Hasil untuk "Literature on music"

Stephen Ni-Hahn, Chao Péter Yang, Mingchen Ma et al.

Artificial Intelligence (AI) for music generation is undergoing rapid developments, with recent symbolic models leveraging sophisticated deep learning and diffusion model algorithms. One drawback with existing models is that they lack structural cohesion, particularly on harmonic-melodic structure. Furthermore, such existing models are largely "black-box" in nature and are not musically interpretable. This paper addresses these limitations via a novel generative music framework that incorporates concepts of Schenkerian analysis (SchA) in concert with a diffusion modeling framework. This framework, which we call ProGress (Prolongation-enhanced DiGress), adapts state-of-the-art deep models for discrete diffusion (in particular, the DiGress model of Vignac et al., 2023) for interpretable and structured music generation. Concretely, our contributions include 1) novel adaptations of the DiGress model for music generation, 2) a novel SchA-inspired phrase fusion methodology, and 3) a framework allowing users to control various aspects of the generation process to create coherent musical compositions. Results from human experiments suggest superior performance to existing state-of-the-art methods.

Yashan Wang, Shangda Wu, Jianhuai Hu et al.

We introduce NotaGen, a symbolic music generation model aiming to explore the potential of producing high-quality classical sheet music. Inspired by the success of Large Language Models (LLMs), NotaGen adopts pre-training, fine-tuning, and reinforcement learning paradigms (henceforth referred to as the LLM training paradigms). It is pre-trained on 1.6M pieces of music in ABC notation, and then fine-tuned on approximately 9K high-quality classical compositions conditioned on "period-composer-instrumentation" prompts. For reinforcement learning, we propose the CLaMP-DPO method, which further enhances generation quality and controllability without requiring human annotations or predefined rewards. Our experiments demonstrate the efficacy of CLaMP-DPO in symbolic music generation models with different architectures and encoding schemes. Furthermore, subjective A/B tests show that NotaGen outperforms baseline models against human compositions, greatly advancing musical aesthetics in symbolic music generation.

Takuya Hasumi, Tatsuya Komatsu, Yusuke Fujita

We propose music tagging with classifier chains that model the interplay of music tags. Most conventional methods estimate multiple tags independently by treating them as multiple independent binary classification problems. This treatment overlooks the conditional dependencies among music tags, leading to suboptimal tagging performance. Unlike most music taggers, the proposed method sequentially estimates each tag based on the idea of the classifier chains. Beyond the naive classifier chains, the proposed method groups the multiple tags by category, such as genre, and performs chains by unit of groups, which we call \textit{classifier group chains}. Our method allows the modeling of the dependence between tag groups. We evaluate the effectiveness of the proposed method for music tagging performance through music tagging experiments using the MTG-Jamendo dataset. Furthermore, we investigate the effective order of chains for music tagging.

Xinyi Tong, Yiran Zhu, Jishang Chen et al.

Video-to-Music generation seeks to generate musically appropriate background music that enhances audiovisual immersion for videos. However, current approaches suffer from two critical limitations: 1) incomplete representation of video details, leading to weak alignment, and 2) inadequate temporal and rhythmic correspondence, particularly in achieving precise beat synchronization. To address the challenges, we propose Video Echoed in Music (VeM), a latent music diffusion that generates high-quality soundtracks with semantic, temporal, and rhythmic alignment for input videos. To capture video details comprehensively, VeM employs a hierarchical video parsing that acts as a music conductor, orchestrating multi-level information across modalities. Modality-specific encoders, coupled with a storyboard-guided cross-attention mechanism (SG-CAtt), integrate semantic cues while maintaining temporal coherence through position and duration encoding. For rhythmic precision, the frame-level transition-beat aligner and adapter (TB-As) dynamically synchronize visual scene transitions with music beats. We further contribute a novel video-music paired dataset sourced from e-commerce advertisements and video-sharing platforms, which imposes stricter transition-beat synchronization requirements. Meanwhile, we introduce novel metrics tailored to the task. Experimental results demonstrate superiority, particularly in semantic relevance and rhythmic precision.

Piotr Dahlig

Charles Spence, Nicola Di Stefano, Felipe Reinoso-Carvalho et al.

Auditory branding is undoubtedly becoming more important across a range of sectors. One area, in particular, that has recently seen significant growth concerns the introduction of music and soundscapes that have been specifically designed to match a particular scent (what one might think of as “audio scents” or “sonic scents”). This represents an exciting new approach to the sensory marketing of fragrance and for industries with strategic sensory goals, such as cosmetics. Crucially, techniques such as the semantic differential technique, as well as the emerging literature on crossmodal correspondences, offer both a mechanistic understanding of, and a practical framework for, those wishing to rigorously align the connotative meaning and conceptual/emotional/sensory associations of sound and scent. These developments have enabled those working in the creative industries to start moving beyond previously popular approaches to matching, or translating between the senses, that were traditionally often based on the idiosyncratic phenomenon of synaesthesia, toward a more scientific approach while nevertheless still enabling/requiring a healthy dose of artistic inspiration. In this narrative historical review, we highlight the various approaches to the systematic matching of sound with scent and review the various marketing activations that have appeared in this space recently.

Elżbieta Witkowska-Zaremba

Niniejszy artykuł jest szkicem problematyki szerszego projektu na temat historiografii muzycznej i jej etapu przednowożytnego. Nie wyczerpuje zatem tematu, sygnalizuje tylko „work in progress”. Przyjmując za punkt wyjścia klasyfikację muzyki zaproponowaną przez Ottona Gibela (1660), który wyróżnił „muzykę historyczną” (musica historica vel didactica) jako dziedzinę teorii muzyki badającą „pochodzenie i rozwój zagadnień związanych z muzyką”, autorka śledzi wybrane wątki związane z myśleniem o historii w traktatach takich autorów, jak Johannes Cotto/Affligemensis, Johannes de Muris, Johannes Boen, tekstach reprezentujących tradycję Johannesa Hollandrina, wreszcie tekstach Johannesa Tinctorisa i Adama z Fuldy. Autorka konkluduje, że wkład średniowiecznych teoretyków muzyki w podwaliny nowożytnej historiografii muzycznej polegał głównie na dostarczeniu głównych punktów orientacyjnych, wokół których później rozwijało się myślenie o historii. Te punkty orientacyjne to: wiara w czasową ciągłość „ars musica”; ustalenie punktu odniesienia i określenie osi czasu; zdefiniowanie własnej tożsamości kulturowej; postrzeganie i konceptualizacja zmian zachodzących w czasie; konstruowanie obrazu przeszłości.  

Yanxu Chen, Linshu Huang, Tian Gou

In recent years, artificial intelligence (AI) has made significant progress in the field of music generation, driving innovation in music creation and applications. This paper provides a systematic review of the latest research advancements in AI music generation, covering key technologies, models, datasets, evaluation methods, and their practical applications across various fields. The main contributions of this review include: (1) presenting a comprehensive summary framework that systematically categorizes and compares different technological approaches, including symbolic generation, audio generation, and hybrid models, helping readers better understand the full spectrum of technologies in the field; (2) offering an extensive survey of current literature, covering emerging topics such as multimodal datasets and emotion expression evaluation, providing a broad reference for related research; (3) conducting a detailed analysis of the practical impact of AI music generation in various application domains, particularly in real-time interaction and interdisciplinary applications, offering new perspectives and insights; (4) summarizing the existing challenges and limitations of music quality evaluation methods and proposing potential future research directions, aiming to promote the standardization and broader adoption of evaluation techniques. Through these innovative summaries and analyses, this paper serves as a comprehensive reference tool for researchers and practitioners in AI music generation, while also outlining future directions for the field.

Bradford Derby, Lucas Dunker, Samarth Galchar et al.

Source separation is the process of isolating individual sounds in an auditory mixture of multiple sounds [1], and has a variety of applications ranging from speech enhancement and lyric transcription [2] to digital audio production for music. Furthermore, Automatic Music Transcription (AMT) is the process of converting raw music audio into sheet music that musicians can read [3]. Historically, these tasks have faced challenges such as significant audio noise, long training times, and lack of free-use data due to copyright restrictions. However, recent developments in deep learning have brought new promising approaches to building low-distortion stems and generating sheet music from audio signals [4]. Using spectrogram masking, deep neural networks, and the MuseScore API, we attempt to create an end-to-end pipeline that allows for an initial music audio mixture (e.g...wav file) to be separated into instrument stems, converted into MIDI files, and transcribed into sheet music for each component instrument.

Lilian Marey, Bruno Sguerra, Manuel Moussallam

While the topic of listening context is widely studied in the literature of music recommender systems, the integration of regular user behavior is often omitted. In this paper, we propose PACE (PAttern-based user Consumption Embedding), a framework for building user embeddings that takes advantage of periodic listening behaviors. PACE leverages users' multichannel time-series consumption patterns to build understandable user vectors. We believe the embeddings learned with PACE unveil much about the repetitive nature of user listening dynamics. By applying this framework on long-term user histories, we evaluate the embeddings through a predictive task of activities performed while listening to music. The validation task's interest is two-fold, while it shows the relevance of our approach, it also offers an insightful way of understanding users' musical consumption habits.

Roser Batlle-Roca, Wei-Hsiang Liao, Xavier Serra et al.

Recent advancements in music generation are raising multiple concerns about the implications of AI in creative music processes, current business models and impacts related to intellectual property management. A relevant discussion and related technical challenge is the potential replication and plagiarism of the training set in AI-generated music, which could lead to misuse of data and intellectual property rights violations. To tackle this issue, we present the Music Replication Assessment (MiRA) tool: a model-independent open evaluation method based on diverse audio music similarity metrics to assess data replication. We evaluate the ability of five metrics to identify exact replication by conducting a controlled replication experiment in different music genres using synthetic samples. Our results show that the proposed methodology can estimate exact data replication with a proportion higher than 10%. By introducing the MiRA tool, we intend to encourage the open evaluation of music-generative models by researchers, developers, and users concerning data replication, highlighting the importance of the ethical, social, legal, and economic consequences. Code and examples are available for reproducibility purposes.

Giusy Caruso

In questo ultimo ventennio, lo studio della performance musicale si sta sviluppando su diversi fronti. All’approccio etnomusicologico, diretto all’analisi della performance nelle tradizioni musicali extraeuropee, si sono affiancati i ‘performance studies’, che hanno portato alla ‘svolta performativa’ e alla ‘svolta artistica’ e, quindi, alla nascita della ricerca artistica musicale incentrata a indagare il processo creativo della performance nella tradizione musicale occidentale. Ma quali sono nello specifico le nuove prospettive di studio della performance musicale rispetto alle domande di ricerca, agli obiettivi, ai metodi e ai risultati della ricerca artistica musicale? Il presente articolo offre una panoramica dei diversi approcci di studio della performance musicale, restringendo il campo ai metodi di analisi della performance di una composizione musicale scritta nell’ambito della ricerca artistica. Nel definire il percorso che determina la trasformazione della pratica musicale in ricerca sulla performance musicale, verranno evidenziate le problematiche relative alla scelta dei metodi, proponendo le divergenze e le convergenze dell’approccio strettamente artistico rispetto all’approccio scientifico. Saranno, quindi, presentati gli obiettivi della ricerca artistica musicale e un metodo misto che integra l’approccio analitico-performativo e l’approccio analitico-empirico. L’applicazione del digitale per la documentazione e l’analisi del gesto del performer sarà tema di discussione per far emergere le potenzialità del dialogo tra arte, scienza e tecnologia, foriero di innovative prospettive per lo studio della performance musicale nella ricerca artistica.

Alyona R. Tychinina. , Nataliia V. Nikoriak

The current postnonclassical methodological situation draws attention to interdisciplinary practices in literary texts analysis, revealing a significant number of “interdiscursive configurations”. The purpose of this research is to analyze the short story “Thirst for Music” by one of the great intellectuals of the Ukrainian emigration, Viktor Petrov-Domontovych (1894–1969), in the aspect of interdisciplinary methodology. The research tasks are to outline the specifics of interdiscursive methodology and interdiscursive analysis of a literary text, in order to identify V. Domontovych’s novel interdiscursive codes. The chosen short story determines the author’s idiom: biographism, fragmentation, intermediality, intertextuality. Accordingly, the leading methodology of the study is interdiscursivity. It involves the use of biographical, hermeneutical, intertextual, and intermedial research methods. The study is based on the research of M. Foucault, V. Cherniavska, Y. Shevelev, I. Ilyin and others. The work outlines a set of discourses important for the general concept of the novel and evaluates their interaction in the discursive polyphony of “Thirst for Music”: biographical (a fragment of Rilke’s biography), intermedial (music, sculpture), intertextual (Rainer Maria Rilke’s Stories of the Good God, Rilke’s correspondence with Magda von Huttingberg), and architectural (Biographical novella fragment). This example convincingly proves that postmodernist methodology is productive in analyzing the literature of another cultural epoch, in this case, the modernist one. The article under studies focuses on the influence of postmodernism on literary methodology in terms of the concept of interdiscursivity. The purpose of the interdiscursive analysis is the reconstruction of all the discursive layers involved (hidden) by the author. The methodology suggests the identification of a broad range of significant bibliographical, cultural, artistic (intermedial and intertextual) architextual insertions and allusions. Through decoding the “interdiscursive configurations”, the article lays particular emphasis on the bibliographical, intertextual, intermedial, and narrative specifics of the text by the Ukrainian emigrant writer Victor Petrov-Domontovych “Thirst for Music”. It also reveals the intertextual connection of V. Domontovych’s story with Rainer Maria Rilke’s “Stories of God”, as well as Rilke’s correspondence with Magda von Huttingberg. The imagological portrait of Rilke, reconstructed from the short story, may be regarded as the essential interpretant of “interdiscursive intertextuality”. The interdiscursive analysis makes it possible to trace up directly the peculiarities of the writer’s (Rilke) relationships with his real reader (M. von Huttingberg), as well as to outline the discursive nature of story’s architextuality and its genre marking, both of which form the respective horizons of expectations. A particular attention is drawn to Rilke’s poem “Music” (1918), which condenses a wide range of themes articulated by Domontovych in his short story “Thirst for Music” - music as a special metalanguage and a timeless format of music capable of transmitting human feelings. Therefore, the musical key to reading this novel can be Domontovych’s consonance with Rilke. The “fragmentary integrity” of the short story is substantiated by means of the fragmentary, gender marked narrative, the constellation of passages, subject detail, specific phonetic coloring, tropology, and artistic syntax, all these give the prose text the rhythmic parameters of lyrics. Through synesthesia, the author creatively interprets Rilke’s literary method, leaving some figurative and musical “traces”. The veiled compositions of Handel, Bach, Schumann, and Scarlatti are seen as musical ekphrasis. The author resorts to a kind of “game” with the reader, leaving intertextual and intermedial discourses for him to decode. In this way, several receptive channels of the reader’s imagination are simultaneously activated, including visual (“seeing”), auditory (“hearing”), and kinesthetic (“feeling”).

Pavel Sýkora

Samarth Bhargav, Anne Schuth, Claudia Hauff

We present a study of Tip-of-the-tongue (ToT) retrieval for music, where a searcher is trying to find an existing music entity, but is unable to succeed as they cannot accurately recall important identifying information. ToT information needs are characterized by complexity, verbosity, uncertainty, and possible false memories. We make four contributions. (1) We collect a dataset - $ToT_{Music}$ - of 2,278 information needs and ground truth answers. (2) We introduce a schema for these information needs and show that they often involve multiple modalities encompassing several Music IR subtasks such as lyric search, audio-based search, audio fingerprinting, and text search. (3) We underscore the difficulty of this task by benchmarking a standard text retrieval approach on this dataset. (4) We investigate the efficacy of query reformulations generated by a large language model (LLM), and show that they are not as effective as simply employing the entire information need as a query - leaving several open questions for future research.

Jan Melechovsky, Zixun Guo, Deepanway Ghosal et al.

The quality of the text-to-music models has reached new heights due to recent advancements in diffusion models. The controllability of various musical aspects, however, has barely been explored. In this paper, we propose Mustango: a music-domain-knowledge-inspired text-to-music system based on diffusion. Mustango aims to control the generated music, not only with general text captions, but with more rich captions that can include specific instructions related to chords, beats, tempo, and key. At the core of Mustango is MuNet, a Music-Domain-Knowledge-Informed UNet guidance module that steers the generated music to include the music-specific conditions, which we predict from the text prompt, as well as the general text embedding, during the reverse diffusion process. To overcome the limited availability of open datasets of music with text captions, we propose a novel data augmentation method that includes altering the harmonic, rhythmic, and dynamic aspects of music audio and using state-of-the-art Music Information Retrieval methods to extract the music features which will then be appended to the existing descriptions in text format. We release the resulting MusicBench dataset which contains over 52K instances and includes music-theory-based descriptions in the caption text. Through extensive experiments, we show that the quality of the music generated by Mustango is state-of-the-art, and the controllability through music-specific text prompts greatly outperforms other models such as MusicGen and AudioLDM2.

Peiling Lu, Xin Xu, Chenfei Kang et al.

Generating music from text descriptions is a user-friendly mode since the text is a relatively easy interface for user engagement. While some approaches utilize texts to control music audio generation, editing musical elements in generated audio is challenging for users. In contrast, symbolic music offers ease of editing, making it more accessible for users to manipulate specific musical elements. In this paper, we propose MuseCoco, which generates symbolic music from text descriptions with musical attributes as the bridge to break down the task into text-to-attribute understanding and attribute-to-music generation stages. MuseCoCo stands for Music Composition Copilot that empowers musicians to generate music directly from given text descriptions, offering a significant improvement in efficiency compared to creating music entirely from scratch. The system has two main advantages: Firstly, it is data efficient. In the attribute-to-music generation stage, the attributes can be directly extracted from music sequences, making the model training self-supervised. In the text-to-attribute understanding stage, the text is synthesized and refined by ChatGPT based on the defined attribute templates. Secondly, the system can achieve precise control with specific attributes in text descriptions and offers multiple control options through attribute-conditioned or text-conditioned approaches. MuseCoco outperforms baseline systems in terms of musicality, controllability, and overall score by at least 1.27, 1.08, and 1.32 respectively. Besides, there is a notable enhancement of about 20% in objective control accuracy. In addition, we have developed a robust large-scale model with 1.2 billion parameters, showcasing exceptional controllability and musicality.

Sandra McNulty, Suja Somanadhan, Simona Karpaviciute et al.

Background: Interest in the application of music in the health, social care and community contexts is growing worldwide. There is an emerging body of literature about the positive effects of music on the well-being and social relationships of children and adult populations. Music has also been found to promote social interaction, communication skills, and social-emotional behaviours of children with medically complex care needs. Despite significant advancements in the area, to the authors’ knowledge, this is the first scoping review to investigate the evidence for using music therapy and music-based interventions for children living with rare diseases in the healthcare setting. Therefore, the purpose of this study is to conduct a scoping review of the literature to map out the existing studies about the use of music therapy and music-based interventions with children who have rare diseases in the healthcare setting. This review will also identify gaps in current knowledge and use of these interventions. Method: This study follows the Joanna Briggs Institute’s methodology for scoping reviews, utilising Arksey and O’Malley’s six-stage scoping review framework: 1) identifying the research question; 2) identifying relevant studies; 3) study selection; 4) charting the data; 5) collating, summarising and reporting results; and 6) consulting with relevant stakeholders step. A comprehensive search will be conducted in CINAHL Complete; MEDLINE Complete; Psychology and Behavioral Sciences Collection; and PubMed Central databases. A search strategy with selected inclusion and exclusion criteria will be used to reveal a wide range of evidence. This study will include quantitative, qualitative and mixed research methods studies published in English from 2010 to 2020.

CHEN Wen, WANG Dongliang, XU Yunhao, CHEN Yuping, YANG Youqing

[Purpose/Significance] In order to solve the core problems in the digitization process of cultural and creative works in China, taking cultural and creative works as the research object, this paper constructs a metadata hierarchy model of cultural and creative works based on their internal and external information characteristics. This model is standardized, accurately described, easy to operate and adapted to the needs of management and research, and is useful in preservation, transmission, knowledge transformation and innovation of cultural and creative works. This paper aims to provide possible solutions for the digitization process of cultural and creative works and make the maintenance of artistic information resources feasible, which is conducive to the standardized management of the data of literary and creative works and meets the needs of the research, appreciation and dissemination of literary and creative works. [Method/Process] The CDWA data standard is designed to describe artistic works, including the physical form, digital images and the relationship between time and space, characters, history and culture, etc. At the same time, it also has a unique description of elements for the preservation and management, which lays the foundation for data exchange and sharing. The completeness and comprehensiveness of information description of CDWA is quite consistent with the purpose of systematically and comprehensively describing cultural and creative works. Different from AACR2R and RDA to describe paper literature, electronic resources, music works and micro literature, the main purpose of CCO is to promote the standardization of cultural relics such as artworks and their image description. It is the first set of data content standards in the field of cultural assets. The data content standards of CCO focus on descriptive metadata and normative control of artistic works. Based on the above, this paper builds the meta framework of digital resource construction of cultural and creative works, then based on the data content standard CCO, it catalogues and describes the cultural and creative works designed by teachers and students of School of Art and Design of Wuxi Institute of Technology, China, and then promotes the practice of digital construction. [Results/Conclusions] Based on the discussion and analysis of existing metadata models of art and intangible cultural heritage, a metadata model was formed to describe cultural and creative works from three aspects: basic metadata, management metadata and associated metadata. As an indispensable part of revealing, transforming and innovating the cultural and artistic value of artistic works, this paper constructed a modular and extensible metadata standard and model which is much more suitable for cultural and creative works, and provided solutions for the digitization process of cultural and creative works. What's more, this study plays an important role in preservation and inheritance of characteristic resources. It also promoted the formation of new formats and new models of digital cultural and creative industries and provided data support for the vigorous development of China's cultural and creative industries.

Jorge Calvo-Zaragoza, Alexander Pacha

The International Workshop on Reading Music Systems (WoRMS) is a workshop that tries to connect researchers who develop systems for reading music, such as in the field of Optical Music Recognition, with other researchers and practitioners that could benefit from such systems, like librarians or musicologists. The relevant topics of interest for the workshop include, but are not limited to: Music reading systems; Optical music recognition; Datasets and performance evaluation; Image processing on music scores; Writer identification; Authoring, editing, storing and presentation systems for music scores; Multi-modal systems; Novel input-methods for music to produce written music; Web-based Music Information Retrieval services; Applications and projects; Use-cases related to written music. These are the proceedings of the 2nd International Workshop on Reading Music Systems, held in Delft on the 2nd of November 2019.