The value of music to society has been researched in terms of social good and change, positive economic contribution, and the successful educational impact on young people’s cognitive development. Despite this, the government exhibits variable support for music education. An open and closed question survey resulting in 186 mostly Australian musically educated adults pursuing non-music professions enriches the current instrumental music education value discourse. Irrespective of attained music standard, participants identified their instrumental music education developed the foundational transferable skills used and scaffolded within their non-music professions. Through sustained, active, formal and structured learning of complex instruments their transferable music skills cultivated confident, productive, highly focused, team-oriented professional employees representing excellent role models for their peers. Such transferable skills align with current, and future employment skills requirements as recognised by the World Economic Forum. Methods for data interpretation included using the Global Skills Taxonomy revealing there is scope for revision of many international skills frameworks to accurately represent music skill value. Through the lens of transferable music skills, it is possible to communicate the relevance of instrumental music education, contributing to a future-proofed capable workforce building a stronger economy. This study is the largest of its kind and offers a robust foundation for future international studies that may capture the cultural and historical contexts surrounding skill classifications.
Most work in AI music generation focused on audio, which has seen limited use in the music production industry due to its rigidity. To maximize flexibility while assuming only textual instructions from producers, we are among the first to tackle symbolic music editing. We circumvent the known challenge of lack of labeled data by proving that LLMs with zero-shot prompting can effectively edit drum grooves. The recipe of success is a creatively designed format that interfaces LLMs and music, while we facilitate evaluation by providing an evaluation dataset with annotated unit tests that highly aligns with musicians' judgment.
Non-metric music forms the core of the repertoire in Iranian classical music. Dastgahi music serves as the underlying theoretical system for both Iranian art music and certain folk traditions. At the heart of Iranian classical music lies the radif, a foundational repertoire that organizes melodic material central to performance and pedagogy. In this study, we introduce a digital corpus representing the complete non-metrical radif repertoire, covering all 13 existing components of this repertoire. We provide MIDI files (about 281 minutes in total) and data spreadsheets describing notes, note durations, intervals, and hierarchical structures for 228 pieces of music. We faithfully represent the tonality including quarter-tones, and the non-metric aspect. Furthermore, we provide supporting basic statistics, and measures of complexity and similarity over the corpus. Our corpus provides a platform for computational studies of Iranian classical music. Researchers might employ it in studying melodic patterns, investigating improvisational styles, or for other tasks in music information retrieval, music theory, and computational (ethno)musicology.
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.
Music composition has long been recognized as a significant art form. However, existing digital audio workstations and music production software often present high entry barriers for users lacking formal musical training. To address this, we introduce ComposeOn, a music theory-based tool designed for users with limited musical knowledge. ComposeOn enables users to easily extend their melodic ideas into complete compositions and offers simple editing features. By integrating music theory, it explains music creation at beginner, intermediate, and advanced levels. Our user study (N=10) compared ComposeOn with the baseline method, Suno AI, demonstrating that ComposeOn provides a more accessible and enjoyable composing and learning experience for individuals with limited musical skills. ComposeOn bridges the gap between theory and practice, offering an innovative solution as both a composition aid and music education platform. The study also explores the differences between theory-based music creation and generative music, highlighting the former's advantages in personal expression and learning.
Alessandro B. Melchiorre, Elena V. Epure, Shahed Masoudian
et al.
Natural language interfaces offer a compelling approach for music recommendation, enabling users to express complex preferences conversationally. While Large Language Models (LLMs) show promise in this direction, their scalability in recommender systems is limited by high costs and latency. Retrieval-based approaches using smaller language models mitigate these issues but often rely on single-modal item representations, overlook long-term user preferences, and require full model retraining, posing challenges for real-world deployment. In this paper, we present JAM (Just Ask for Music), a lightweight and intuitive framework for natural language music recommendation. JAM models user-query-item interactions as vector translations in a shared latent space, inspired by knowledge graph embedding methods like TransE. To capture the complexity of music and user intent, JAM aggregates multimodal item features via cross-attention and sparse mixture-of-experts. We also introduce JAMSessions, a new dataset of over 100k user-query-item triples with anonymized user/item embeddings, uniquely combining conversational queries and user long-term preferences. Our results show that JAM provides accurate recommendations, produces intuitive representations suitable for practical use cases, and can be easily integrated with existing music recommendation stacks.
Moonbeam is a transformer-based foundation model for symbolic music, pretrained on a large and diverse collection of MIDI data totaling 81.6K hours of music and 18 billion tokens. Moonbeam incorporates music-domain inductive biases by capturing both absolute and relative musical attributes through the introduction of a novel domain-knowledge-inspired tokenization method and Multidimensional Relative Attention (MRA), which captures relative music information without additional trainable parameters. Leveraging the pretrained Moonbeam, we propose 2 finetuning architectures with full anticipatory capabilities, targeting 2 categories of downstream tasks: symbolic music understanding and conditional music generation (including music infilling). Our model outperforms other large-scale pretrained music models in most cases in terms of accuracy and F1 score across 3 downstream music classification tasks on 4 datasets. Moreover, our finetuned conditional music generation model outperforms a strong transformer baseline with a REMI-like tokenizer. We open-source the code, pretrained model, and generated samples on Github.
The field of AI-assisted music creation has made significant strides, yet existing systems often struggle to meet the demands of iterative and nuanced music production. These challenges include providing sufficient control over the generated content and allowing for flexible, precise edits. This thesis tackles these issues by introducing a series of advancements that progressively build upon each other, enhancing the controllability and editability of text-to-music generation models. First, we introduce Loop Copilot, a system that tries to address the need for iterative refinement in music creation. Loop Copilot leverages a large language model (LLM) to coordinate multiple specialised AI models, enabling users to generate and refine music interactively through a conversational interface. Central to this system is the Global Attribute Table, which records and maintains key musical attributes throughout the iterative process, ensuring that modifications at any stage preserve the overall coherence of the music. While Loop Copilot excels in orchestrating the music creation process, it does not directly address the need for detailed edits to the generated content. To overcome this limitation, MusicMagus is presented as a further solution for editing AI-generated music. MusicMagus introduces a zero-shot text-to-music editing approach that allows for the modification of specific musical attributes, such as genre, mood, and instrumentation, without the need for retraining. By manipulating the latent space within pre-trained diffusion models, MusicMagus ensures that these edits are stylistically coherent and that non-targeted attributes remain unchanged. This system is particularly effective in maintaining the structural integrity of the music during edits, but it encounters challenges with more complex and real-world audio scenarios. ...
Recent years have witnessed a rapid growth of large-scale language models in the domain of music audio. Such models enable end-to-end generation of higher-quality music, and some allow conditioned generation using text descriptions. However, the control power of text controls on music is intrinsically limited, as they can only describe music indirectly through meta-data (such as singers and instruments) or high-level representations (such as genre and emotion). We aim to further equip the models with direct and content-based controls on innate music languages such as pitch, chords and drum track. To this end, we contribute Coco-Mulla, a content-based control method for music large language modeling. It uses a parameter-efficient fine-tuning (PEFT) method tailored for Transformer-based audio models. Experiments show that our approach achieved high-quality music generation with low-resource semi-supervised learning, tuning with less than 4% parameters compared to the original model and training on a small dataset with fewer than 300 songs. Moreover, our approach enables effective content-based controls, and we illustrate the control power via chords and rhythms, two of the most salient features of music audio. Furthermore, we show that by combining content-based controls and text descriptions, our system achieves flexible music variation generation and arrangement. Our source codes and demos are available online.
Franz Liszt created a new tradition by playing transcriptions and paraphrasing the most well-known operas and works of his time on his fabulous concerts. This habit created new genres like Transcriptions (Reminiscences de Norma S. 394, Grandes études de Paganini S. 141) and Paraphrases (The Rigoletto Paraphrase S.434, The Ernani Paraphrase S. 432). The Variations on „Weinen Klagen Sorgen Zagen” fits into both categories: On the one hand Liszt paraphrases J.S.Bach’s Crucifixus and the 12th Cantata. On the other hand, he transcribes with a great craftsmanship his piano work for organ. The historical and private background of this work testifies to an extraordinary faith.
This article discusses audience education as a ‘third mission’ commitment, a specific institutional task assigned to universities by recent government legislation, as well as a preferred subject of recent debate among Italian musicologists. Starting from a distinction between various types of audiences, from the general public to the diverse group of university audiences, the article proposes two action perspectives for universities in their task of educating the public, both in a curricular and extracurricular setting, focusing in particular on the former. The notion of ‘education’ as Bildung is recalled and applied to the field of music education within the broader context of democratic education. The notion of a ‘knowledge society’, which lies at the heart of the social, political and economic development of Western societies, is also reconsidered as part of a reflection on the complexity of today’s knowledge production, in particular expert knowledge, and on the ways in which knowledge itself is acquired by the general public. Within this perspective, the article finally proposes four directions for university teaching in musicological subjects aimed at audience education: a rigorous disciplinarity, as the foundation of true cross-disciplinarity; an enhancement of historical training; laboratory teaching; the mutual support that universities can provide in their own research efforts, teaching and third mission initiatives, also thanks to Rete Universitaria per l’Educazione musicale [University Network for Music Education].
Music and books on Music, Musical instruction and study
Symbolic music generation aims to generate music scores automatically. A recent trend is to use Transformer or its variants in music generation, which is, however, suboptimal, because the full attention cannot efficiently model the typically long music sequences (e.g., over 10,000 tokens), and the existing models have shortcomings in generating musical repetition structures. In this paper, we propose Museformer, a Transformer with a novel fine- and coarse-grained attention for music generation. Specifically, with the fine-grained attention, a token of a specific bar directly attends to all the tokens of the bars that are most relevant to music structures (e.g., the previous 1st, 2nd, 4th and 8th bars, selected via similarity statistics); with the coarse-grained attention, a token only attends to the summarization of the other bars rather than each token of them so as to reduce the computational cost. The advantages are two-fold. First, it can capture both music structure-related correlations via the fine-grained attention, and other contextual information via the coarse-grained attention. Second, it is efficient and can model over 3X longer music sequences compared to its full-attention counterpart. Both objective and subjective experimental results demonstrate its ability to generate long music sequences with high quality and better structures.
Izabela Maria z Lubomirskich Sanguszkowa była córką Henryka Lubomirskiego (1777–1850) i Teresy z Czartoryskich (1785–1868). Jej ojciec – wychowany przez daleką zamożną krewną Elżbietę z Czartoryskich Lubomirską (1736–1816), jedną z największych patronek sztuki na przełomie XVIII i XIX wieku – znany był za swojego szczególnego zamiłowania do muzyki. Zainteresowanie sprawami muzycznymi, a szczególnie operą, Henryk przekazał córce. Izabela świetnie śpiewała (w Wiedniu pobierała nauk u włoskich mistrzów – słynnego barytona Antonio Tamburiniego (1800–76), a następnie u kompozytora Stefano Pavesi (1779–1850)) i grała na fortepianie. W listach do ojca często komentowała bieżące wydarzenia muzyczne, a w oficynach wydawniczych Wiednia, Paryża, Mediolanu kupowała fragmenty wysłuchanych dzieł (głównie) operowych w opracowaniu na głos i fortepian czy też na cztery ręce. Ślady tych nabytków widać w zachowanych do dziś muzykaliach należących ongiś do Izabeli – w zbiorach Narodowego Zakładu im. Ossolińskich (zbiory sprzed zamążpójścia) i, nieznane do tej pory badaczom, Miejskiej Bibliotece Publicznej w Tarnowie (zbiory Izabeli, jej męża i dzieci). W Przeworsku, w którym Izabela dorastała, miała do dyspozycji przebogatą bibliotekę muzyczną, liczącą blisko 1400 pozycji, inwentarzem której obecnie dysponujemy. Po zamążpójściu nie zaprzestała muzykowania, prowadząc, zachowany do dziś, dzienniczek, zawierający w znacznej części nieznane 32 kompozycje, gromadząc muzykalia, dbając o wykształcenie muzyczne dzieci, wspierając twórczość kompozytorów. Kreowana przez Izabelę aktywność muzyczno-artystyczna w Krakowie i Gumniskach jest istotnym uzupełnieniem obrazu kultury muzycznej XIX-wiecznej Rzeczpospolitej.
As reading musical notation and its actualization of the stave are directed by man’s psychological process, there arises the necessity to control these movements.The investigation of free movements is based on a person’s image reflection o f music he is performing and this fact makes the orientated reaction its necessary functional component. Thus, the movements resulted from the actions in terms o f their orientation are viewed at deferent levels.
Abstract We aimed to determine the effects of wearing a cloth face mask on cardiorespiratory response, peak oxygen uptake (Vo2), respiratory muscle effort, and exercise tolerance during incremental exercise. The study had a randomized crossover design: 11 apparently healthy young men performed the Bruce protocol treadmill test in two conditions, wearing a cloth face mask (CFM) and without CFM (CON), in random order. Minute ventilation and oxygen uptake were measured using a mass spectrometry metabolic analyzer; cardiac output (CO) was measured using an impedance CO monitor; and mouth pressure (Pm) was measured and calculated as an integral Pm to assess respiratory muscle effort. Maximal minute ventilation was 13.4 ± 10.7% lower in the CFM condition than in the CON condition (P < 0.001). The peak Vo2 (52.4 ± 5.6 and 55.0 ± 5.1 mL/kg/min in CFM and CON, respectively) and CO were not significantly different between the two conditions. However, the integral value of Pm was significantly higher (P = 0.02), and the running time to exhaustion was 2.6 ± 3.2% lower (P = 0.02) in the CFM condition than in the CON condition. Our results suggest that wearing a cloth face mask increased respiratory muscle effort and decreased ventilatory volume in healthy young men; however, Vo2 remained unchanged. Exercise tolerance also decreased slightly.
We are currently in the modern era, where the era is all sophisticated, sophisticated and easy. New media or new media are media whose development and progress are accompanied by sophisticated technology. Currently, there are many social media applications that are used by many people. One of them is a social media application, namely video snacks. is a short video-based social media application with various features and video content. In addition to providing these music videos, this application can also give free money to its users. The purpose of this study was to determine user acceptance of video snack applications for video snacks. This study uses a qualitative method, with the reception analysis method, the number of informants using 5 people, with data collection techniques through interviews. The result of this research is the acceptance of 3 informants from 5 informants tend to be in a dominant hegemonic position and 2 people are in a negotiating position.
Dance choreography for a piece of music is a challenging task, having to be creative in presenting distinctive stylistic dance elements while taking into account the musical theme and rhythm. It has been tackled by different approaches such as similarity retrieval, sequence-to-sequence modeling and generative adversarial networks, but their generated dance sequences are often short of motion realism, diversity and music consistency. In this paper, we propose a Music-to-Dance with Optimal Transport Network (MDOT-Net) for learning to generate 3D dance choreographies from music. We introduce an optimal transport distance for evaluating the authenticity of the generated dance distribution and a Gromov-Wasserstein distance to measure the correspondence between the dance distribution and the input music. This gives a well defined and non-divergent training objective that mitigates the limitation of standard GAN training which is frequently plagued with instability and divergent generator loss issues. Extensive experiments demonstrate that our MDOT-Net can synthesize realistic and diverse dances which achieve an organic unity with the input music, reflecting the shared intentionality and matching the rhythmic articulation. Sample results are found at https://www.youtube.com/watch?v=dErfBkrlUO8.
Dance and music typically go hand in hand. The complexities in dance, music, and their synchronisation make them fascinating to study from a computational creativity perspective. While several works have looked at generating dance for a given music, automatically generating music for a given dance remains under-explored. This capability could have several creative expression and entertainment applications. We present some early explorations in this direction. We present a search-based offline approach that generates music after processing the entire dance video and an online approach that uses a deep neural network to generate music on-the-fly as the video proceeds. We compare these approaches to a strong heuristic baseline via human studies and present our findings. We have integrated our online approach in a live demo! A video of the demo can be found here: https://sites.google.com/view/dance2music/live-demo.