Hasil untuk "Musical instruction and study"

Nouhoum Coulibaly, Ousmane Ly, Michael Leventhal et al.

This study explores the capacity of generative artificial intelligence (Gen AI) to contribute to the construction of peace narratives and the revitalization of musical heritage in Mali. The study has been made in a political and social context where inter-community tensions and social fractures motivate a search for new symbolic frameworks for reconciliation. The study empirically explores three questions: (1) how Gen AI can be used as a tool for musical creation rooted in national languages and traditions; (2) to what extent Gen AI systems enable a balanced hybridization between technological innovation and cultural authenticity; and (3) how AI-assisted musical co-creation can strengthen social cohesion and cultural sovereignty. The experimental results suggest that Gen AI, embedded in a culturally conscious participatory framework, can act as a catalyst for symbolic diplomacy, amplifying local voices instead of standardizing them. However, challenges persist regarding the availability of linguistic corpora, algorithmic censorship, and the ethics of generating compositions derived from copyrighted sources.

Monalika Padma Reddy, Aruna Balasubramanian, Jiawei Zhou et al.

AI tools like ChatGPT and Be-My-AI are increasingly being used by blind individuals. Although prior work has explored their use in some Do-It-Yourself (DIY) tasks by blind individuals, little is known about how they use these tools and the available product-manual resources to assemble, operate, and troubleshoot physical or tangible products - tasks requiring spatial reasoning, structural understanding, and precise execution. We address this knowledge gap via an interview study and a usability study with blind participants, investigating how they leverage AI tools and product manuals for DIY tasks with physical products. Findings show that manuals are essential resources, but product-manual instructions are often inadequate for blind users. AI tools presently do not adequately address this insufficiency; in fact, we observed that they often exacerbate this issue with incomplete, incoherent, or misleading guidance. Lastly, we suggest improvements to AI tools for generating tailored instructions for blind users' DIY tasks involving tangible products.

Aurelio Tello Malpartida

Las pocas líneas que abren la edición que aquí se comenta resultan muy elocuentes, que bien vale reproducirlas in extenso: "Entre las actividades del Centro de Estudios Musicales Bolivia una de las iniciativas más interesantes del 2024 fue el “Foro Latinoamericano de Compositores”, no solamente por la talla de los participantes sino también por el aporte de ideas que se manifestaron en esa ocasión. Fruto de este intercambio es la presente revista “Música Latinoamericana hoy” así como el canal YouTube del mismo nombre. De hecho, entonces, “Música Latinoamericana hoy” constituye un espacio abierto a las ideas, a los pensamientos y a las propuestas artísticas musicales que busquen un contexto en el cual expresarse libremente".

Jane Pettegree

Wenzhe Li, Shujian Zhang, Wenxuan Zhou et al.

Evaluating the quality of multi-turn conversations is crucial for developing capable Large Language Models (LLMs), yet remains a significant challenge, often requiring costly human evaluation. Multi-turn reward models (RMs) offer a scalable alternative and can provide valuable signals for guiding LLM training. While recent work has advanced multi-turn \textit{training} techniques, effective automated \textit{evaluation} specifically for multi-turn interactions lags behind. We observe that standard preference datasets, typically contrasting responses based only on the final conversational turn, provide insufficient signal to capture the nuances of multi-turn interactions. Instead, we find that incorporating contrasts spanning \textit{multiple} turns is critical for building robust multi-turn RMs. Motivated by this finding, we propose \textbf{MU}lti-\textbf{S}tep \textbf{I}nstruction \textbf{C}ontrast (MUSIC), an unsupervised data augmentation strategy that synthesizes contrastive conversation pairs exhibiting differences across multiple turns. Leveraging MUSIC on the Skywork preference dataset, we train a multi-turn RM based on the Gemma-2-9B-Instruct model. Empirical results demonstrate that our MUSIC-augmented RM outperforms baseline methods, achieving higher alignment with judgments from advanced proprietary LLM judges on multi-turn conversations, crucially, without compromising performance on standard single-turn RM benchmarks.

Joann Ching, Gerhard Widmer

Music Emotion Recognition (MER) is a task deeply connected to human perception, relying heavily on subjective annotations collected from contributors. Prior studies tend to focus on specific musical styles rather than incorporating a diverse range of genres, such as rock and classical, within a single framework. In this paper, we address the task of recognizing emotion from audio content by investigating five datasets with dimensional emotion annotations -- EmoMusic, DEAM, PMEmo, WTC, and WCMED -- which span various musical styles. We demonstrate the problem of out-of-distribution generalization in a systematic experiment. By closely looking at multiple data and feature sets, we provide insight into genre-emotion relationships in existing data and examine potential genre dominance and dataset biases in certain feature representations. Based on these experiments, we arrive at a simple yet effective framework that combines embeddings extracted from the Jukebox model with chroma features and demonstrate how, alongside a combination of several diverse training sets, this permits us to train models with substantially improved cross-dataset generalization capabilities.

Qing Wang, Xiaohang Yang, Yilan Dong et al.

Music-to-dance generation aims to synthesize human dance motion conditioned on musical input. Despite recent progress, significant challenges remain due to the semantic gap between music and dance motion, as music offers only abstract cues, such as melody, groove, and emotion, without explicitly specifying the physical movements. Moreover, a single piece of music can produce multiple plausible dance interpretations. This one-to-many mapping demands additional guidance, as music alone provides limited information for generating diverse dance movements. The challenge is further amplified by the scarcity of paired music and dance data, which restricts the modelâĂŹs ability to learn diverse dance patterns. In this paper, we introduce DanceChat, a Large Language Model (LLM)-guided music-to-dance generation approach. We use an LLM as a choreographer that provides textual motion instructions, offering explicit, high-level guidance for dance generation. This approach goes beyond implicit learning from music alone, enabling the model to generate dance that is both more diverse and better aligned with musical styles. Our approach consists of three components: (1) an LLM-based pseudo instruction generation module that produces textual dance guidance based on music style and structure, (2) a multi-modal feature extraction and fusion module that integrates music, rhythm, and textual guidance into a shared representation, and (3) a diffusion-based motion synthesis module together with a multi-modal alignment loss, which ensures that the generated dance is aligned with both musical and textual cues. Extensive experiments on AIST++ and human evaluations show that DanceChat outperforms state-of-the-art methods both qualitatively and quantitatively.

Virginia Blankenhorn

Nicoletta Leone

All’inizio del XX secolo, il nuovo governo di Mustafa Kemal Atatürk si interessò a portare innovazione nella scena musicale turca, dando inizio ad un nuovo genere di musica turca che doveva fondere gli elementi tradizionali con lo stile compositivo occidentale. È sotto questa luce che bisogna analizzare la musica di Fazil Say (1970-): le sue composizioni sono affacci nella storia e tradizioni del suo Paese, e in ognuna di esse egli trova nuovi modi di evocare suoni e ambienti, con e senza la presenza di veri e propri strumenti tradizionali turchi. Con questo lavoro si è voluto esplorare la storia della musica turca dal Novecento ad oggi e il contributo di Fazil Say in qualità di uno dei massimi esponenti della musica del suo Paese, tramite un’analisi della forma e della struttura di due sue composizioni per violino che riassumono appieno il suo stile compositivo: la prima Sonata per violino e pianoforte e Cleopatra per violino solo.

SeungHeon Doh, Jongpil Lee, Dasaem Jeong et al.

Word embedding has become an essential means for text-based information retrieval. Typically, word embeddings are learned from large quantities of general and unstructured text data. However, in the domain of music, the word embedding may have difficulty understanding musical contexts or recognizing music-related entities like artists and tracks. To address this issue, we propose a new approach called Musical Word Embedding (MWE), which involves learning from various types of texts, including both everyday and music-related vocabulary. We integrate MWE into an audio-word joint representation framework for tagging and retrieving music, using words like tag, artist, and track that have different levels of musical specificity. Our experiments show that using a more specific musical word like track results in better retrieval performance, while using a less specific term like tag leads to better tagging performance. To balance this compromise, we suggest multi-prototype training that uses words with different levels of musical specificity jointly. We evaluate both word embedding and audio-word joint embedding on four tasks (tag rank prediction, music tagging, query-by-tag, and query-by-track) across two datasets (Million Song Dataset and MTG-Jamendo). Our findings show that the suggested MWE is more efficient and robust than the conventional word embedding.

Sangjun Han, Jiwon Ham, Chaeeun Lee et al.

In this work, we introduce the demonstration of symbolic music generation, focusing on providing short musical motifs that serve as the central theme of the narrative. For the generation, we adopt an autoregressive model which takes musical metadata as inputs and generates 4 bars of multitrack MIDI sequences. During training, we randomly drop tokens from the musical metadata to guarantee flexible control. It provides users with the freedom to select input types while maintaining generative performance, enabling greater flexibility in music composition. We validate the effectiveness of the strategy through experiments in terms of model capacity, musical fidelity, diversity, and controllability. Additionally, we scale up the model and compare it with other music generation model through a subjective test. Our results indicate its superiority in both control and music quality. We provide a URL link https://www.youtube.com/watch?v=-0drPrFJdMQ to our demonstration video.

Dinh-Viet-Toan Le, Louis Bigo, Mikaela Keller

Byte-Pair Encoding (BPE) is an algorithm commonly used in Natural Language Processing to build a vocabulary of subwords, which has been recently applied to symbolic music. Given that symbolic music can differ significantly from text, particularly with polyphony, we investigate how BPE behaves with different types of musical content. This study provides a qualitative analysis of BPE's behavior across various instrumentations and evaluates its impact on a musical phrase segmentation task for both monophonic and polyphonic music. Our findings show that the BPE training process is highly dependent on the instrumentation and that BPE "supertokens" succeed in capturing abstract musical content. In a musical phrase segmentation task, BPE notably improves performance in a polyphonic setting, but enhances performance in monophonic tunes only within a specific range of BPE merges.

Mara E. Culp, V. Davis

The elementary music program is often most likely to include all students in the United States. As such, teachers have an opportunity to encourage lifelong musicianship and musical engagement. Researchers have reported, however, that children’s interest in school music activities declines over the elementary years, and general music teachers struggle to invigorate older students. This raises questions about the nature of school music and why some students lose interest or cease participating. Recently, teachers have sought to address student preferences through diverse offerings, such as popular music instruction and ensemble-focused music classes. Still, teachers cannot be sure they are addressing students’ interests without seeking students’ input. In this second article in our research-to-practice series, we demonstrate this process, sharing how we surveyed students in Grades 3 to 5 regarding their music class activity preferences. Understanding the activities children enjoy and tailoring experiences accordingly may help increase school music engagement and support children’s lifelong musicianship.

Qihan Wang, Anique Tahir, Zeyad Alghamdi et al.

Depression has emerged as a significant mental health concern due to a variety of factors, reflecting broader societal and individual challenges. Within the digital era, social media has become an important platform for individuals navigating through depression, enabling them to express their emotional and mental states through various mediums, notably music. Specifically, their music preferences, manifested through sharing practices, inadvertently offer a glimpse into their psychological and emotional landscapes. This work seeks to study the differences in music preferences between individuals diagnosed with depression and non-diagnosed individuals, exploring numerous facets of music, including musical features, lyrics, and musical networks. The music preferences of individuals with depression through music sharing on social media, reveal notable differences in musical features and topics and language use of lyrics compared to non-depressed individuals. We find the network information enhances understanding of the link between music listening patterns. The result highlights a potential echo-chamber effect, where depression individual's musical choices may inadvertently perpetuate depressive moods and emotions. In sum, this study underscores the significance of examining music's various aspects to grasp its relationship with mental health, offering insights for personalized music interventions and recommendation algorithms that could benefit individuals with depression.

Bolim Lee

Objectives The purpose of this study is to examine the types of digital media that can be used in the secondary music education field, discuss music class design strategies, and then present a teaching and learning guidance plan to find out how actual classes that apply them can be implemented. Methods Therefore, the types of digital media that can be effectively used in the secondary music education field were divided into 11 categories and considered, and pedagogical strategies for designing music classes to maintain the essence of the music curriculum while actively using digital media were examined. And lastly, I drew a blueprint for secondary music class design using digital media by presenting a lesson plan for ‘The Nutcracker Suite’ and ‘Daechwita’, which are loaded in secondary textbooks. Results The results of this study are six in total. Music education using digital arouses learners' interest, provides scaffolding to improve musical literacy, and expands digital literacy. The point is that it is important to integrate the design and the process, to study the textbook faithfully, and to secure the connection to learning. In addition, the points to be considered while expanding the digital element to secondary music classes include preventing learners from losing concentration in online classes, securing the safety of realistic content for learners' health, maintaining the essence of music subjects, and changing the educational field that has been changed by science and technology. It is necessary to think about the role of teachers. Conclusions It is necessary to think about the role of teachers. If a music class design plan using digital is actively carried out by reading the current trend, music education for secondary students will more actively permeate into their lives, leading to true understanding and enjoyment.

Jee-hea Baek

Objectives The purpose of this study is to review Bachelard's material imagination, analyze how material imagination is expressed in musical encounters of young children, and examine the meaning of material imagination in early childhood music education. Methods After examining the historical flow of the concept and value of imagination and the distinctive characteristics of Bachelard's theory of imagination through literature research, examples were extracted from previous studies on the researcher's invented notations. How material imagination is expressed was analyzed in their invented notations. Results Bachelard's theory of imagination overcomes the limitations of opticocentrism, and establishes the dynamic status of imagination by reorganizing the concept of motion of matter of objects. In material imagination, the essence in the depths of the object moves and approaches the subject, and the subject also recognizes the movement of the object with feelings of joy and wonder. The motility of matter possessed by the object gives the object initiative and gives it a status equal to that of the subject. In addition, the ontological qualification of the object is given due to continuous creation, which has the significance of enabling the subject to become an object. Conclusions In the children's invented notations, the children sensed the motility of the musical characteristics of the song and created a new mental image by intertwining their experiences and environments. It can be seen that this is a creation that leads to ‘children - song of ‘everyone jump’ - invented notation - becoming’ through the manifestation of the material imagination of young children.

Hyunsu Lee

Objectives For the purpose of restoring the value of music education and forming citizens who can express the arts as a society Positive psychology was reviewed and a plan to apply it to music education was presented. Methods The background of the emergence of positive psychology and the concepts and contents of Optimism Learning, Strengths Development, Well-being Theory, and Flourish, which constitute positive psychology, were explored, typified, and considered. Based on this, a plan that can be used for music education was presented. Results As a result first, the degree of optimism of learners for music classes is identified in the form of a basic survey, second, it can be used as a survey of learners' musical strengths, third, a method of reconstructing music classes by reflecting on strengths, and fourth, a way to examine learners' happiness after class using the well-being theory was presented in the form of checks and descriptions. Conclusions In the current educational environment, the proposal of a music education plan using positive psychology for educational practice for learners to discover music emotion and make it strength through music education shows another possibility.

J. Ko

Objectives This study is a on teaching methods for early childhood music concepts using picture books. The aim of this study is to enhance the level of utilization of picture books by frontline teachers by examining the correlation between literary and musical elements of picture books and thereby suggesting music teaching methods using picture books, eventually in order for picture books, which have sufficient value as a music education medium, to be used more widely. Methods In this study, the current situation of early childhood music instruction using picture books was examined through the analysis of previous studies. In addition, through the literature survey, the developmental stages of early childhood music ability, and the relationship between picture books, Music education activities and music concepts were investigated. For the selection of picture books, picture books suitable for 5 to 7 years old were initially selected by referring to the list of recommended picture books and award-winning picture books. and than, 37 books eventually selected and analyzed according to the selection criteria established by previous studies and related literature. Based on this, pedagogical ideas for using picture books for teaching music concepts were suggested. Results In order to utilize common picture books as material for music education, this study suggested a way to connect musical concepts and picture books, and analyzed and presented picture books that can be used in each activity area of music education. Based on this, specific methods and examples of how picture books can be used for music instruction were presented to enhance teacher’s understanding and provide practical materials for effective teaching. Conclusions Picture books enable a variety of approaches to music teaching. Depending on the teacher’s approach, picture books allow more attempts for young children than any other media. Thus, teachers should expand their awareness and exploration of picture books as a valuable medium for music education to expand young children’s musical experiences.

Emmanuel Deruty, Maarten Grachten

Although the use of AI tools in music composition and production is steadily increasing, as witnessed by the newly founded AI song contest, analysis of music produced using these tools is still relatively uncommon as a mean to gain insight in the ways AI tools impact music production. In this paper we present a case study of "Melatonin", a song produced by extensive use of BassNet, an AI tool originally designed to generate bass lines. Through analysis of the artists' work flow and song project, we identify style characteristics of the song in relation to the affordances of the tool, highlighting manifestations of style in terms of both idiom and sound.

Seungyoun Hong

The primary purpose of this study was to examine the self-efficacy of pre-primary teachers for musical aptitude, such as pitch and rhythm, and to examine whether there is a significant change in self-efficacy through individual practice and instruction of Chorubungen exercises for eight weeks. Another purpose of the study was to examine the relationship between the musical experience and musicality of pre-service teachers, and their musical experience and achievement. To this end, a survey was conducted at the end of the semester for first-year students (56 males, 84 females) of a University of Education after regular individual practice in and guidance for eight weeks in the second semester of 2020. According to the results of the analysis, the positive self-efficacy of the pre-service teachers for pitch and rhythm before class participation was about 22.1% and 34.3% of the respondents, respectively, but after participating in the class, self-efficacy increased to 82.1% for pitch and 72.9% for rhythm. In comparison with the lower five variables, namely whether they learned an instrument among musical experiences (t-test) and the degree of singing (F test), pitch sensitivity (t=2.41, p<.05), rhythm sensitivity (t =1.98, p<.05), tempo sensitivity (t=2.79, p<.01), major scale, and major harmony pattern sensitivity (t=2.67, p<.01), all showed significant differences. In comparison to the achievement groups (chi-square test), differences between the achievement groups were measured based on whether they previously had experienced musical instruments (χ2=10.11, p<.01) and whether they had been active in a club (χ2=8.70, p<.05).