Intelligent reflecting surface (IRS) has emerged as a promising technology to reconfigure the radio propagation environment by dynamically controlling wireless signal’s amplitude and/or phase via a large number of reflecting elements. In contrast to the vast literature on studying IRS’s performance gains in wireless communications, we study in this paper a new application of IRS for sensing/localizing targets in wireless networks. Specifically, we propose a new self-sensing IRS architecture where the IRS controller is capable of transmitting probing signals that are not only directly reflected by the target (referred to as the direct echo link), but also consecutively reflected by the IRS and then the target (referred to as the IRS-reflected echo link). Moreover, dedicated sensors are installed at the IRS for receiving both the direct and IRS-reflected echo signals from the target, such that the IRS can sense the direction of its nearby target by applying a customized multiple signal classification (MUSIC) algorithm. However, since the angle estimation mean square error (MSE) by the MUSIC algorithm is intractable, we propose to optimize the IRS passive reflection for maximizing the average echo signals’ total power at the IRS sensors and derive the resultant Cramer-Rao bound (CRB) of the angle estimation MSE. Last, numerical results are presented to show the effectiveness of the proposed new IRS sensing architecture and algorithm, as compared to other benchmark sensing systems/algorithms.
Abstract The rise of AI-generated music has implications for how people derive meaning from the listening experience, including the propensity to imagine a story as music unfolds. Previous research suggests that such narrative listening requires some form of common ground between composer and listener. Therefore, people may be less likely to engage in narrative listening when they believe music is the product of an AI system rather than a human mind. We tested this possibility across two preregistered studies in which US participants (N = 399) listened to several pieces of instrumental music and reported their experience of narrative listening—whether they imagined a story and how engaging it was. When presented with unlabeled, human-composed music, participants reported imagining fewer and less engaging narratives in response to pieces they regarded as more likely computer generated than human composed (Study 1). When we experimentally manipulated the purported composer by labeling human- and AI-composed music clips as either “Human” or “AI” composed, the “AI”-labeled pieces elicited fewer and less engaging narratives than their “Human”-labeled counterparts, regardless of the actual composer (Study 2). Together, these findings suggest that ascribing music to AI is associated with—and can engender—an impoverished listening experience, devoid of the mental narratives that unfold as the composer’s musical choices guide the listener’s imagination. Our findings contribute to an emerging literature on perceptions of artificial creators, with practical implications for listeners, musicians, and policymakers.
The purpose of this report was to review the literature on and closely related to empathy development in music education and to augment music educators’ knowledge of empathy development practices within their own professional contexts. In this review of literature, I explore empathy development in music education by investigating (a) the definitions, types, and characteristics of empathy; (b) empathy education; (c) empathy in the context of musical group interaction; (d) empathy in the context of music ensembles; and (e) empathy development in music education settings. Scholars have suggested that empathy may support positive behaviors including perspective-taking, active listening, helping, and caring for and about others. Due in part to the empathic characteristics of music and interactive music activities, music classrooms provide a potentially empathy-rich environment in which teachers may engage students in empathy development. I end the review by discussing implications and suggested practices for music educators.
Lyria Team, Antoine Caillon, Brian McWilliams
et al.
We introduce a new class of generative models for music called live music models that produce a continuous stream of music in real-time with synchronized user control. We release Magenta RealTime, an open-weights live music model that can be steered using text or audio prompts to control acoustic style. On automatic metrics of music quality, Magenta RealTime outperforms other open-weights music generation models, despite using fewer parameters and offering first-of-its-kind live generation capabilities. We also release Lyria RealTime, an API-based model with extended controls, offering access to our most powerful model with wide prompt coverage. These models demonstrate a new paradigm for AI-assisted music creation that emphasizes human-in-the-loop interaction for live music performance.
Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving forward-backward diffusion processes. However, these methods often struggle to preserve the musical content. Additionally, text instructions alone usually fail to accurately describe the desired music. In this paper, we propose two music editing methods that improve the consistency between the original and edited music by leveraging score distillation. The first method, SteerMusic, is a coarse-grained zero-shot editing approach using delta denoising score. The second method, SteerMusic+, enables fine-grained personalized music editing by manipulating a concept token that represents a user-defined musical style. SteerMusic+ allows for the editing of music into user-defined musical styles that cannot be achieved by the text instructions alone. Experimental results show that our methods outperform existing approaches in preserving both music content consistency and editing fidelity. User studies further validate that our methods achieve superior music editing quality.
This paper presents a new approach to algorithmic composition, called predictive controlled music (PCM), which combines model predictive control (MPC) with music generation. PCM uses dynamic models to predict and optimize the music generation process, where musical notes are computed in a manner similar to an MPC problem by optimizing a performance measure. A feedforward neural network-based assessment function is used to evaluate the generated musical score, which serves as the objective function of the PCM optimization problem. Furthermore, a recurrent neural network model is employed to capture the relationships among the variables in the musical notes, and this model is then used to define the constraints in the PCM. Similar to MPC, the proposed PCM computes musical notes in a receding-horizon manner, leading to feedback controlled prediction. Numerical examples are presented to illustrate the PCM generation method.
El presente trabajo busca trazar paralelismos entre el cine y la música, desde una perspectiva fronteriza y decolonial. Para ello, se eligieron y analizaron algunas películas, con sus bandas sonoras, así como canciones que resuenan con los temas abordados. Construyendo una mirada transversal del cine a través de la música, se buscó cuestionar o desmantelar categorías cruciales para el cine Occidente-centrado, que aún reflejan una nostalgia colonial y persisten en divisiones ideológicas, como entre el «cine-arte» o cine «moderno» y el «resto». Así, el texto se divide en tres secciones centrales y dos conclusivas: Cine visto por la música inserta epistemológicamente el tema, analizando rizomáticamente las fuerzas horizontales y verticales del cine y de la música; Cine-música modal aborda algunas películas-músicas desde una perspectiva transcultural de la música modal, centrándose en sus ciclos de repetición, transformación, así como de muerte y renacimiento simbólicos; Modal, tonal, atonal aborda los cambios que la música y el cine han enfrentado y engendrado, desde las transformaciones de la música modal en tonal y «atonal»; Pequeña coda resume brevemente el camino trazado a lo largo de la obra y Da capo al fine lo concluye. Se espera que el artículo, de carácter ensayístico, pueda contribuir a enriquecer las reflexiones cinematográficas y de otras artes, sobre todo porque parte de una mirada-escucha no especializada, construida a partir de un arte distinto, la música, lo que considero una poderosa y fecunda forma de encuentro, precisamente porque permite el tránsito transcultural y rizomático entre diferentes artes y saberes.
Music and books on Music, Musical instruction and study
Nursalam Nursalam, Anang Santoso, Imam Agus Basuki
et al.
The Makassar Kelong Performance (henceforth abbreviated as MKP) is an oral literary performance presented in the wedding tradition of the Makassar community to convey moral messages. This study aims to narratively and visually highlight the symbolic meaning of the MKP, that represent the values and characteristics of the cultural identity of the Makassar community. Within a qualitative approach, semiotic study was applied to examine the formation of meaning through signs. The research findings emphasized the values representation tied with the MKP’s symbolic meaning, including politeness, sincerity, tenderness, and commitment to the tradition. Additionally, the MKP symbolically portrayed characters of courage, persistence, religiosity, endurance, loyalty, cooperation, and heroism, reflecting the cultural identity of the Makassar community. Symbolic meaning is narratively represented through word forms, tones, music, lights, and sound effects. Furthermore, the visual symbolic meanings of the performance are represented through facial expressions, gestures, attire, movements, costumes, equipment such as rebana, gendang, kecaping, kannong-kannong, bamboo, plates and spoons, fire wicks, and settings. The MKP also has an impact on enhancing the moral values of the Makassar community. This study contributes to the preservation of oral literary traditions and the understanding of local Makassar culture. The contribution offers opportunities to revitalize oral literature and local Makassar culture to ensure their existence.
Background Comfort is a primary goal of healthcare. Theory-informed interventions and measurement are essential for comfort enhancement.Objectives To categorise and synthesise the international literature on the application of Kolcaba’s Comfort Theory in research and practice aiming to promote adults’ comfort.Eligibility criteria Papers reporting the application of Kolcaba’s Comfort Theory on adult participants published in English and Chinese.Sources of evidence MEDLINE, CINAHL, APA PsycInfo, Embase, AMED, Web of Science, Scopus, The Cochrane Library, JBI EBP Database, CNKI, Wan Fang; grey literature of Google Scholar, Baidu Scholar and The Comfort Line were searched from January 1991 to January 2024.Chart methods Following the Joanna Briggs Institute guidance and Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews checklist, two reviewers selected papers and extracted data independently using a standardised chart embedded in NVivo software. A thematic synthesis and a descriptive analysis were provided.Results The review included 359 papers. Approximately two-thirds (n=216, 60.2%) had been published since 2017. The majority of papers (n=316, 88.0%) originated from China, the USA, Turkey, Brazil and Portugal. The use of Kolcaba’s Comfort Theory was dominated in a range of hospital settings (n=263) and with participants suffering neoplasms (n=55). Seven categories of theory application were identified: (I) interventions underpinned by Comfort Theory as the theoretical framework, (II) interventions evaluated by instruments derived from Comfort Theory, (III) descriptive or observational studies of services or practices underpinned by Comfort Theory, (IV) surveys using questionnaires derived from Comfort Theory, (V) questionnaires development or adaption based on Comfort Theory, (VI) qualitative studies interpreted by Comfort Theory and (VII) literature reviews and discussion about Comfort Theory use. The most commonly evaluated interventions included music therapy (n=31), position intervention (n=20) and massage (n=19), and the most commonly used questionnaire was General Comfort Questionnaire (n=109).Conclusions Kolcaba’s Comfort Theory has been largely used in interventions and assessments across a wide range of contexts, providing a set of options for practitioners. However, quantifying evidence is needed through further systematic reviews, and continuous development of Comfort Theory is warranted based on the categorisation by this review.
Hyun-Woong Kim, Jessica Kovar, Jesper Singh Bajwa
et al.
Abstract A growing body of literature has reported the relationship between music and language, particularly between individual differences in perceptual rhythm skill and grammar competency in children. Here, we investigated whether motoric aspects of rhythm processing—as measured by rhythmic finger tapping tasks—also explain the rhythm-grammar connection in 150 healthy young adults. We found that all expressive rhythm skills (spontaneous, synchronized, and continued tapping) along with rhythm discrimination skill significantly predicted receptive grammar skills on either auditory sentence comprehension or grammaticality well-formedness judgment (e.g., singular/plural, past/present), even after controlling for verbal working memory and music experience. Among these, synchronized tapping and rhythm discrimination explained unique variance of sentence comprehension and grammaticality judgment, respectively, indicating differential associations between different rhythm and grammar skills. Together, we demonstrate that even simple and repetitive motor behavior can account for seemingly high-order grammar skills in the adult population, suggesting that the sensorimotor system continue to support syntactic operations.
We present a framework for learning to generate background music from video inputs. Unlike existing works that rely on symbolic musical annotations, which are limited in quantity and diversity, our method leverages large-scale web videos accompanied by background music. This enables our model to learn to generate realistic and diverse music. To accomplish this goal, we develop a generative video-music Transformer with a novel semantic video-music alignment scheme. Our model uses a joint autoregressive and contrastive learning objective, which encourages the generation of music aligned with high-level video content. We also introduce a novel video-beat alignment scheme to match the generated music beats with the low-level motions in the video. Lastly, to capture fine-grained visual cues in a video needed for realistic background music generation, we introduce a new temporal video encoder architecture, allowing us to efficiently process videos consisting of many densely sampled frames. We train our framework on our newly curated DISCO-MV dataset, consisting of 2.2M video-music samples, which is orders of magnitude larger than any prior datasets used for video music generation. Our method outperforms existing approaches on the DISCO-MV and MusicCaps datasets according to various music generation evaluation metrics, including human evaluation. Results are available at https://genjib.github.io/project_page/VMAs/index.html
Antonio Ríos-Vila, Jorge Calvo-Zaragoza, David Rizo
et al.
Optical Music Recognition (OMR) has made significant progress since its inception, with various approaches now capable of accurately transcribing music scores into digital formats. Despite these advancements, most so-called end-to-end OMR approaches still rely on multi-stage processing pipelines for transcribing full-page score images, which entails challenges such as the need for dedicated layout analysis and specific annotated data, thereby limiting the general applicability of such methods. In this paper, we present the first truly end-to-end approach for page-level OMR in complex layouts. Our system, which combines convolutional layers with autoregressive Transformers, processes an entire music score page and outputs a complete transcription in a music encoding format. This is made possible by both the architecture and the training procedure, which utilizes curriculum learning through incremental synthetic data generation. We evaluate the proposed system using pianoform corpora, which is one of the most complex sources in the OMR literature. This evaluation is conducted first in a controlled scenario with synthetic data, and subsequently against two real-world corpora of varying conditions. Our approach is compared with leading commercial OMR software. The results demonstrate that our system not only successfully transcribes full-page music scores but also outperforms the commercial tool in both zero-shot settings and after fine-tuning with the target domain, representing a significant contribution to the field of OMR.
Rapid advancements in artificial intelligence have significantly enhanced generative tasks involving music and images, employing both unimodal and multimodal approaches. This research develops a model capable of generating music that resonates with the emotions depicted in visual arts, integrating emotion labeling, image captioning, and language models to transform visual inputs into musical compositions. Addressing the scarcity of aligned art and music data, we curated the Emotion Painting Music Dataset, pairing paintings with corresponding music for effective training and evaluation. Our dual-stage framework converts images to text descriptions of emotional content and then transforms these descriptions into music, facilitating efficient learning with minimal data. Performance is evaluated using metrics such as Fréchet Audio Distance (FAD), Total Harmonic Distortion (THD), Inception Score (IS), and KL divergence, with audio-emotion text similarity confirmed by the pre-trained CLAP model to demonstrate high alignment between generated music and text. This synthesis tool bridges visual art and music, enhancing accessibility for the visually impaired and opening avenues in educational and therapeutic applications by providing enriched multi-sensory experiences.
This study is a theoretical approach for exploring the applicability of a 2D cellular automaton based on melodic and harmonic intervals in random arrays of musical notes. The aim of this study was to explore alternatives uses for a cellular automaton in the musical context for better understanding the musical creativity. We used the complex systems and humanities approaches as a framework for capturing the essence of creating music based on rules of music theory. Findings suggested that such rules matter for generating large-scale patterns of organized notes. Therefore, our formulation provides a novel approach for understanding and replicating aspects of the musical creativity.
Symbolic Music, akin to language, can be encoded in discrete symbols. Recent research has extended the application of large language models (LLMs) such as GPT-4 and Llama2 to the symbolic music domain including understanding and generation. Yet scant research explores the details of how these LLMs perform on advanced music understanding and conditioned generation, especially from the multi-step reasoning perspective, which is a critical aspect in the conditioned, editable, and interactive human-computer co-creation process. This study conducts a thorough investigation of LLMs' capability and limitations in symbolic music processing. We identify that current LLMs exhibit poor performance in song-level multi-step music reasoning, and typically fail to leverage learned music knowledge when addressing complex musical tasks. An analysis of LLMs' responses highlights distinctly their pros and cons. Our findings suggest achieving advanced musical capability is not intrinsically obtained by LLMs, and future research should focus more on bridging the gap between music knowledge and reasoning, to improve the co-creation experience for musicians.
BackgroundThe literature suggests a beneficial effect of motor imagery (MI) if combined with physical practice, but detailed descriptions of MI training session (MITS) elements and temporal parameters are lacking. The aim of this review was to identify the characteristics of a successful MITS and compare these for different disciplines, MI session types, task focus, age, gender and MI modification during intervention.MethodsAn extended systematic literature search using 24 databases was performed for five disciplines: Education, Medicine, Music, Psychology and Sports. References that described an MI intervention that focused on motor skills, performance or strength improvement were included. Information describing 17 MITS elements was extracted based on the PETTLEP (physical, environment, timing, task, learning, emotion, perspective) approach. Seven elements describing the MITS temporal parameters were calculated: study duration, intervention duration, MITS duration, total MITS count, MITS per week, MI trials per MITS and total MI training time.ResultsBoth independent reviewers found 96% congruity, which was tested on a random sample of 20% of all references. After selection, 133 studies reporting 141 MI interventions were included. The locations of the MITS and position of the participants during MI were task-specific. Participants received acoustic detailed MI instructions, which were mostly standardised and live. During MI practice, participants kept their eyes closed. MI training was performed from an internal perspective with a kinaesthetic mode. Changes in MI content, duration and dosage were reported in 31 MI interventions. Familiarisation sessions before the start of the MI intervention were mentioned in 17 reports. MI interventions focused with decreasing relevance on motor-, cognitive- and strength-focused tasks. Average study intervention lasted 34 days, with participants practicing MI on average three times per week for 17 minutes, with 34 MI trials. Average total MI time was 178 minutes including 13 MITS. Reporting rate varied between 25.5% and 95.5%.ConclusionsMITS elements of successful interventions were individual, supervised and non-directed sessions, added after physical practice. Successful design characteristics were dominant in the Psychology literature, in interventions focusing on motor and strength-related tasks, in interventions with participants aged 20 to 29 years old, and in MI interventions including participants of both genders. Systematic searching of the MI literature was constrained by the lack of a defined MeSH term.
Este estudio examina la conexión entre la interpretación de música experimental y el contexto que la enmarca. Si bien una realización supone un proceso creativo que depende del músico que la lleva a cabo, la elaboración se da más en función de las referencias que el mismo contexto produce. Se da entonces a entender que este tipo de repertorio posee una epistemología estabilizada de la práctica, un sistema de signos circunscrito a las demandas de un estilo referenciado por la discografía que sustenta un modo de producción problemática para este tipo de obras: el acto reflejo (Alvear, 2021). Para abordarlo, tomaré como ejemplos una de las páginas de singularidad #1 (2016), obra del compositor chileno Santiago Astaburuaga, la cual es examinada a través de un aparato que entrevera la teoría semiótica de Charles Peirce y tres tipos signos, íconos, índices y símbolos; la teoría de la reproducción de técnica de Walter Benjamin; y la noción de técnica elaborada por Ben Spatz (2015). El objetivo es mostrar que la comprensión de la epistemología de la interpretación comporta sentar las bases para un proceso de exploración, en concordancia con el concepto de indeterminación, de las posibilidades de una obra experimental.
Music and books on Music, Musical instruction and study
AbstractSchools have been considered crucial social contexts for character formation. Hong Kong’s recent education policy has put moral and character education on the agenda of early childhood education (ECE); it states that moral and character education should be integrated into the major kindergarten subjects. However, questions remain on how it should be integrated into the ECE subject areas. Music has been officially identified as part of kindergartens’ daily activities. Scholarship has established the inextricable interconnection between character development and music participation. This study aims to explore subject-based implementation of the moral education through the lens of musical instructions. Literature confirms school leaders’ impact on shaping the implementation of policy, hence, school leaders’ perceptions and challenges regarding the implementation of this newly emphasized policy was explored through semi-structured interviews with 12 purposively selected principals. The results reveal that the principals valued using music education to teach children about morals and ethics, but found that they faced hurdles in the implementation, e.g. teachers’ insufficient pedagogical content knowledge and parents’ attitude. This study identifies traditionalism as the most prevailing view in kindergarten principals’ conceptualizations of moral education. Musical activities for moral education that principals support are play-based but adult-guided.