Hasil untuk "Music and books on Music"

Nataliia POSIKIRA-OMELCHUK, Tymur IVANNIKOV, Ulyana MOLCHKO et al.

The subject of this research is the essence of performing interpretation, which is considered an integral part of the functioning of a musical work from its creation to its presentation to the audience. The research methodology is based on a comparative analysis of historical and music-theoretical sources, an analysis of approaches to the definition and classification of different types of interpretation. The research compares the performing interpretation with other types of interpretation of contemporary music – composer’s and sound director’s interpretation. Interpretation is considered in relation to the concept of performance – if performance implies the physical act of playing a musical instrument or singing, the concept of interpretation is the ideal image of a musical work formed by the performer in the process of studying it. A comparative analysis of various definitions of the concept of interpretation allows us to conclude that the basis of interpretation is a thought process, understanding of its intonational features, including the analysis of the musical text, studying the circumstances of the composition of the work, stylistic and genre features. The issue of the correlation between the individual and the traditional in the course of forming an interpretation is important: the performer must take into account all the features of the musical text, the traditions of performing music of the relevant era and the relevant genres, while within the framework of traditions, the performer always has the space to bring his or her own individual understanding and performance characteristics. The issue of objective analysis of interpretations based on sound recordings is raised. Given the complexity of objective auditory analysis, we believe that the development of software that will allow us to identify agogic and dynamic features of performance at the level of individual sounds in musical phrases is a promising direction.

Keon Ju Maverick Lee, Jeff Ens, Sara Adkins et al.

The Musical Instrument Digital Interface (MIDI), introduced in 1983, revolutionized music production by allowing computers and instruments to communicate efficiently. MIDI files encode musical instructions compactly, facilitating convenient music sharing. They benefit Music Information Retrieval (MIR), aiding in research on music understanding, computational musicology, and generative music. The GigaMIDI dataset contains over 1.4 million unique MIDI files, encompassing 1.8 billion MIDI note events and over 5.3 million MIDI tracks. GigaMIDI is currently the largest collection of symbolic music in MIDI format available for research purposes under fair dealing. Distinguishing between non-expressive and expressive MIDI tracks is challenging, as MIDI files do not inherently make this distinction. To address this issue, we introduce a set of innovative heuristics for detecting expressive music performance. These include the Distinctive Note Velocity Ratio (DNVR) heuristic, which analyzes MIDI note velocity; the Distinctive Note Onset Deviation Ratio (DNODR) heuristic, which examines deviations in note onset times; and the Note Onset Median Metric Level (NOMML) heuristic, which evaluates onset positions relative to metric levels. Our evaluation demonstrates these heuristics effectively differentiate between non-expressive and expressive MIDI tracks. Furthermore, after evaluation, we create the most substantial expressive MIDI dataset, employing our heuristic, NOMML. This curated iteration of GigaMIDI encompasses expressively-performed instrument tracks detected by NOMML, containing all General MIDI instruments, constituting 31% of the GigaMIDI dataset, totalling 1,655,649 tracks.

Aditya Bhattacharjee, Ivan Meresman Higgs, Mark Sandler et al.

Automatic sample identification (ASID), the detection and identification of portions of audio recordings that have been reused in new musical works, is an essential but challenging task in the field of audio query-based retrieval. While a related task, audio fingerprinting, has made significant progress in accurately retrieving musical content under "real world" (noisy, reverberant) conditions, ASID systems struggle to identify samples that have undergone musical modifications. Thus, a system robust to common music production transformations such as time-stretching, pitch-shifting, effects processing, and underlying or overlaying music is an important open challenge. In this work, we propose a lightweight and scalable encoding architecture employing a Graph Neural Network within a contrastive learning framework. Our model uses only 9% of the trainable parameters compared to the current state-of-the-art system while achieving comparable performance, reaching a mean average precision (mAP) of 44.2%. To enhance retrieval quality, we introduce a two-stage approach consisting of an initial coarse similarity search for candidate selection, followed by a cross-attention classifier that rejects irrelevant matches and refines the ranking of retrieved candidates - an essential capability absent in prior models. In addition, because queries in real-world applications are often short in duration, we benchmark our system for short queries using new fine-grained annotations for the Sample100 dataset, which we publish as part of this work.

Miles Blencowe, Michael Casey, Kimberly Tan

We describe our investigations concerning the sonification of measured data from experiments involving various mesoscopic mechanical oscillator systems cooled down close to their quantum ground states, and music generation from a programmed quantum computer that subjects a single quantum bit ("qubit") to various unitary rotations, composed in order to test for the breakdown of macroscopic realism as expressed by the violation of the Leggett-Garg inequality. "Listening'' to data via their resulting sonifications facilitates the discovery of signals that might otherwise be hard to detect in common graphic (i.e., visual) representations, and for the quantum computer music experiment provides a complementary way to discern when the measured qubit data violates macroscopic realism with some prior listening training. The resulting soundscapes and music also provide a complementary window into the quantum realm that is accessible to non-experts with open ears.

Farshad Jafari, Claire Arthur

Initiating a quest to unravel the complexities of musical aesthetics through the lens of information dynamics, our study delves into the realm of musical sequence modeling, drawing a parallel between the sequential structured nature of music and natural language. Despite the prevalence of neural network models in MIR, the modeling of symbolic music events as applied to music cognition and music neuroscience has largely relied on statistical models. In this "proof of concept" paper we posit the superiority of neural network models over statistical models for predicting musical events. Specifically, we compare LSTM, Transformer, and GPT models against a widely-used markov model to predict a chord event following a sequence of chords. Utilizing chord sequences from the McGill Billboard dataset, we trained each model to predict the next chord from a given sequence of chords. We found that neural models significantly outperformed statistical ones in our study. Specifically, the LSTM with attention model led with an accuracy of 0.329, followed by Transformer models at 0.321, GPT at 0.301, and standard LSTM at 0.191. Variable Order Markov and Markov trailed behind with accuracies of 0.277 and 0.140, respectively. Encouraged by these results, we extended our investigation to multidimensional modeling, employing a many-to-one LSTM, LSTM with attention, Transformer, and GPT predictors. These models were trained on both chord and melody lines as two-dimensional data using the CoCoPops Billboard dataset, achieving an accuracy of 0.083, 0.312, 0.271, and 0.120, respectively, in predicting the next chord.

Danbinaerin Han, Mark Gotham, Dongmin Kim et al.

We introduce a project that revives a piece of 15th-century Korean court music, Chihwapyeong and Chwipunghyeong, composed upon the poem Songs of the Dragon Flying to Heaven. One of the earliest examples of Jeongganbo, a Korean musical notation system, the remaining version only consists of a rudimentary melody. Our research team, commissioned by the National Gugak (Korean Traditional Music) Center, aimed to transform this old melody into a performable arrangement for a six-part ensemble. Using Jeongganbo data acquired through bespoke optical music recognition, we trained a BERT-like masked language model and an encoder-decoder transformer model. We also propose an encoding scheme that strictly follows the structure of Jeongganbo and denotes note durations as positions. The resulting machine-transformed version of Chihwapyeong and Chwipunghyeong were evaluated by experts and performed by the Court Music Orchestra of National Gugak Center. Our work demonstrates that generative models can successfully be applied to traditional music with limited training data if combined with careful design.

Helen J. English, Michelle Kelly, Genevieve A. Dingle et al.

Globally our society is shifting to an older demographic and our lifespan increasing. It is therefore critical that we find and promote solutions to ageing well. There is emerging evidence that engagement in creative activities benefits psychosocial wellbeing and supports cognitive health. However, there are aspects of creative ageing research and implementation that need further development and solution-based thinking. These can be summarized as, (1) providing strong evidence for the benefits of engaging in creative activities; (2) overcoming barriers for participants and researchers; and (3) making engagement in creative activities sustainable. To address these areas, we held a symposium in 2022 and invited stakeholders, including older-adult participants, researchers, practitioners, and aged-care professionals. Symposium participants were allocated into three groups, each with representation from different stakeholders. The groups discussed one of the above areas and then shared ideas with the symposium group. An expert panel led further discussions and sought suggestions for solutions. Key suggestions included involving older adults in research design and planning from the beginning of the process; solutions for accessibility and sense of safety including having “try out” sessions and buddying participants; and creating partnerships with community organizations to promote sustainability. This report summarizes our discussions and advocates for more forums to move the debate forward.

Seyed Mohammadreza Beladi

This article examines parts of the oral literature and music of Bushehr, a port city in southern Iran. There is a song in Bushehr's music that uses words like helleh (heːlle̞) and heliosa (heːlijosa), that have no meaning for the people of Bushehr. This paper suggests that the origin of these words goes back to Greek mythology and that they are the remains of hymns or spells recited in praise of Helios and other ancient gods. To this end, in addition to qualitative and field research, extensive historical studies were carried out, focusing on the Hellenistic period after the conquest of Iran by Alexander the Great. I suggest that although the evolution of music in Bushehr was influenced by the military domination of Greece through acculturation, the cultural background of Bushehr was not ineffective in accepting this. As a result, assimilation occurred, and some mythical elements of Greece were localised in Bushehr.

Eliana Rosales

Digital scores were introduced in contemporary music some decades ago, as well as extra-musical images and visual signs in music writing. What is not yet explored and seems to be a very fertile field of research is musical writing based on research on transmodality. This article presents an investigation on some of the possibilities of musical and sonic writing through the incorporation of images of food textures. This is part of more extensive work that includes research on sonic relationships with visual textures (not only food) and that also investigates the compositional and performative possibilities of transmodal digital dynamic scores (video scores).

Angela Precup

The Relationship Between the Online Advertising and the Growth of Narcissistic Behaviours in Youth Cyberpsychology analyzed, since the beginning of the 90s, human behaviour in the digital environment and emphasized a few defining effects of this behaviour, such as the online anonymity effect, related to the online uninhibited effect or the online escalation effect. (Aiken 2019, 13) Analyzed from this perspective, online narcissism, exacerbated by the intense social media usage during the Covid-19 pandemic, is a behaviour amplified in the digital environment, compared to its dimensions in the real life. The specialists underline that individuals who use social media excessively develop narcissistic tendencies, and the young manifest oppositional behaviours, aggressive and anxious tendencies, being the most vulnerable category of the online public. The article analyses the relationship between online publicity and the amplification of narcissistic behaviours in young users, using as a case study the campaign #TheSelfieTalk, launched by the brand DOVE in the spring of 2021, as a communication programme meant to fight the young girls’ vulnerability in social media.

Dong Yao, Jieming Zhu, Jiahao Xun et al.

Recent research in self-supervised contrastive learning of music representations has demonstrated remarkable results across diverse downstream tasks. However, a prevailing trend in existing methods involves representing equally-sized music clips in either waveform or spectrogram formats, often overlooking the intrinsic part-whole hierarchies within music. In our quest to comprehend the bottom-up structure of music, we introduce MART, a hierarchical music representation learning approach that facilitates feature interactions among cropped music clips while considering their part-whole hierarchies. Specifically, we propose a hierarchical part-whole transformer to capture the structural relationships between music clips in a part-whole hierarchy. Furthermore, a hierarchical contrastive learning objective is crafted to align part-whole music representations at adjacent levels, progressively establishing a multi-hierarchy representation space. The effectiveness of our music representation learning from part-whole hierarchies has been empirically validated across multiple downstream tasks, including music classification and cover song identification.

Vassilis Lyberatos, Spyridon Kantarelis, Edmund Dervakos et al.

In the age of music streaming platforms, the task of automatically tagging music audio has garnered significant attention, driving researchers to devise methods aimed at enhancing performance metrics on standard datasets. Most recent approaches rely on deep neural networks, which, despite their impressive performance, possess opacity, making it challenging to elucidate their output for a given input. While the issue of interpretability has been emphasized in other fields like medicine, it has not received attention in music-related tasks. In this study, we explored the relevance of interpretability in the context of automatic music tagging. We constructed a workflow that incorporates three different information extraction techniques: a) leveraging symbolic knowledge, b) utilizing auxiliary deep neural networks, and c) employing signal processing to extract perceptual features from audio files. These features were subsequently used to train an interpretable machine-learning model for tag prediction. We conducted experiments on two datasets, namely the MTG-Jamendo dataset and the GTZAN dataset. Our method surpassed the performance of baseline models in both tasks and, in certain instances, demonstrated competitiveness with the current state-of-the-art. We conclude that there are use cases where the deterioration in performance is outweighed by the value of interpretability.

Nathan Fradet, Nicolas Gutowski, Fabien Chhel et al.

When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different approaches, as music can be composed of simultaneous tracks, of simultaneous notes with several attributes. Until now, the proposed tokenizations rely on small vocabularies of tokens describing the note attributes and time events, resulting in fairly long token sequences, and a sub-optimal use of the embedding space of language models. Recent research has put efforts on reducing the overall sequence length by merging embeddings or combining tokens. In this paper, we show that Byte Pair Encoding, a compression technique widely used for natural language, significantly decreases the sequence length while increasing the vocabulary size. By doing so, we leverage the embedding capabilities of such models with more expressive tokens, resulting in both better results and faster inference in generation and classification tasks. The source code is shared on Github, along with a companion website. Finally, BPE is directly implemented in MidiTok, allowing the reader to easily benefit from this method.

Emmanuel Deruty, Maarten Grachten

Although the use of AI tools in music composition and production is steadily increasing, as witnessed by the newly founded AI song contest, analysis of music produced using these tools is still relatively uncommon as a mean to gain insight in the ways AI tools impact music production. In this paper we present a case study of "Melatonin", a song produced by extensive use of BassNet, an AI tool originally designed to generate bass lines. Through analysis of the artists' work flow and song project, we identify style characteristics of the song in relation to the affordances of the tool, highlighting manifestations of style in terms of both idiom and sound.

Rui Guo, Ivor Simpson, Chris Kiefer et al.

We present a novel music generation framework for music infilling, with a user friendly interface. Infilling refers to the task of generating musical sections given the surrounding multi-track music. The proposed transformer-based framework is extensible for new control tokens as the added music control tokens such as tonal tension per bar and track polyphony level in this work. We explore the effects of including several musically meaningful control tokens, and evaluate the results using objective metrics related to pitch and rhythm. Our results demonstrate that adding additional control tokens helps to generate music with stronger stylistic similarities to the original music. It also provides the user with more control to change properties like the music texture and tonal tension in each bar compared to previous research which only provided control for track density. We present the model in a Google Colab notebook to enable interactive generation.

Gilank Yonsutrisno, Muhamad Idris, Deria Sepdwiko

This study aims to describe mixed ensemble learning in extracurricular activities in class IX students of SMP Negeri 15 Palembang. The research method used is descriptive qualitative with data collection techniques in the form of observation, interviews, and documentation. The preparation of the trainer before doing the learning is to determine the material that is taught to students at each meeting, then the trainer determines the strategies and learning methods that will be used in learning so that learning objectives are achieved. The implementation of mixed ensemble learning at SMP Negeri 15 Palembang includes; 1) The mixed ensemble learning process consists of group division, placement and selection of musical instruments, learning for each instrument, 2) Mixed ensemble learning includes three stages, namely preparation, implementation, and evaluation

Eduardo R. Miranda, Suchitra T. Basak

Quantum computing is a nascent technology, which is advancing rapidly. There is a long history of research into using computers for music. Nowadays computers are absolutely essential for the music economy. Thus, it is very likely that quantum computers will impact the music industry in time to come. This chapter lays the foundations of the new field of 'Quantum Computer Music'. It begins with an introduction to algorithmic computer music and methods to program computers to generate music, such as Markov chains and random walks. Then, it presents quantum computing versions of those methods. The discussions are supported by detailed explanations of quantum computing concepts and walk-through examples. A bespoke generative music algorithm is presented, the Basak-Miranda algorithm, which leverages a property of quantum mechanics known as constructive and destructive interference to operate a musical Markov chain. An Appendix introducing the fundamentals of quantum computing deemed necessary to understand the chapter and a link to access Jupyter Notebooks with examples are also provided.

Johanna Devaney

Digital audio processing tools offer music researchers the opportunity to examine both non-notated music and music as performance. This chapter summarises the types of information that can be extracted from audio as well as currently available audio tools for music corpus studies. The survey of extraction methods includes both a primer on signal processing and background theory on audio feature extraction. The survey of audio tools focuses on widely used tools, including both those with a graphical user interface, namely Audacity and Sonic Visualiser, and code-based tools written in the C/C++, Java, MATLAB, and Python computer programming languages.

Shuqi Dai, Zeyu Jin, Celso Gomes et al.

Recent advances in deep learning have expanded possibilities to generate music, but generating a customizable full piece of music with consistent long-term structure remains a challenge. This paper introduces MusicFrameworks, a hierarchical music structure representation and a multi-step generative process to create a full-length melody guided by long-term repetitive structure, chord, melodic contour, and rhythm constraints. We first organize the full melody with section and phrase-level structure. To generate melody in each phrase, we generate rhythm and basic melody using two separate transformer-based networks, and then generate the melody conditioned on the basic melody, rhythm and chords in an auto-regressive manner. By factoring music generation into sub-problems, our approach allows simpler models and requires less data. To customize or add variety, one can alter chords, basic melody, and rhythm structure in the music frameworks, letting our networks generate the melody accordingly. Additionally, we introduce new features to encode musical positional information, rhythm patterns, and melodic contours based on musical domain knowledge. A listening test reveals that melodies generated by our method are rated as good as or better than human-composed music in the POP909 dataset about half the time.

Charles Brazier, Gerhard Widmer

Fully automatic opera tracking is challenging because of the acoustic complexity of the genre, combining musical and linguistic information (singing, speech) in complex ways. In this paper, we propose a new pipeline for complete opera tracking. The pipeline is based on two trackers. A music tracker that has proven to be effective at tracking orchestral parts, will lead the tracking process. In addition, a lyrics tracker, that has recently been shown to reliably track the lyrics of opera songs, will correct the music tracker when tracking parts that have a text dominance over the music. We will demonstrate the efficiency of this method on the opera Don Giovanni, showing that this technique helps improving accuracy and robustness of a complete opera tracker.