Music Items Research Articles

Immersive technologies in the formation of musical audio space

Immersive audio technology is increasingly used in music, with devices like cell phones and televisions replicating formats. The increasing adoption of immersive audio technologies by both consumers and professionals in the music industry has made this topic more relevant. The purpose of the research is to analyse immersive technologies that contribute to the creation of the musical audio environment. The research employed methods: literature and historical review, technical analysis, practical cases, statistical method, and the author’s personal empirical experience. The article examines the function of audio space in relation to the perception of musical art and the characteristics of musical audio space. The proposed classification categories musical audio spaces into two distinct types: natural and artificial, as well as offline and online. The article’s statistical data illustrates the changing patterns of growth in online audio consumers and the rivalry between radio stations and streaming platforms to enhance their impact on shaping listeners’ audio spaces. The research demonstrates that streaming platforms actively encourage the incorporation of musical content in immersive formats as a means to expand their market share and evoke heightened emotional and perceptual responses in customers. The article outlines techniques used in immersive music spaces to provide a distinct aural experience for the listener. The article’s practical analysis of immersive audio technologies encompasses the examination of requisite microphones and digital audio workstations that facilitate the transition from two-dimensional audio space formation to threedimensional. In contemporary circumstances, the distribution of musical items is progressively employing threedimensional immersive technologies. The article enumerates audio technologies that guarantee the creation of an immersive auditory environment for both listeners and musicians: Ambisonics, KLANG: technologies, and DPA 5100. The practical significance of this work rests in examining the perceptual attributes of users of immersive technologies and exploring the potential for developing immersive technologies, such as immersive musical instruments or immersive radio stations

Odkryty księgozbiór nutowy Friedricha Wilhelma Jünckego (1842–1897) jako początek badań nad odtworzeniem dawnego inwentarza muzycznego

This article attempts to determine the function of the discovered small collection of 19 pieces of music, owned by Friedrich Wilhelm Jüncke (1842–1897) stored in the Library of the Stanisław Moniuszko Academy of Music in Gdańsk. In the face of limited knowledge about the life of this merchant from Gdańsk, and then from Sopot, the discovery that, apart from numismatic items and so-called Gdansk door, he also collected musical items was a big surprise for the employees of the Art Inkubator, an institution that, since 2019, has been taking care of, e.g. Jüncke’s villa and cherishes the memory of the former owner of the building. The musical and bibliological characteristics of the music prints showed that Jüncke gathered them for collecting rather than for utilitarian purposes. The provenance entries found in two prints prove that Jüncke was not their first owner. In addition, the entries found in the next five prints may prove that after Jüncke’s death some items were in the possession of the Gdańsk NSDAP, and after the war they ended up in the aMuz Library. Undoubtedly, finding this small book collection contributes to supplementing the information about Jüncke and – indirectly – to expanding knowledge about the musical culture of Gdańsk in the period 1939–1945.

MKGCN: Multi-Modal Knowledge Graph Convolutional Network for Music Recommender Systems

With the emergence of online music platforms, music recommender systems are becoming increasingly crucial in music information retrieval. Knowledge graphs (KGs) are a rich source of semantic information for entities and relations, allowing for improved modeling and analysis of entity relations to enhance recommendations. Existing research has primarily focused on the modeling and analysis of structural triples, while largely ignoring the representation and information processing capabilities of multi-modal data such as music videos and lyrics, which has hindered the improvement and user experience of music recommender systems. To address these issues, we propose a Multi-modal Knowledge Graph Convolutional Network (MKGCN) to enhance music recommendation by leveraging the multi-modal knowledge of music items and their high-order structural and semantic information. Specifically, there are three aggregators in MKGCN: the multi-modal aggregator aggregates the text, image, audio, and sentiment features of each music item in a multi-modal knowledge graph (MMKG); the user aggregator and item aggregator use graph convolutional networks to aggregate multi-hop neighboring nodes on MMKGs to model high-order representations of user preferences and music items, respectively. Finally, we utilize the aggregated embedding representations for recommendation. In training MKGCN, we adopt the ratio negative sampling strategy to generate high-quality negative samples. We construct four different-sized music MMKGs using the public dataset Last-FM and conduct extensive experiments on them. The experimental results demonstrate that MKGCN achieves significant improvements and outperforms several state-of-the-art baselines.

A Novel Feature-Based Music Recommendation System Considering the Uniqueness of Musical Items

A Novel Feature-Based Music Recommendation System Considering the Uniqueness of Musical Items

A method for personalised music recommendation based on emotional multi-label

In this paper, a personalised music recommendation method based on emotion multi-label was proposed. First is the analysis of music emotion and music emotional label, then, the principal component analysis method is used to reduce the dimension to process the music features and complete the preprocessing. Secondly, construct the music emotion multi-label, and combine the cosine method to calculate the emotional multi-label similarity. Finally, the interest degree of emotional multi-label is calculated to obtain the user's interest degree of music resources, and the personalised recommendation method is optimised to realise the personalised recommendation of music. Experimental results show that the average coverage rate of personalised music recommendation of the proposed method is as high as 99.5%, the accuracy is 98.3%, and the recommendation time of 500 music items is only 18.9 s. Therefore, the recommendation effect of the proposed method is good, the accuracy of personalised music recommendation is improved, and the recommendation time is shortened.

From Oblivion to Reappearance: A Multi-Faceted Evaluation of the Sustainability of Folk Music in Yunnan Province of China

The Southwestern Chinese province of Yunnan is the home to a plethora of traditional music, folk songs, and ethnic musical instruments with 24 local folk music items included in the national intangible cultural heritage list and extended list. In this article, the authors intend to delve into the issue of Yunnan folk music protection from the perspective of cultural sustainability theory. With an in-depth qualitative analysis of the data on the protection of 24 folk music items of Yunnan, the achievement, impact, and challenges of the current safeguarding efforts are revealed. The findings suggest that: 1. Government agencies at all levels have a dominant influence on the protection effort. 2. The local community, musicians, culture bearers, troupes, clubs, and social organizations form the “brick and mortar” of the folk music sustainability system. 3. The current reappearance or resurface of certain folk music items is a significant step toward truly reviving the folk music items in the future.

OrangeMusic: An orange computing‐inspired recommender framework in internet of music things

AbstractRecent computational analytics in the domain of the Internet of Things provides crowd‐sourced reviews for decision assistance for innumerable aspects of our living standards and socio‐entertainments. However, one of the most significant tasks for obtainable online music libraries and websites is the demand for personalized and professionalized courses of action for music listeners and composers to elect suitable musical performances. In this paper, we illustrate a hybrid matrix factorization‐based content‐sensitive music recommender schema on the Internet of Music Things. Emerging orange computing technology offers a harmonic fusion framework for psychological care and happiness‐concerned computing. We elucidate the projected music recommender paradigm in the domain of Internet of Music Things, titled as OrangeMusic. The OrangeMusic schema differs from the earlier contributions in the following aspects: (a) Orange computing‐based information fusion framework is applied on the Internet of Music Things; (b) Provided musical content revisions can be exposed by listeners' rating metrics and be exploited to amend original listener‐provided ratings; (c) Music listeners' preferences and musical items are incorporated into the standard matrix factorization mechanism. The performance metrics flourish that our proposed OrangeMusic presents a proficient rating prediction and intensifies the accuracy of content‐sensitive music recommendation expressively.

Influence of a continuous affect ratings task on listening time for unfamiliar art music

We aim to increase user engagement in unfamiliar music. We investigated listening duration for 100 unfamiliar art music items from the Australian Music Centre (AMC) library, presented under four different exposure conditions: a continuous affect response task, text/photographic information, text only, and no information. Participants could skip each item, and provided post-excerpt liking or familiarity ratings. Time-series analysis models of listening duration, liking, and familiarity, showed no increase in successive item liking or familiarity, although user liking and familiarity, positively predicted listening duration. The data confirm that directing listeners’ attention to discerning affect can enhance their engagement with unfamiliar music.

ОСОБЕННОСТИ СТАНОВЛЕНИЯ МУЗЫКАЛЬНОЙ ИНФРАСТРУКТУРЫ КЕМЕРОВСКОЙ ОБЛАСТИ (20–40-е ГОДЫ ХХ ВЕКА)

Describes a stage of formation and development of music in the Kemerovo region's infrastructure as a young industrial region of Russia. Due to interaction between socio-cultural and socio-economic aspects of development of the region, the musical life of the Kemerovo region was prepared in the pre-industrial period (until 1920), featuring the development of music performance within folk, Church, amateur music-making and unable to exit professional level due to lack of expertise in the region. After the October revolution in the conditions of intensive formation of the industrial structure in young cities region and the initial installation on massification of amateur (amateur) creativity, gradually formed the basis for the establishment of a fully fledged musical infrastructure. This phase was marked by the emergence and intensive development of musical performance mainly in the form of amateur music: choral and instrumental groups in constructed folk houses and clubs, performing cultural and educational functions among the working population. Parallel to the process of formation of the educational basis of musical infrastructure: opening of children's music schools, music schools, offices, children's creativity centres at clubs and houses of culture industry enterprises. During the great patriotic war, resulting in the evacuation and the arrival in the region of creative collectives and professional musicians going on formation of academic performance. Creating a pop concert Bureau (1943), subsequently converted in Kemerovo Oblast Philharmonic, translation of theatre of musical comedy (1945 g.) led to revitalize and strengthen the processes of professional music art items in Kemerovo oblast. With the opening of vocational educational institution-Kemerovo musical College (1944)-lay the Foundation for training new personnel in the sphere of musical culture of the region. With the advent of the professional segment in the cultural traditions of stabilization activities are envisaged with the totality of the prevailing musical infrastructure functioning in the context of the musical life of the region. Consequently, the period under review is an important link in the panorama of music art development in the industrial region, and determines subsequent lush flowering in 1970–1990.

‘Putting Radiohead Next to Bach.’ Perceptions of Cultural Hierarchy Unravelled with a Ranking Task

Although cultural hierarchy is a social construction – the result of ever changing distinction practices by elites – the consequential division between ‘high culture’ and ‘low culture’ is often either taken for granted as a fixed opposition, or disputed because of waning boundaries. To what extent individuals of different status groups adhere to such hierarchy is not known, nor whether changed cultural taste patterns result in alternate perceptions. This article aims to unravel cultural taste, perceptions of and opinions on cultural hierarchy, by means of a ranking task with musical items among ninety people in the Netherlands. It shows, first, that perceptions of cultural hierarchy are still sound among many, regardless of egalitarian opinions. Second, many distinguish personal tastes – which are evidently diverse – from their perceptions of cultural hierarchy – on which a certain agreement exists. Third, this agreement is not absolute, as there are several deviations, that are related to educational level and age.

Deep Learning in Music Recommendation Systems

Like in many other research areas, deep learning (DL) is increasingly adopted in music recommender systems (MRS). Deep neural networks are used in this area particularly for extracting latent factors of music items from audio signals or metadata and for learning sequential patterns of music items (tracks or artists) from music playlists or listening sessions. Latent item factors are commonly integrated into content-based filtering and hybrid MRS, whereas sequence models of music items are used for sequential music recommendation, e.g., automatic playlist continuation. This review article explains particularities of the music domain in RS research. It gives an overview of the state of the art that employs deep learning for music recommendation. The discussion is structured according to the dimensions of neural network type, input data, recommendation approach (content-based filtering, collaborative filtering, or both), and task (standard or sequential music recommendation). In addition, we discuss major challenges faced in MRS, in particular in the context of the current research on deep learning.

Changeability in Musical Folklore Performing Process: Evolution or Just Variability?

The musical folklore items use to have continuity of general changes in large scale historically. We can see it in the instrumental folk music, singing folklore, traditional choreography developments. It is not easy to make clear analysis of this process and we need a great number of special studies based on it. We can show only the main points or directions of this object in some different levels here. Each tune of particular traditional folk song has a great number of its variations. Each folklore performer does not want to make clear copy while singing the particular song the same way, as he has heard it from the other performer. So, we are able to find hundreds of the same folk tune variants, performed by particular singers in different times and various localities at the folklore archives in Lithuania. We have a nice possibility to make a comparative analysis of definite part (it is impossible to record all the performing variations) of this melody existing in real folklore life this way. And all variants are both in melodic lines and in poetic texts there, as a rule. On the other hand, we also can see the very clear stability of some the most important intonations, motives or phrases in almost all the different recordings of the melody (and text, of course). It shows us a sort of very clear non-written rules, known intuitively for all the traditional folklore performers as the basic forms of all the oral tradition. All sorts of music performance on the stage have their own specific standards. We have to make a folklore program in clear time and sequence. We have to show the interesting things for all the audience only. Therefore, traditional folklore performers have to make themselves as the artists. They have to turn their faces right way, to speak, to sing and to play music enough loudly, to smile and cry according to the stage program. What more terrible things we can ask them to do? Is it the right perspective of the folklore evolution? Thus, in this article we set the main goal – to define, theoretically and practically comprehend the forms of modifications performed by musical folklore, meaning the definitions of its evolution and variability. Methods – scientific analysis, historical, deductive and comparative methods, generalization and hypothesis. The novelty of the research is primarily determined by applying the experience of Lithuanian ethnomusicology in solving the general problems of the musical features development in traditional singing folklore. Conclusions. All the situations presented in this article we would like to define as the changeability, variability or at least developments of folklore (or in folklore). And some of them we can find as development and evolution of all the art and culture history using the folklore (musical, verbal etc.) essence or its elements. Traditional folklore has its own basic laws. We are not allowed to force and to influence them. We can use the traditional folklore elements as the copies of primary folklore items for all the other purposes we need in the history of worldwide culture, but we will never be able to make clear primary items from such copies. This is the essence of everlasting process of folklore changeability in one hand and evolution in another one.

Global and country-specific mainstreaminess measures: Definitions, analysis, and usage for improving personalized music recommendation systems.

RelevancePopularity-based approaches are widely adopted in music recommendation systems, both in industry and research. These approaches recommend to the target user what is currently popular among all users of the system. However, as the popularity distribution of music items typically is a long-tail distribution, popularity-based approaches to music recommendation fall short in satisfying listeners that have specialized music preferences far away from the global music mainstream. Addressing this gap, the contribution of this article is three-fold.Definition of mainstreaminess measuresFirst, we provide several quantitative measures describing the proximity of a user’s music preference to the music mainstream. Assuming that there is a difference between the global music mainstream and a country-specific one, we define the measures at two levels: relating a listener’s music preferences to the global music preferences of all users, or relating them to music preferences of the user’s country. To quantify such music preferences, we define a music item’s popularity in terms of artist playcounts (APC) and artist listener counts (ALC). Moreover, we adopt a distribution-based and a rank-based approach as means to decrease bias towards the head of the long-tail distribution. This eventually results in a framework of 6 measures to quantify music mainstream.Differences between countries with respect to music mainstreamSecond, we perform in-depth quantitative and qualitative studies of music mainstream in that we (i) analyze differences between countries in terms of their level of mainstreaminess, (ii) uncover both positive and negative outliers (substantially higher and lower country-specific popularity, respectively, compared to the global mainstream), analyzing these with a mixed-methods approach, and (iii) investigate differences between countries in terms of listening preferences related to popular music artists. We conduct our studies and experiments using the standardized LFM-1b dataset, from which we analyze about 800,000,000 listening events shared by about 53,000 users (from 47 countries) of the music streaming platform Last.fm. We show that there are substantial country-specific differences in listeners’ music consumption behavior with respect to the most popular artists listened to.Rating prediction experimentsThird, we demonstrate the applicability of our study results to improve music recommendation systems. To this end, we conduct rating prediction experiments in which we tailor recommendations to a user’s level of preference for the music mainstream using the proposed 6 mainstreaminess measures: defined by a distribution-based or rank-based approach, defined on a global level or on a country level (for the user’s country), and for APC or ALC. Our approach roughly equals a hybrid recommendation approach in which a demographic filtering strategy is implemented before collaborative filtering is performed. Results suggest that, in terms of rating prediction accuracy, each of the presented mainstreaminess definitions has its merits.

Verbal and Musical Short-Term Memory: Evidence for Shared Serial Order Processes?

This study explored the validity of an integrative framework for verbal and musical short-term memory (STM). Following this framework, access to domain-specific long-term knowledge bases supports the processing of musical and verbal item information in STM, while domain-general ordering processes support the representation of serial order information in the two domains. We exposed participants to verbal and musical STM tasks assessing either item information, order information, or both item and order information. Using an interindividual differences approach, we observed that performance in item-based STM tasks was not strongly associated between musical and verbal domains. In contrast, strong between-domain associations were observed for STM tasks assessing processing of verbal order and musical rhythm information. These preliminary results are overall in agreement with an integrative approach of verbal and musical STM. At the same time, the results highlight the difficulty of measuring serial order processing in the musical STM domain in a direct and specific manner.

On the relevance of music genre-based analysis in research on musical tastes

The investigation of the link between personality and musical tastes has led certain psychology researchers to examine the latent dimensions of musical tastes. In this area of research, investigators have largely relied on genre-based analysis, the relevance of which remains unclear. In this study, we examined the impact of changes in the selection of musical items on the identification of musical taste dimensions. Indeed, investigators have employed heterogeneous sets of music genres in prior research. Such a heterogeneity may partly explain why no clearly reproducible structure of musical tastes has emerged in the literature. Based on principal component analysis, our results indicate that the apparent structure of musical tastes is highly affected by even subtle variations in the items selected. Our findings also suggest that the identified structure of musical tastes strongly depends on the social background and cultural capital of respondents. Finally, our results highlight the limitations of the models that interpret the dimensions of musical tastes in terms of intrinsic musical properties.

Melodic Similarity and Applications Using Biologically-Inspired Techniques

Music similarity is a complex concept that manifests itself in areas such as Music Information Retrieval (MIR), musicological analysis and music cognition. Modelling the similarity of two music items is key for a number of music-related applications, such as cover song detection and query-by-humming. Typically, similarity models are based on intuition, heuristics or small-scale cognitive experiments; thus, applicability to broader contexts cannot be guaranteed. We argue that data-driven tools and analysis methods, applied to songs known to be related, can potentially provide us with information regarding the fine-grained nature of music similarity. Interestingly, music and biological sequences share a number of parallel concepts; from the natural sequence-representation, to their mechanisms of generating variations, i.e., oral transmission and evolution respectively. As such, there is a great potential for applying scientific methods and tools from bioinformatics to music. Stripped-down from biological heuristics, certain bioinformatics approaches can be generalized to any type of sequence. Consequently, reliable and unbiased data-driven solutions to problems such as biological sequence similarity and conservation analysis can be applied to music similarity and stability analysis. Our paper relies on such an approach to tackle a number of tasks and more notably to model global melodic similarity.

Musical Expertise Increases Top–Down Modulation Over Hippocampal Activation during Familiarity Decisions

The hippocampus has classically been associated with episodic memory, but is sometimes also recruited during semantic memory tasks, especially for the skilled exploration of familiar information. Cognitive control mechanisms guiding semantic memory search may benefit from the set of cognitive processes at stake during musical training. Here, we examined using functional magnetic resonance imaging, whether musical expertise would promote the top–down control of the left inferior frontal gyrus (LIFG) over the generation of hippocampally based goal-directed thoughts mediating the familiarity judgment of proverbs and musical items. Analyses of behavioral data confirmed that musical experts more efficiently access familiar melodies than non-musicians although such increased ability did not transfer to verbal semantic memory. At the brain level, musical expertise specifically enhanced the recruitment of the hippocampus during semantic access to melodies, but not proverbs. Additionally, hippocampal activation contributed to speed of access to familiar melodies, but only in musicians. Critically, causal modeling of neural dynamics between LIFG and the hippocampus further showed that top–down excitatory regulation over the hippocampus during familiarity decision specifically increases with musical expertise – an effect that generalized across melodies and proverbs. At the local level, our data show that musical expertise modulates the online recruitment of hippocampal response to serve semantic memory retrieval of familiar melodies. The reconfiguration of memory network dynamics following musical training could constitute a promising framework to understand its ability to preserve brain functions.

Utilizing context-relevant keywords extracted from a large collection of user-generated documents for music discovery

The contextual background of a user is one of the important criteria when deciding what music to listen to. In this paper, we propose a novel method to embed the user context for music search and retrieval. The proposed system extracts keywords from a large collection of documents written by users. Each of these documents contains a personal story about the writer’s situation and/or mood, followed by a song request. We consider that there is a strong correlation between the story and the song. Therefore, by extracting keywords from these documents, it is possible to develop a list of terms that can generally be used to describe the user context when requesting a song, which may then be employed to represent a music item in a richer manner. Once each song is represented using the proposed context-relevant music descriptors, we perform Latent Dirichlet Allocation to retrieve similar music based on context similarity. By conducting a series of experiments, we identified a correlation between the proposed music descriptors and conventional approaches, such as acoustic features or lyrics. The identified correlation can be used to auto-tag songs with no document association. We also qualitatively evaluated our system by comparing the performance of our proposed music descriptors with other conventional features for music retrieval. The results showed that the performance of the proposed music descriptors was competitive with conventional features, thereby suggesting their potential use for describing music in semantic music search/retrieval.

‚Komponist‘ und ‚Komponieren‘ im frühen Mittelalter zwischen Umbruch und Kontinuität

AbstractSince around 800 in Europe, new music has been constantly created to an ever increasing degree, so that the early 9th century has the character of an epochal shift in music history. The creation of new music, first of broadly liturgical chants, is testified, on the one hand, by manuscripts transmitting texts and melodies, and on the other hand by literary sources (chronicles, lives of saints, etc.) which speak of the production of new musical items. It has often been doubted whether these creative processes can be qualified as acts of ‘composing’ in the modern sense of the word. In this essay, however, the main question will be what can be learned by the existing sources, if one asks what kind of information they offer regarding an early-medieval attitude towards ‘composers’ of music and the nature of their activities. In addition, it seems that this discourse had its beginnings mainly in the 9th century, and that it retained certain traits, and remained faithful to a restricted number of ideas (such as questions of

Neural alpha oscillations index the balance between self-other integration and segregation in real-time joint action

Shared knowledge and interpersonal coordination are prerequisites for most forms of social behavior. Influential approaches to joint action have conceptualized these capacities in relation to the separate constructs of co-representation (knowledge) and self-other entrainment (coordination). Here we investigated how brain mechanisms involved in co-representation and entrainment interact to support joint action. To do so, we used a musical joint action paradigm to show that the neural mechanisms underlying co-representation and self-other entrainment are linked via a process – indexed by EEG alpha oscillations – regulating the balance between self-other integration and segregation in real time. Pairs of pianists performed short musical items while action familiarity and interpersonal (behavioral) synchronization accuracy were manipulated in a factorial design. Action familiarity referred to whether or not pianists had rehearsed the musical material performed by the other beforehand. Interpersonal synchronization was manipulated via congruent or incongruent tempo change instructions that biased performance timing towards the impending, new tempo. It was observed that, when pianists were familiar with each other's parts, millisecond variations in interpersonal synchronized behavior were associated with a modulation of alpha power over right centro-parietal scalp regions. Specifically, high behavioral entrainment was associated with self-other integration, as indexed by alpha suppression. Conversely, low behavioral entrainment encouraged reliance on internal knowledge and thus led to self-other segregation, indexed by alpha enhancement. These findings suggest that alpha oscillations index the processing of information about self and other depending on the compatibility of internal knowledge and external (environmental) events at finely resolved timescales.