Musical Score Research Articles

Comparative Analysis of Object Detection Models for Sheet Music Recognition: A Focus on YOLO and OMR Technologies

Abstract. As Artificial Intelligence (AI) technologies are developing rapidly and are widely used in various domains, it is efficient and convenient for composers to make music using AI to convert sheet music to audio. This research aims to compare the performance of different models in identifying individual notes within sheet music. Compared to traditional technologies like Optical Music Recognition (OMR), deep learning models have a significant advantage in processing blurry images with high efficiency. In the research process, three different models are used in searching for musical notes: OMR, You Only Look Once (YOLO)v5, and YOLOv8. The evaluation index consists of recognition accuracy, mean Average Precision (mAP), inference speed, and parameter quantity. After the experiment, it is found that the YOLO model performs best with high accuracy and fast speed. Based on the above analyses, the thesis finds that the YOLO model can be an efficient tool in composing music, with further research.

Study on the Emotional Expression and Playing Skills of Mozart's Piano Trio in B Flat Major

This paper focuses on the study of the emotional expression and playing skills of Mozart's piano trio in B flat Major (K.502), aiming to deeply analyze the artistic connotation and performance practice of this classical music masterpiece. Mozart played a role in establishing the "template" in the piano trio music genre. In his creation, the three instruments in the piano trio were truly independent and unique, and the theme of the three voices began to resonate and depend on each other, one after another. He also established the three-movement pattern of piano trio writing and the musical structure of the first and last movements. Through the detailed analysis of the emotional level and performance skills of the work, it provides a more abundant understanding and deductive perspective for music scholars, performers and lovers. The purpose of this study is to systematically explore the ways of emotional expression and the subtleties of performance skills through literature review, music score analysis and field performance experiments. The research process integrates the multi-disciplinary methods of music theory, emotional psychology and performance practice. The conclusion is that Mozart's piano trio in B flat major not only shows his outstanding creative talent, but also provides a broad stage for players to show their personal emotional understanding and technical level.

Audiovisual Imagery in Multimodal Perception and Performance of Qigang Chen’s Er Huang Concerto

In the realm of musical performance, the role of a pianist extends beyond the mere execution of musical scores to become a pivotal contributor to artistic expression. This study delves into the auditory and visual imagination through the perception and performance of piano works by the Chinese-French composer Qigang Chen from the early 21st century, involving the performer’s meticulous response to the nuances of musical sound as well as the interplay of visual synaesthesia.The study also explores the inherent conveyance chain within the performance process, experimenting with multimodal forms of expression. These creative choices not only enrich the narrative of the arts but also contribute to crafting a comprehensive, immersive concert experience for the audience. The principal aim of this research is to explore the prismatic view within Qigang Chen’s piano work, offering multiple possibilities of meaning and emphasizing the crucial role of the pianist in forming and elucidating the fusion of auditory and visual senses in performative action.By transcending traditional performance boundaries, this exploration invites the audience to witness the multimodal interactions inherent in musical performances, providing a fresh perspective on dynamic exchanges between different sensory elements and cultural influences.

2015 개정 및 2022 개정 교육과정에 따른 '즐거운 생활' 교육과정과 교과서의 음악 학습 내용 비교

As the 2022 revised curriculum was implemented, significant changes emerged in the content structure and textbook system of the elementary school integrated curriculum. This study aims to investigate how the "Pleasant Life" curriculum and the music learning content in elementary school textbooks impact music education. To this end, the study first compares the characteristics of the "Joyful Life" curriculum in the 2015 and 2022 revised curriculum. Second, the study analyzes in detail the characteristics of songs and music learning activities included in the integrated textbooks of both periods. Third, it identifies the challenges faced in music education for first and second-grade students within the integrated curriculum system and proposes improvement strategies to address these issues. The findings reveal that while the 2022 revised curriculum emphasizes teacher and student autonomy, it does not adequately support foundational music learning. Specifically, as the difficulty of songs in the textbooks increased and music activities decreased, students lacked sufficient opportunities for meaningful musical experiences. Therefore, to ensure effective music education for lower grades, music instruction should be delivered separately from integrated subjects, with a more systematic and developmentally appropriate approach. Additionally, there is a need to present musical scores in varied formats and include easier songs in textbooks. Improvements should also focus on designing music learning activities that align with the developmental stages of young learners, making musical concepts easier to understand and learn systematically.

Altered resting-state connectivity of the auditory cortex in congenital amusia: A functional magnetic resonance imaging study in Mandarin speakers.

Brain imaging studies have reported that the neural deficits of congenital amusia in non-tonal language speakers are mainly in the connectivity between the auditory cortex and the inferior frontal gyrus (IFG) in the right hemisphere. However, the relationship between the functional connectivity (FC) in these regions and the music perception ability of amusia in tonal language speakers remains unclear. In this study, we investigated the FC characteristics of amusia in Mandarin speakers in resting-state functional magnetic resonance imaging data by voxel-wise connectivity analyses with seeds in left and right Heschl's gyri (HG) and region of interest (ROI)-to-ROI connectivity analyses. Our findings indicate increased connectivity between right HG and bilateral posterior superior temporal gyrus, as determined by voxel-wise connectivity analyses in amusia. Conversely, reduced connectivity was observed between bilateral HG and bilateral IFG (orbital part) as assessed through ROI-to-ROI connectivity analyses in amusia when compared to controls. Moreover, the music perception scores of amusia in Mandarin speakers were associated with diminished connectivity between the left HG and the right IFG. This study furnishes direct evidence for the link between music perception deficits and the aberrant frontotemporal connectivity of congenital amusia in tonal language speakers in resting state.

The Use of Cloud Platform Technology to Help University Music Teachers Teaching Decision-Making Research

With the COVID-19 pandemic, more and more universities are turning to online teaching, and music teaching is no exception. Because music teaching pays attention to the particularness of teachers' demonstration and students' imitation, the change of teaching environment from offline teaching to online teaching has a greater impact on the music discipline, which has new requirements for teachers' decision-making level. Through literature and questionnaires, this study identified that the most significant factor affecting teachers' decision making after the teaching environment was changed to online teaching was teacher-student interaction and designed a model to improve the interactive teaching of teachers through cloud platform technology. It is found that the model can effectively improve the interaction between teachers and students, so that teachers can make good decisions more easily and easily, so as to improve students' music scores and achieve effective teaching.

THE ROLE AND SIGNIFICANCE OF MODERN TECHNOLOGY FOR THE FUTURE OF MUSIC EDUCATION

This study presents research on prospective primary school teachers engaged in music instruction in primary school settings. The research focuses on the development of skills in using and adapting educational content through modern technology. Specifically, it examines the competencies required to utilize an application for composing musical scores using elements of musical notation, a topic typically studied in grades one to four.

Комментарий очерка Сергея Слонимского «Скандалист поневоле: хроника хронического стресса – 1972-1991» из книги «Заметки на полях нотной тетради»

The article continues the publication and commentary of S. M. Slonimsky’s 2002 essay “An Unwilling Scandalmonger: A Chronicle of Chronic Stress – 1972-1991” from the book “Notes in the Margin of a Music Score”. Due to space limitations, the entire material of the essay is divided into three parts: the first article is dedicated to the post-war period of the author’s life until the beginning of the 1970s. The second (this) article explores events from the composer’s life and work in 1972-1991. The following, third article will cover the last decade of the 20th century and the beginning of the 21st century, 1992-2002. The focal points of the author’s reflections in the second essay of the “chronicle of chronic stress – 1972-1991” are also themes of moral and ethical issues within the composer’s society. These themes are explored in a different light – in direct connection with S. M. Slonimsky’s life in chronological order. The essay covers the second half of the 20th century and the beginning of the 21st century. The writing of this commentary is driven by the intensifying crisis of moral values in contemporary society. The author concludes: one should “focus on only one painful moment, quite typical of my creative and life path. Perhaps scandalous storms are my cross, the fateful predetermination of my destiny. Perhaps it is a fatal necessity for an independent person walking their own path, not wanting to prudently submit to those in power, to what promises peace, recognition, success, prosperity, and happy success. That is how I am, and that is how I will remain until the end <…> In my work, my philosophical worldview, personal traits of my emotional temperament, and my attitude towards many people inhabiting Russia, Europe, Asia, our entire earth are absolutely obvious.” As a result of the study, Slonimsky’s unwavering commitment to the established moral and ethical order and his uncompromising stance against manifestations of evil, envy, and betrayal in the composers’ milieu and music teaching have been identified and confirmed.

Using Music Features for Managing Revisions and Variants of Musical Scores

Abstract Music engravers nowadays use music notation software to create scores for musical works. As is common in any creative process, many different versions of digital artifacts are created—e.g., to manage editions of the same musical work, editorial markups, or the history and genesis of compositions. In the field of software engineering, researchers have proposed the use of features, i.e., user-visible aspects of systems, to manage both revisions and variants of source code and other software artifacts. Feature-based version control systems establish and maintain feature-to-code mappings defining which parts of the artifacts realize particular features, e.g., which code implements a specific function. These mappings can then be used to generate new variants based on the artifacts by selecting the desired features. Our article provides an in-depth study on feature-based version control for music notation. Our automated approach adopts the domain-specific language (DSL) LilyPond and the feature-oriented version control system ECCO. Existing studies show that features in musical scores are often fine-grained and affect only small parts of an artifact, are scattered across noncontiguous locations in the artifact, and highly interact with each other. Such properties have strong implications for the usefulness of versioning tools. Our experiment investigates two factors related to the correctness of output from feature-based version control systems when used for symbolic music notation. We demonstrate the incremental refinement of feature-to-artifact mappings when committing DSL code. We further study the impact of the order of feature interactions on the correctness of the automatically generated music artifacts. We find that a larger feature interaction threshold produces only marginally more correct results, but fixing and recommitting incorrect variants has a more powerful effect. Our results further show that considering DSL specifics is important for versioning fine-grained and scattered features.

Timings of Dance Techniques as a Separate Lexical Component of Papping

The purpose of the work is to identify, analyse, and structure one of the understudied lexical components of papping and illusory styles. Research methodology. In the process of research, the principle of induction was used, as well as the following methods: analysis and synthesis – in the process of working with information sources; comparison – to identify identical facts and patterns; formalisation – for recording the detected timings in a single format. Scientific novelty. For the first time, in the process of analysing the dance vocabulary of popping and other illusory styles, their little-studied lexical component – timings – was revealed. A clear definition of this term is given, that is, the main characteristics of this component. Most of the used (basic) timings are identified and described, and their graphic record is also given. Conclusions. The analysis of the dance vocabulary of popping and other illusory styles made it possible to highlight their little-studied lexical component – timings. A clear meaning was also given to the term "timing", which is rhythmic after the use of dance technique (muscle control), which the dancer can impose on their own dance (dance movements, position). Research into this lexical constituent process has identified several "baseline" timings for popping and illusory styles. They are based on two basic dance techniques – pap and dime stop. Some of them correspond to individual dance movements or a specific illusory style. For a simple analysis and understanding of the timings, the article used a graphic model of their recording, which allows you to visually display the timings in accordance with the musical score. Thus, timings can be used as a separate lexical component of papping and its adjacent styles with their own characteristics and specificity. This component is closely related to music and, for the most part, a conflict for the dancer to diversify their performance by adding to its various rhythms.

Commentary on Sergey Slonimsky’s essay “An Unwilling Scandalmonger: A Chronicle of Chronic Stress – 1943-1971” from the Book “Notes in the Margin of a Music Score”

Commentary on Sergey Slonimsky’s essay “An Unwilling Scandalmonger: A Chronicle of Chronic Stress – 1943-1971” from the Book “Notes in the Margin of a Music Score”

Detecting chord tone alterations and suspensions

Chord detection is the task of assigning chord labels to segments of an input musical piece. The labels are typically drawn from a pre-defined vocabulary in which each symbol comprises at least a root pitch and a chord quality. In this paper, we introduce a post-processing method that takes as input a musical score with such labels and adds chord tone alterations such as suspensions to them. Although it is an important aspect of harmonic analysis, it is infeasible to do so by simply adding features to the labels in the vocabulary, given the multiplicative effect on vocabulary sizes which can already be over 1000. We evaluate our method using both ground truth input and input derived from a chord detection model, showing that it outperforms a strong heuristic baseline in both cases. Furthermore, we show that our model can be used to detect the rarer chord qualities from the model's output alterations, potentially enabling chord detection models to be trained on small vocabularies containing only the more common (and easier to identify) chord qualities (e.g. only triads).

Functionality and Scar Evaluation of the Donor Site in Extended Radial Forearm Flap Phalloplasty: How Affected Is the Arm in Day-to-Day Life?

Background: The radial forearm flap remains the gold standard in phalloplasty in gender-affirming surgery due to its versatility and functional outcome, but the significant donor site morbidity and its impact on daily functioning and aesthetic perception remains understudied. This study provides valuable insights into the mid-term functional and aesthetic outcomes of the forearm in transgender individuals following radial forearm flap phalloplasty using widespread instruments for assessment scoring systems and for the evaluation of postoperative wound healing of surgical interventions in general. Methods: Between January 2013 and March 2018, a total of 47 patients underwent radial phalloplasty at AGAPLESION Markus Hospital, and 20 consented to participate in this cross-sectional, retrospective study evaluating functional and aesthetic outcomes post-radial forearm flap phalloplasty using standardized questionnaires (DASH, POSAS, and SBSES). A univariate median regression of each score was performed to determine the associations with selected variables, and correlation analyses between scores was performed using a nonparametric Spearman rank correlation. Results: Among the 20 participants, the median Quick DASH, DASH functionality, DASH sport and music, and DASH work scores indicated minimal to no functional impairment. Scar evaluations using the PSAS, OSAS, and SBSES scales showed overall patient satisfaction with minimal concerns regarding pigmentation and scar texture. Notably, an increase of 0.27 cm2 in wound surface area added one point to the DASH sport and music score (p = 0.037). Statistical analysis also demonstrated a significant correlation between functional and aesthetic assessment scores. Conclusions: The radial forearm phalloplasty donor site, evaluated by the PSAS, OSAS, and SBSES scales, leads to minimal or no functional impairment; however, the worsening of the DASH sport and music score with increasing wound surface reflects a direct relation between wound size and functional impairment.

Johan Halvorsens engagemang i Helsingfors 1889–92 som katalysator för hans arbete som kompositör

The first part of the article examines the Norwegian composer Johan Halvorsen’s activities in Helsinki during the years 1889-92. The flourishing musical life of the Finnish capital, which actually inspired Halvorsen to begin composing, as well as Halvorsen’s musical agency, are examined from a variety of perspectives, both socio-cultural and biographical. The research is based on extensive historical archival material. The aim of the article is twofold: first, to map the musical and personal impulses that inspired Halvorsen’s emergence as a creative artist, and second, to highlight his contribution to Helsinki’s musical life during this period. The second part of the article presents Halvorsen’s String Quartet in E minor (1892). This is his most important work from this period in terms of its scope and the prestige of the genre. The public response to the work’s first performance was positive, but the composer himself was not satisfied: a few years later he destroyed most of the material, but transcribed the slow movement for orchestra. Since Halvorsen was a self-taught composer, it is natural to ask why: was the destruction of the work the result of a lack of quality, the composer’s excessive self-criticism, or simply the conviction that the work did not represent his stylistic idiom as a composer? These questions will be explored through a transcription of the surviving orchestral score, an analysis of musical structures such as form (macro and micro), melody and harmony in the one surviving movement, the contemporary reception of the work, and finally a comparison of the work with Halvorsen’s oeuvre as a whole.

HiddenSinger: High-quality singing voice synthesis via neural audio codec and latent diffusion models

Recently, denoising diffusion models have demonstrated remarkable performance among generative models in various domains. However, in the speech domain, there are limitations in complexity and controllability to apply diffusion models for time-varying audio synthesis. Particularly, a singing voice synthesis (SVS) task, which has begun to emerge as a practical application in the game and entertainment industries, requires high-dimensional samples with long-term acoustic features. To alleviate the challenges posed by model complexity in the SVS task, we propose HiddenSinger, a high-quality SVS system using a neural audio codec and latent diffusion models. To ensure high-fidelity audio, we introduce an audio autoencoder that can encode audio into an audio codec as a compressed representation and reconstruct the high-fidelity audio from the low-dimensional compressed latent vector. Subsequently, we use the latent diffusion models to sample a latent representation from a musical score. In addition, our proposed model is extended to an unsupervised singing voice learning framework, HiddenSinger-U, to train the model using an unlabeled singing voice dataset. Experimental results demonstrate that our model outperforms previous models regarding audio quality. Furthermore, the HiddenSinger-U can synthesize high-quality singing voices of speakers trained solely on unlabeled data.

«AH, CHE BARBARO APPETITO!», O L’ARTE DELLA TAVOLA NEL CONVITATO DI PIETRA DI GIOVANNI BATTISTA LORENZI PER GIACOMO TRITTO E DINTORNI

In considering Il convitato di pietra by Giovanni Bassista Lorenzi and Giacomo Tritto (Naples, Teatro dei Fiorentini, 1783), this essay aims to first present the characters and the plot, to then study the orchestral score, and, closely linked to the intonation, the metrical choices of the librettist. Finally, it focuses on the topos of the banquet in its various facets, contextualising the 1783 draft with respect to the spoken versions of the pseudo-Cicognini, dating back to around the middle of the seventeenth century, and of Don Giovanni Tenorio (1736) by Carlo Goldoni, and other contemporary adaptations: the other Convitato di pietra (1776) by Nunziato Porta and Vincenzo Righini, Don Giovanni (1787) by Giovanni Bertati and Giuseppe Gazzaniga, Il nuovo convitato di pietra (1787) by Giuseppe Foppa and Francesco Gardi, Il dissoluto punito (1787) by Lorenzo Da Ponte and Wolfgang Amadeus Mozart.

Research on Multi-Modal Music Score Alignment Model for Online Music Education

As music data storage becomes increasingly diverse in the era of big data, ensuring alignment of music works with the same semantics for online music education is crucial. To achieve this, a multi-modal music score alignment algorithm model based on deep learning was developed and optimized. Experimental results demonstrated that Note + DCO feature combination yielded the best MIDI input characteristics (mean value: 13.27 ms), whereas CQT feature comparison produced the best results for audio input (average: 12.85 ms). The ResNet-34 network was noted to have the most effective music score alignment effect with alignment errors averaging less than one frame. Compared with other algorithms, the proposed algorithm had the lowest average value of 9.28 ms, median value of 5.85 ms, and standard deviation of 20.17 ms. Actual music retrieval showed a Top-1 retrieval accuracy of 10.93% that was close to 11%. Overall, the proposed algorithm is significant for score alignment and music retrieval recognition in online music education.

Commentary on Sergey Slonimsky’s essay “Myths and Reality: On False Reputations” from the book “Notes in the Margin of a Music Score”

Commentary on Sergey Slonimsky’s essay “Myths and Reality: On False Reputations” from the book “Notes in the Margin of a Music Score”

Digital critical edition of Čiurlionis' piano music: a case study

Mikalojus Konstantinas Čiurlionis (1875–1911) is a key figure in Lithuanian music and art. As a professional composer and painter, he left behind over 220 paintings and 350 musical compositions. His art showcases early examples of abstract painting and serial music in Europe. However, his work and contributions to the music world are not widely known. The publication of his music was delayed for 50 years, and several different systems of cataloguing Čiurlionis' music were used, as well as different editing practices and multiple editorial versions. This complexity made the performance and further research of his music complicated for contemporary users. After a grant of the Lithuanian Research Council was received in 2022, the digital critical edition of Čiurlionis' piano music was started. It is based on the previous research done by members of a research team, when the Chronological Catalogue of Čiurlionis Music (2007) and several urtext editions were published (2010–2020). The currently developed prototype online system is a web-based application that enables users to work with all of Čiurlionis' piano music (manuscripts and previous editions), to use the digital edition for performances, and for further studies or research. The corpus of material is presented as an online digital critical edition with a catalogue, search tool and a specially developed tool for musicological and computational analysis of music scores.

AESTHETIC ALCHEMY FOR UNVEILING THE TRANSFORMATIVE POWER OF ARTISTIC CHOICES IN POSTCOLONIAL TRAUMA NARRATIVES: EVALUATING THROUGH THE INTERPRETATIONS OF AMITAV GHOSH'S SELECTED NARRATIVES

A crucial role is played by aesthetics in shaping trauma narratives, impacting how individuals perceive, undergo, and process traumatic events. In this context, "aesthetics" encompasses the artistic or stylistic elements employed in storytelling across various mediums like literature, film, visual arts, and more. Aesthetic choices such as symbols and metaphors become potent tools for conveying intricate emotions and experiences linked with trauma, providing a layer of abstraction that facilitates a nuanced exploration of its psychological and emotional dimensions. Aesthetics also influence the structure of a trauma narrative, with elements like flashbacks, non-linear timelines, or fragmented storytelling mimicking the disjointed nature of traumatic memories, effectively conveying the disorientation experienced by those who have undergone trauma. In visual arts and cinema, the visual representation of trauma significantly influences its perception, employing stark imagery, visual metaphors, and symbolic elements to communicate the profound impact of trauma, transcending the limitations of language in capturing its depth. Aesthetic elements like soundtracks and musical scores contribute to the emotional tone, heightening tension, creating a sense of foreboding, and influencing the audience's engagement with the traumatic content. In literature, the choice of language and literary devices shapes the narrative style, impacting how trauma is portrayed. Vivid descriptions, metaphors, and unique linguistic styles evoke a visceral response, fostering a more intimate connection between readers and the trauma narrative. Additionally, aesthetics can influence the resolution of a trauma narrative, utilizing specific visual or narrative elements to contribute to a sense of catharsis or closure for both the characters and the audience, providing a pathway towards healing and recovery. In summary, aesthetics serve as a crucial lens through which trauma narratives are presented and experienced, enabling creators to enhance their depth, emotional resonance, and impact, fostering a greater understanding and empathy for the complex nature of trauma through thoughtful and intentional artistic choices. In the context of Amitav Ghosh's novels, the discussion of postcolonial historic aporia becomes significant, especially given Ghosh's aversion to the term "postcolonial" which tends to portray the aftermath of colonialism in a negative light. Ghosh expresses his dissatisfaction with this characterization, stating, ". . . when I think of the world that I grew up to inhabit, my dominant memory of it is not that it was trying to be a successor state to a colony; it was trying to create its own reality, which today is the reality that we do inhabit" (Kumar 105). This perspective reflects Ghosh's inclination to focus on the efforts of postcolonial societies in shaping their distinct realities rather than being defined solely in opposition to their colonial past. Ghosh's novels, influenced by this viewpoint, illustrate the complexities of postcolonial experiences through the aesthetics of storytelling. Within his narrative framework, he employs symbolism, metaphor, and narrative structure to delve into the intricacies of trauma. Through these aesthetic choices, Ghosh offers a nuanced exploration of the psychological and emotional dimensions of characters' traumatic experiences, challenging conventional postcolonial narratives that tend to emphasize negativity. Ghosh's deliberate use of visual representation, sound, and literary devices in portraying trauma further underscores his commitment to presenting a multifaceted understanding of postcolonial realities. Consequently, his intentional and thoughtful aesthetic choices serve as a critical lens through which postcolonial trauma narratives are depicted, fostering a richer appreciation for the intricate nature of these stories and the diverse realities they represent.