Hasil untuk "Literature on music"

Tobias Morocutti, Emmanouil Karystinaios, Jonathan Greif et al.

Music Source Restoration (MSR) targets recovery of original, unprocessed instrument stems from fully mixed and mastered audio, where production effects and distribution artifacts violate common linear-mixture assumptions. This technical report presents the CP-JKU team's system for the MSR ICASSP Challenge 2025. Our approach decomposes MSR into separation and restoration. First, a single BandSplit-RoFormer separator predicts eight stems plus an auxiliary other stem, and is trained with a three-stage curriculum that progresses from 4-stem warm-start fine-tuning (with LoRA) to 8-stem extension via head expansion. Second, we apply a HiFi++ GAN waveform restorer trained as a generalist and then specialized into eight instrument-specific experts.

Mehmet SÖYLEMEZ

This study investigates the musical and cultural continuities among Turkish-speaking Anatolian Greeks who were resettled in Greece following the 1923 Greco–Turkish Population Exchange. It aims to understand how these displaced communities have preserved, transformed, and reinterpreted their Anatolian musical heritage as part of their collective memory and identity reconstruction processes. The research adopts a qualitative ethnomusicological methodology, combining fieldwork, oral history, and archival analysis. Field studies conducted between 2018 and 2025 in more than seventy villages—particularly in Ioannina, Western Macedonia, and Eastern Thrace—include in-depth interviews, participant observations, and live musical recordings. These empirical materials are complemented by an extensive literature review of historical sources, musical manuscripts, and previous scholarship on migration, identity, and cultural hybridity. The theoretical framework draws on Stuart Hall’s cultural identity theory, Homi Bhabha’s concept of the “third space”, and Berry’s acculturation model, situating music as both a medium of resistance and a repository of memory. Analysis of early musical publications such as Mousikon Apanthisma (1856–1873) reveals that Turkish-speaking communities historically maintained a hybrid repertoire encompassing Turkish, Greek, and Byzantine elements. Findings demonstrate that music functions as a transgenerational mechanism of cultural continuity: while younger generations predominantly use Greek in daily life, Turkish persists through song, ritual, and communal gatherings. This sustained musical bilingualism reflects an enduring emotional geography connecting Anatolia and Greece. Ultimately, the study concludes that the legacy of Anatolian culture survives in Greece as a living soundscape—an evolving synthesis of displacement, memory, and hybridity rather than a static remnant of the past.

Xianghui Zou, Ziqi Jin, Ziqi Jin et al.

ObjectivesTo explore the research hotspots and trends in the field of music therapy and pain based on bibliometrics and to provide reference and guidance for the current status and development of research in this field.MethodsUsing the Web of Science Core Collection (WOSCC) and Pubmed databases as data sources, we used VOSviewer and CiteSpace, R language combined, way to visualize and analyze the number of publications, countries, institutions, researchers, keywords, and literature in the fixed field from 2004 to 2024.ResultsPublication volume increased each year, with 2013 having the highest average citation rate. Lead authors included Bradt Joke, Silverman Michael J., Warth Marco, and Kessler Jens. the Journal of Music Therapy ranked first in terms of published papers. The United States leads in research but lacks national collaboration. Research topics have evolved from anxiety, cancer, and pain management to rehabilitation, virtual reality, and quality of life.ConclusionThis study presents a roadmap for optimizing the clinical application of music therapy, addresses gaps in protocol standardization, advocates for cross-national collaboration to improve research quality, and provides important insights and guidance for future music therapy and pain research and applications.

Yash Bhake, Ankit Anand, Preeti Rao

This paper presents an attempt to study the aesthetics of North Indian Khayal music with reference to the flexibility exercised by artists in performing popular compositions. We study expressive timing and pitch variations of the given lyrical content within and across performances and propose computational representations that can discriminate between different performances of the same song in terms of expression. We present the necessary audio processing and annotation procedures, and discuss our observations and insights from the analysis of a dataset of two songs in two ragas each rendered by ten prominent artists.

Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth et al.

Recent years have seen a boom in computational approaches to music analysis, yet each one is typically tailored to a specific analytical domain. In this work, we introduce AnalysisGNN, a novel graph neural network framework that leverages a data-shuffling strategy with a custom weighted multi-task loss and logit fusion between task-specific classifiers to integrate heterogeneously annotated symbolic datasets for comprehensive score analysis. We further integrate a Non-Chord-Tone prediction module, which identifies and excludes passing and non-functional notes from all tasks, thereby improving the consistency of label signals. Experimental evaluations demonstrate that AnalysisGNN achieves performance comparable to traditional static-dataset approaches, while showing increased resilience to domain shifts and annotation inconsistencies across multiple heterogeneous corpora.

Anna Kruspe

Large Language Models (LLMs) reflect the biases in their training data and, by extension, those of the people who created this training data. Detecting, analyzing, and mitigating such biases is becoming a focus of research. One type of bias that has been understudied so far are geocultural biases. Those can be caused by an imbalance in the representation of different geographic regions and cultures in the training data, but also by value judgments contained therein. In this paper, we make a first step towards analyzing musical biases in LLMs, particularly ChatGPT and Mixtral. We conduct two experiments. In the first, we prompt LLMs to provide lists of the "Top 100" musical contributors of various categories and analyze their countries of origin. In the second experiment, we ask the LLMs to numerically rate various aspects of the musical cultures of different countries. Our results indicate a strong preference of the LLMs for Western music cultures in both experiments.

Liam Pond, Ichiro Fujinaga

This study evaluates the baseline capabilities of Large Language Models (LLMs) like ChatGPT, Claude, and Gemini to learn concepts in music theory through in-context learning and chain-of-thought prompting. Using carefully designed prompts (in-context learning) and step-by-step worked examples (chain-of-thought prompting), we explore how LLMs can be taught increasingly complex material and how pedagogical strategies for human learners translate to educating machines. Performance is evaluated using questions from an official Canadian Royal Conservatory of Music (RCM) Level 6 examination, which covers a comprehensive range of topics, including interval and chord identification, key detection, cadence classification, and metrical analysis. Additionally, we evaluate the suitability of various music encoding formats for these tasks (ABC, Humdrum, MEI, MusicXML). All experiments were run both with and without contextual prompts. Results indicate that without context, ChatGPT with MEI performs the best at 52%, while with context, Claude with MEI performs the best at 75%. Future work will further refine prompts and expand to cover more advanced music theory concepts. This research contributes to the broader understanding of teaching LLMs and has applications for educators, students, and developers of AI music tools alike.

Richa Namballa, Giovana Morais, Magdalena Fuentes

Musical source separation (MSS) has recently seen a big breakthrough in separating instruments from a mixture in the context of Western music, but research on non-Western instruments is still limited due to a lack of data. In this demo, we use an existing dataset of Brazilian sama percussion to create artificial mixtures for training a U-Net model to separate the surdo drum, a traditional instrument in samba. Despite limited training data, the model effectively isolates the surdo, given the drum's repetitive patterns and its characteristic low-pitched timbre. These results suggest that MSS systems can be successfully harnessed to work in more culturally-inclusive scenarios without the need of collecting extensive amounts of data.

Mahmut Yontar

This study analyzes the first movement of Igor Stravinsky’s neoclassical work, "Concerto for Piano and Winds," from musical and structural perspectives. By thoroughly examining the musical structure of the piece, it highlights Stravinsky’s contributions to the concerto genre and positions this work within his neoclassical approach. The analysis was conducted using qualitative research methods, specifically document analysis techniques. The aim of the study is to examine the score and audio recordings of the work to identify its structural features and prominent musical elements. The findings reveal Stravinsky’s subjective approaches to harmonic structures and musical materials, as well as the innovative perspectives he brought to the concerto genre with this work. Additionally, it has been determined that the piece departs from the classical concerto form through certain musical transitions characteristic of the Baroque period and the solo-ensemble dynamics found in the Baroque concerto grosso. The results also detail Stravinsky’s innovations in the use of tonality, rhythmic diversity, and orchestration techniques. These structural features are significant elements that reinforce the dynamic and dramatic atmosphere of the work. Furthermore, the use of the piano in the piece goes beyond the typical soloist role, establishing a rich dialogue with the orchestra. This study sheds light on how this work reflects the evolution of Stravinsky’s musical language and the characteristic features of the neoclassical period, illuminating the innovations it introduced into the music literature.

Ricardo Mazzini Bordini, Marcos da Silva Sampaio

Este trabalho objetiva encontrar encadeamentos relacionados por semitom na peça em epígrafe seguindo o modelo do espaço atonal de encadeamentos. A partir da tese de doutorado de Deborah How identifica-se problemas analíticos ao escandir a série e faz-se uma perquirição das propriedades dos tetracordes e seus tricordes derivados. Escolhe-se trechos selecionados para investigar a presença de encadeamentos por semitom, colhe-se os dados avaliando suas possíveis configurações, faz-se um levantamento de distribuição estatística e conclui-se compilando os dados relevantes em perspectiva.

Ilaria Manco, Justin Salamon, Oriol Nieto

Audio-text contrastive models have become a powerful approach in music representation learning. Despite their empirical success, however, little is known about the influence of key design choices on the quality of music-text representations learnt through this framework. In this work, we expose these design choices within the constraints of limited data and computation budgets, and establish a more solid understanding of their impact grounded in empirical observations along three axes: the choice of base encoders, the level of curation in training data, and the use of text augmentation. We find that data curation is the single most important factor for music-text contrastive training in resource-constrained scenarios. Motivated by this insight, we introduce two novel techniques, Augmented View Dropout and TextSwap, which increase the diversity and descriptiveness of text inputs seen in training. Through our experiments we demonstrate that these are effective at boosting performance across different pre-training regimes, model architectures, and downstream data distributions, without incurring higher computational costs or requiring additional training data.

Karn N. Watcharasupat, Chih-Wei Wu, Iroro Orife

Cinematic audio source separation (CASS), as a standalone problem of extracting individual stems from their mixture, is a fairly new subtask of audio source separation. A typical setup of CASS is a three-stem problem, with the aim of separating the mixture into the dialogue (DX), music (MX), and effects (FX) stems. Given the creative nature of cinematic sound production, however, several edge cases exist; some sound sources do not fit neatly in any of these three stems, necessitating the use of additional auxiliary stems in production. One very common edge case is the singing voice in film audio, which may belong in either the DX or MX or neither, depending heavily on the cinematic context. In this work, we demonstrate a very straightforward extension of the dedicated-decoder Bandit and query-based single-decoder Banquet models to a four-stem problem, treating non-musical dialogue, instrumental music, singing voice, and effects as separate stems. Interestingly, the query-based Banquet model outperformed the dedicated-decoder Bandit model. We hypothesized that this is due to a better feature alignment at the bottleneck as enforced by the band-agnostic FiLM layer. Dataset and model implementation will be made available at https://github.com/kwatcharasupat/source-separation-landing.

Li-Yang Tseng, Tzu-Ling Lin, Hong-Han Shuai et al.

Nowadays, humans are constantly exposed to music, whether through voluntary streaming services or incidental encounters during commercial breaks. Despite the abundance of music, certain pieces remain more memorable and often gain greater popularity. Inspired by this phenomenon, we focus on measuring and predicting music memorability. To achieve this, we collect a new music piece dataset with reliable memorability labels using a novel interactive experimental procedure. We then train baselines to predict and analyze music memorability, leveraging both interpretable features and audio mel-spectrograms as inputs. To the best of our knowledge, we are the first to explore music memorability using data-driven deep learning-based methods. Through a series of experiments and ablation studies, we demonstrate that while there is room for improvement, predicting music memorability with limited data is possible. Certain intrinsic elements, such as higher valence, arousal, and faster tempo, contribute to memorable music. As prediction techniques continue to evolve, real-life applications like music recommendation systems and music style transfer will undoubtedly benefit from this new area of research.

Ewa Partyga

Artykuł zestawia ze sobą wybrane narracje historycznoteatralne i historycznomuzyczne interpretujące rolę muzyki scenicznej op. 23 Edvarda Griega, stworzonej na potrzeby prapremiery Peera Gynta Henrika Ibsena (1876), w recepcji tego utworu i ustanawianiu jego znaczenia. W pierwszej części przedstawiono współpracę amatorskich i profesjonalnych środowisk muzycznych i teatralnych, które tworzyły norweski teatr jako miejsce konstruowania tożsamości narodowej, oraz wprzęgnięte w ten cel tradycje muzyczno-teatralne, ze szczególnym uwzględnieniem popularnego gatunku syngespill. Omówiono także muzyczne doświadczenia Ibsena zgromadzone w trakcie dziesięcioletniej pracy w teatrach w Bergen i w Christianii, które wpłynęły na jego oczekiwania wobec kompozytora. Druga część jest poświęcona formom współpracy Griega ze środowiskiem teatralnym w Christianii. W trzeciej części w centrum uwagi są istotne ogniwa procesu powstawania prapremierowej inscenizacji: list Ibsena do Griega jako świadectwo muzyczno teatralnej wyobraźni pisarza, list Griega do dyrygującego prawykonaniem Johana Hennuma jako dowód troski kompozytora o teatralne działanie muzyki, rola doświadczonego w inscenizowaniu utworów muzyczno-dramatycznych i oper reżysera Ludviga Josephsona jako autora całościowej koncepcji prapremiery, która miała przyciągnąć do teatru szeroką publiczność. W ostatniej części określono czynniki wpływające na performatywną otwartość i siłę oddziaływania muzyki do Peera Gynta stworzonej przez Griega w wielu wariantach i funkcjonującej od początku w rozmaitych kontekstach. Zestawienie historycznoteatralnych i historycznomuzycznych narracji przekonuje, że Peer Gynt Griega jako dzieło artystyczne, fenomen kulturowy i przedmiot refleksji naukowej stanowi materiał, który w nowym świetle mogą ukazać badania o charakterze interdyscyplinarnym. Uzupełnieniem artykułu jest aneks zawierający przekład omawianego w drugiej części listu Ibsena do Griega z 23 stycznia 1874 roku.

Carmen H Logie, Sarah Van Borek, Anoushka Lad et al.

Adolescent perspectives are crucially important for developing sustainable solutions to address climate change yet remain overlooked in the literature, particularly in low and middle-income contexts. Kenya is an important context to explore youth climate solutions, as youth constitute the fastest growing population facing climate change-related challenges, such as extreme weather events (e.g., droughts) and issues of water, food, and sanitation security. This manuscript details a methodology for participatory mapping on climate-related issues that was co-developed with Kenyan youth and community-based organizations in Kenya. The aim of this paper is to describe the design of a multi-media participatory mapping tool to identify and address the interconnections between social, health, and environmental well-being with very young adolescents (aged 10-14 years) in six geographically-diverse, climate-affected regions of Kenya (Nairobi, Kisumu, Kilifi, Naivasha, Isiolo, and Kalobeyei Refugee Settlement). The authors describe methods used to develop a strengths-based multi-media participatory mapping approach that combines user-friendly geographic information system (GIS) technology with arts-based methods (dance, drawing, music, video). The aim is to share these methods and process of co-development to inform future participatory mapping approaches with youth climate-related issues.

Mojahed Gholami

Amir Khosrow Dehlavi (725-651 AH.) is one of the most knowledgeable and capable writers and poets and at the same time one of the lesser known figures of Persian literature. Amir Khosrow, was born in 1253 in a place called Patiyali, Uttar Pradesh. His real name was Ab'ul Hasan Yamin al-Din Khosrow whereas Amir Khosrow was his pen name. Also known as Amir Khosrow Dehlavi, this creative classical poet was associated with the royal empires of more than seven rulers of Delhi. The life history of Amir Khosrow is truly an inspiring one and he is considered to be one of the first recorded Indian dignitaries who are also a household name. Known for his immense contribution in literature and music, this legendary personality was born of a Turkish father and an Indian mother in a village in India. His fame in our time is much less than his fame in his time. The lack of accurate editions of his work and the scant research on his life, writings, and poems confirm this claim. Amir Khosrow has tended to innovate in music and rhetoric. He has innovations in these two areas. In the third article of “Rasa'il al-Ijaz” or “Ijaz-e Khosrawi”, entitled "Fi al-Latayf men al-Masnouāt", this poet has spoken about the word ornaments created by him. He also in this article talked about the changes he made in the old word ornaments. Among the authors of Persian rhetorical books, Seyf Jam Herawi, the author of “Jame 'al-Sana'i va al-Aouzan” (before 778 AH), for the first time attributed inventions in rhetoric to him. Also this work has been continued by the Vaez Kashfi in “Badāye al-Afkar fi Sanaye al-Ash'ar” (between 875 and 910 AH.), Azad Belgerami in “Sobhat al-Marjan fi Asāre Hendoustan” (1177 AH.) and “Ghezlan al-Hind” (1178 AH.), and Allameh Shebli Nomani (d. 1332 AH.) in the “Sher Al-Ajam”. Thus, a number of rhetorical inventions have been attributed to this poet. These speech ornaments have Arabic names. This article has been written with the aim of narrating and analyzing opinions about Amir Khosrow's rhetorical inventions. The method was analytical-descriptive and based on library sources. First, unknown rhetorical inventions are defined. Then the background of those inventions and similar ones in Persian rhetorical works are analyzed. Because it should be clarified whether their attribution to Amir Khosrow is correct or not? The impact of these inventions on the aesthetics of poetry has also been investigated.

Rodrigo Lara Alonso

El objetivo central de este artículo es examinar el uso que el compositor cubano Leo Brouwer hace de la construcción motívica en su Concierto Elegíaco. En primer lugar, se analizan los conceptos de motivo y célula a partir de las definiciones propuestas por algunos teóricos musicales del siglo XX. Se muestra que una célula —entendida como un material musical mínimo— puede ser también un motivo y se propone el término de construcción motívica para referirse al proceso con el que se acumula con motivos una obra musical. Posteriormente, se analiza el empleo que Leo Brouwer hace de la construcción motívica con algunas composiciones tempranas. A partir del análisis del Concierto Elegíaco se muestra que el tratamiento de su célula motívica (un intervalo de segunda) a) se nutre de elementos musicales afrocubanos, materia prima de la estética brouweriana; b) se sirve de la autocita, recurso con el que Brouwer usa fragmentos de composiciones anteriores para la creación de nuevas obras; c) forma parte de una etapa compositiva autodenominada por Leo Brouwer como nueva simplicidad —contemporánea del posminimalismo.

Luigi Dei

This essay aims to stimulate reflection on the creativity characterising homo sapiens in the different realms in which it occurs. Over recent decades scholarly research into creativity has extended the original concept, restricted to geniuses, to a broader field that encompasses the qualities and abilities of every individual, in line with a democratisation of the creative act. However, the aim of this contribution is to illustrate the creativity of geniuses, referring to examples in various fields, according to Poincaré’s definition of connecting pre-existing elements into new combinations that are novel and useful. The objective of this study is to show that pre-existing elements can be found in works of art, literature, poetry, and music, as well as in scientific discoveries or inventions. Having demonstrated the existence of concrete and real analogies in the various – and apparently profoundly different – fields of human creativity, a second objective was to construct a convincing proof of a notion of a culture characterised by an essential unity, without any separation between humanities and sciences. I trust that the analysis of the creative acts that generated Picasso’s Les Demoiselles d’Avignon, Michelangelo’s Vaticano Pietà, Primo Levi’s The Periodic Table, Giacomo Leopardi’s L’infinito (The infinite) and Wisława Szymborska’s Liczba Pi (Pi), the beginning of Beethoven’s Fifth Symphony and Brahms’ Fourth Symphony the finale of Stravinsky’s  Sacre du Printemps, the discovery of X-rays by Wilhelm Conrad Röntgen and of the therapeutic properties of lithium salts for psychiatric disorders by John Frederick Joseph Cade, the invention of incandescent light bulbs by Thomas Alva Edison and many other inventors and of the electronic television by Philo Taylor Farnsworth, may succeed in achieving the first objective and, by extension, the second also.

Sofia Nuria Lisa, Endang Dwiyanti

ABSTRACT Increased employee productivity can provide benefits for the company. However, isntability of employee productivity can cause some companies to find losses. Accompaniment music at work can be used as a solution to increase employee productivity. This study aims to determine the effect of accompaniment music at work on employee productivity in few companies. This study used a literature study method by reviewing 16 articles obtained from Google Scholar. The criteria for the articles used in this study discussed topics related to accompaniment music at work and employee productivity in several companies at least the last 10 years. Some data that have been collected will be analyzed using a description analysis flow. The results of the study showed that accompaniment music at work has a significant effect on employee productivity in several companies, that productivity was influenced by work environment factors, work spirit, cooperation, work loyalty, work speed, work stress, workload, fatigue, comfort, education level, age, work experience, gender, training, mental, and physical abilities of employees, as well as the relationship between superiors and subordinates. The form of increased employee productivity after accompaniment music while working are work being completed quickly and the results of the product or goods produced exceeding the target.    ABSTRAK Meningkatnya produktivitas karyawan dapat memberikan keuntungan bagi perusahaan. Namun karena produktivitas karyawan yang cenderung tidak stabil, menyebabkan beberapa perusahaan mengalami kerugian. Musik pengiring kerja dapat dijadikan sebagai salah satu solusi untuk meningkatkan produktivitas karyawan. Penelitian ini bertujuan untuk mengetahui pengaruh musik pengiring kerja terhadap produktivitas karyawan di beberapa perusahaan. Metode penelitian yang digunakan dalam penelitian ini adalah metode studi literatur dengan mengkaji sebanyak 16 artikel yang didapatkan dari google scholar. Kriteria artikel yang digunakan adalah artikel yang membahas mengenai topik yang berhubungan dengan musik pengiring kerja dan produktivitas karyawan di beberapa perusahaan pada 10 tahun terakhir. Beberapa data yang dikumpulkan akan dianalisis menggunakan alur analisis deskripsi. Hasil pengkajian menunjukkan bahwa musik pengiring kerja berpengaruh secara signifikan terhadap produktivitas karyawan di beberapa perusahaan, dimana produktivitas ini dipengaruhi oleh faktor lingkungan kerja, semangat kerja, kerjasama, loyalitas kerja, kecepatan kerja, stress kerja, beban kerja, kelelahan, kenyamanan, tingkat pendidikan, usia, pengalaman kerja, jenis kelamin, pelatihan, mental dan kemampuan fisik karyawan, serta hubungan antara atasan dan bawahan. Produktivitas karyawan dapat meningkat setelah diberi perlakuan mendengarkan musik berupa pekerjaan menjadi cepat selesai dan hasil produk atau barang yang dihasilkan melebihi target.

Axel Chemla--Romeu-Santos, Philippe Esling

The development of generative Machine Learning (ML) models in creative practices, enabled by the recent improvements in usability and availability of pre-trained models, is raising more and more interest among artists, practitioners and performers. Yet, the introduction of such techniques in artistic domains also revealed multiple limitations that escape current evaluation methods used by scientists. Notably, most models are still unable to generate content that lay outside of the domain defined by the training dataset. In this paper, we propose an alternative prospective framework, starting from a new general formulation of ML objectives, that we derive to delineate possible implications and solutions that already exist in the ML literature (notably for the audio and musical domain). We also discuss existing relations between generative models and computational creativity and how our framework could help address the lack of creativity in existing models.