation experiment, which indicates that the system can quickly generate melody lines for students in music teaching and improve their learning efficiency. The system can significantly improve the rationality and efficiency of music skill training, which is worth promoting.

Musical Projects in Guitar Pro 7.5 Sequencer

The purpose of the article is to study the process of creating musical projects in the GUITAR PRO 7.5 sequencer. Research methodology. The article uses a systematic approach, as well as methods of analysis and synthesis, comparison and generalisation. The scientific novelty lies in the identification and development of innovative methods of working in the GUITAR PRO 7.5 sequencer, which allows creating musical compositions from scratch using modern software tools, as well as the possibilities of using music information technologies in the further artistic practice of musicians, sound producers, sound engineers, producers and in professional music education. Conclusions. This software product is a powerful music editor that allows one to create original scores at a professional level for subsequent editing. The programme presents many necessary tools with which the user can work with a variety of musical notation symbols and a wide range of sound dynamics and tempo control, which allows you to create samples of sounding musical pieces and their phonograms. It has a powerful built-in MIDI editor, chord builder, player, metronome, and other useful tools for musicians. Guitar Pro 7.5 can be run on Windows, Linux, and Mac OS platforms. It is widely used by musicians, composers, arrangers, sound engineers, sound designers, and producers. In addition, Guitar Pro 7.5 methods can be used for studying by students who are mastering the relevant specialties in higher educational institutions. Keywords: music notation editor, score, arrangement, sound, musician, composer, sound producer, sound engineer, producer, professional music education.

Electronic music composition thinking using visual learning and visual sensing technology

AbstractThis exploration aims to provide a kind of interactive electronic music composition thinking based on visual learning and visual sensing technology to enhance the thinking process of electronic music composition. Initially, it summarizes the functionalities of the physics components in Unity and analyzes the principles of visual interaction implementation using Virtual Reality (VR) devices and Leap Motion in Unity. Subsequently, the composition of interactive electronic music works is designed and implemented based on ultrasonic sensor technology. Lastly, this exploration focuses on the complete visual design of the audio‐visual integration of Musical Instrument Digital Interface (MIDI) music to represent Cymatics' images of the emotional content of the music. MIDI data can be assigned to provide various mapping possibilities between images and content in music visualization composition. This exploration also designs experiments based on sensory aftereffects and audio‐visual synesthesia to further determine the counterpoint law between the shape of dynamic Cymatics' images and the timbre's audio‐visual synesthetic results. The results indicate that Bass and Kick are distributed in the mid‐low frequency and sub‐low frequency range (20–160 Hz), Vocal and Lead are distributed in the mid‐high frequency range (1280–2560 Hz), and Hihat is distributed in the high‐frequency range (2560–5120 Hz). This exploration utilizes computer technology to create a music visualization method that conforms to the visual expression and aesthetic style of a multi‐sensory experience.

Using cognitive mapping to analyze the aesthetic value of music education in colleges and universities

Abstract In this paper, firstly, on the basis of cognitive mapping, music data are processed in four directions, namely, sound spectrum extraction, audio superposition, audio tempo, and tone intensity adjustment, and then audio sequences are sliced and diced, so that the cognitive mapping can be more focused on capturing localized useful information. Then, the BERT model is used to encode the music sequences so that the output music sequences already contain aesthetic and emotional features and the cognitive mapping-based music emotion analysis model is constructed according to the music emotion learning layer, the emotion feature aggregation layer, and the full connectivity layer, and analyzes the aesthetic value of music education in colleges and universities. According to the results, the BERT model had a difference of 0.13% on the MED dataset and 0.03% on the MTD dataset. On the mean value of the aesthetic value of traditional music, introverted personality (3.61) was higher than extroverted personality (3.52). This study has a positive effect on the cultivation of aesthetic value in music education in colleges and universities and proposes effective ways to enhance aesthetic value in college and university music teaching.

Challenges to and Perspectives on Mainstream Music Radio Programs in Germany

ABSTRACT Although radio still holds a high status among everyday media users in German society, there has been a clear downward trend in the usage of mainstream pop radios in recent years. In this essay, we highlight six central problems of current linear mainstream music radio and present possible solutions for creating more attractive and contemporary programs. In sum, we argue for greater inclusion of music editors’ creativity and experience, which is connected to the conscious downgrading of music-based market research, and for a stronger harmonization and curation of at least parts of the program by editors and moderators.

Neuromodulation of the Left Inferior Frontal Cortex Affects Social Monitoring during Motor Interactions.

Motor interactions require observing and monitoring a partner's performance as the interaction unfolds. Studies in monkeys suggest that this form of social monitoring might be mediated by the activity of the ventral premotor cortex (vPMc), a critical brain region in action observation and motor planning. Our previous fMRI studies in humans showed that the left vPMc is indeed recruited during social monitoring, but its causal role is unexplored. In three experiments, we applied online anodal or cathodal transcranial direct current stimulation over the left lateral frontal cortex during a music-like interactive task to test the hypothesis that neuromodulation of the left vPMc affects participants' performance when a partner violates the agent's expectations. Participants played short musical sequences together with a virtual partner by playing one note each in turn-taking. In 50% of the trials, the partner violated the participant's expectations by generating the correct note through an unexpected movement. During sham stimulation, the partner's unexpected behavior led to a slowdown in the participant's performance (observation-induced posterror slowing). A significant interaction with the stimulation type showed that cathodal and anodal transcranial direct current stimulation induced modulation of the observation-induced posterror slowing in opposite directions by reducing or enhancing it, respectively. Cathodal stimulation significantly reduced the effect compared to sham stimulation. No effect of neuromodulation was found when the partner behaved as expected or when the observed violation occurred within a context that was perceptually matched but noninteractive in nature. These results provide evidence for the critical causal role that the left vPMc might play in social monitoring during motor interactions, possibly through the interplay with other brain regions in the posterior medial frontal cortex.

Creating Zhudi and Guzheng sampler based on Nyquist

Nyquist is a strong and basic software for making music with algorithms. With the western instruments available as functions inside the software, this research aims to create sampler of traditional Chinese instruments that can read Musical Instrument Digital Interface (MIDI) files based on the present functions. This research mainly focuses on two instruments: Guzheng, a traditional plucked instrument in China and Zhudi, the oldest Chinese musical instrument found so far and the most representative woodwind in the Chinese musical instrument family. The methods used in this research is built on original functions, envelopes, filters in the software. After creating the samplers, the MIDI file users uploaded will be converted into scores inside Nyquist for the samplers to read. The separation of the MIDI file is done by if and else clauses, splitting the samplers to each focus on a certain part of the song. Based on the methods above, this research yields a sample song that has a MIDI file originally in the timbre of piano applied to both samplers at the same time. The outcome yielded applies two samplers separated at a certain pitch, forming a contrast between the main melody and the chords. This research successfully achieves its intended purpose, creating a bridge that connects western music culture with traditional eastern music culture.

The Myth of Don Juan: A. S. Pushkin and A. G. Schnittke

The article discusses the characteristics of the interpretation of the myth of Don Juan in A. S. Pushkin’s play “The Stone Guest”, as well as the embodiment of Pushkin's play in M. A. Schweitzer’s 1978 film from the series “Little Tragedies”. The analysis of Pushkin’s text in the context of the development of the myth reveals its anti-romanticism, which sharply distinguishes it from its artistic and historical environment, in particular the poet's negative attitude towards the right to freedom of feeling proclaimed by the Romantics. These ideas are further developed in the film version of The Stone Guest, in which the musical sequence created by A.G. Schnittke plays an important role.

Implizites und explizites Vermitteln?

Abstract Thinking about knowledge transfer in hybrid music editions raises follow-up questions, since music editions can traditionally be characterised by a coexistence of scholarly-critical and practical approaches. The article focuses in particular on implicit and explicit aspects of three interrelated dimensions of transfer: the concept of the edition, internal communication processes, and performance-related editorial acts. The author argues that in scholarly hybrid editions, which are also intended for musical practice, several issues of knowledge transfer are implicit: in the overall aim of the edition, in the presentation of edited texts and critical notes, and in the consideration of user groups. The article discusses the importance of transmitting the concept of the edition to the editorial team involved. Project leaders play an important role in establishing communication structures, organising the many steps of an edition, and facilitating smooth collaboration between project members from different academic disciplines. Finally, the article explores the ways in which the feasibility of an edition is consciously or unconsciously present during the editing process, and the extent to which editors perform an inherent mediating function.