Music Segments Research Articles

Fractal and Complex Patterns Existing in Music: Application to the Composition DIAPHONIES of Michael Paouris

This paper reports fractal patterns identified in the complex musical composition DIAPHONIES by Michael Paouris via power-law fractal analysis with sliding-windows of size 1024. From 7,647,232 analysed musical segments of DIAPHONIES, 3,222,832 (42.4%) are fractional Brownian motion (fBm) fractal segments and 4,424,400 (57.6%) are fractional Gaussian noise (fGn) stochastic ones. From the fBm fractal segments 295,294 (9.1%) exhibit strong persistency-P with power-law segments in the range of 2.3≤b≤3. These are the very strong fractal areas in DIAPHONIES. Numerous segments with strong antipersistency 1.7≤b<2 are reported together with segments with AP changes (1.7≤b<2.3). In DIAPHONIES continuous fractal fBm areas are dipped in non-fractal fGn areas of deterministic music. The results are within the fBm fractal areas reported in existing papers. Very importantly, the simple composition called Nocturnal-Angel by Michael Paouris, exhibited limited fBm areas of average b¯=1.98 (σ=0.3), namely of pure statistical, deterministic music, while simultaneously, the fractal analysis profile was completely different from the profiles of DIAPHONIES, hence reinforcing, the fractal findings of DIAPHONIES in relation to trivial music harmony.

MTV Brazil: musical repertoire and construction of a televised youth (1990)

Objective/context: this article analyzes the construction of youth representations through the musical repertoire produced by MTV Brasil in its first year. The objective is to understand the musical segments most explored by the broadcaster during this period, as well as how to articulate their protagonism in the transformation of the “youth music” category, with a singular impact on Brazilian youth culture. mtv was a television channel aimed at young audiences, which started in the United States in 1981 and arrived in Brazil in 1990 through Grupo Abril, a national media conglomerate. The broadcast on Brazilian soil is based on the American format, showing musical videos from artists and specific musical segments, with a strong attraction for consumption in this sector of the population. Methodology: considering music as a social marker, this study analyzes the specific repertoire of musical segments and artists produced by the broadcaster as a means of identification. Therefore, an examination based on the first musical videos by Brazilian artists produced by the broadcaster and broadcast in its first year is proposed. Originality: the level of importance of certain media or media programs in the constitution of the identities of social agents, especially in the development of juvenile identities in the recent past, is only a little analyzed. Conclusions: it can be concluded that MTV operated as a musical authority for young people, acting as a curator of what they should consume to perform their youthful condition, acting as an artificer of youth. The broadcaster was based on its initial repertoire among a group of artists linked to rock music, with a strong influence on the recording industry in the 1990s and a decisive impact on Brazilian youth.

Segmenting and Predicting Musical Phrase Structure Exploits Neural Gain Modulation and Phase Precession.

Music, like spoken language, is often characterized by hierarchically organized structure. Previous experiments have shown neural tracking of notes and beats, but little work touches on the more abstract question: how does the brain establish high-level musical structures in real time? We presented Bach chorales to participants (20 females and 9 males) undergoing electroencephalogram (EEG) recording to investigate how the brain tracks musical phrases. We removed the main temporal cues to phrasal structures, so that listeners could only rely on harmonic information to parse a continuous musical stream. Phrasal structures were disrupted by locally or globally reversing the harmonic progression, so that our observations on the original music could be controlled and compared. We first replicated the findings on neural tracking of musical notes and beats, substantiating the positive correlation between musical training and neural tracking. Critically, we discovered a neural signature in the frequency range ∼0.1 Hz (modulations of EEG power) that reliably tracks musical phrasal structure. Next, we developed an approach to quantify the phrasal phase precession of the EEG power, revealing that phrase tracking is indeed an operation of active segmentation involving predictive processes. We demonstrate that the brain establishes complex musical structures online over long timescales (>5 s) and actively segments continuous music streams in a manner comparable to language processing. These two neural signatures, phrase tracking and phrasal phase precession, provide new conceptual and technical tools to study the processes underpinning high-level structure building using noninvasive recording techniques.

Musical protein: Mapping the time sequence of music onto the spatial architecture of proteins

Background and objectiveMusic, the ubiquitous language across human cultures, is traditionally considered as a form of art but has been linked to biomolecules in recent years. However, previous efforts have only been addressed on sonification of nucleic acids and proteins to produce so-called life music, the soundscape from the basic building blocks of life. In this study, we attempted to, for the first time, conduct a reverse operation of this process, i.e. conversion of music to protein (CoMtP). MethodsA novel notion termed musical protein (MP) –– the protein defined by music –– was proposed and, on this basis, we described a computational strategy to map the time sequence of music onto the spatial architecture of proteins, which considered that each note in the stave of a music (target) can be simply characterized by two acoustical quantities and that each residue in the primary sequence of a protein (hit) was represented by amino acid descriptors. ResultsA simulated annealing (SA) algorithm was applied to iteratively generate the best matched MP hit for a music target and structural bioinformatics was then used to model spatial advanced structure for the resulting MP. We also demonstrated that some small MPs derived from music segments may have potential biological functions, which, for example, can serve as antimicrobial peptides (AMPs) to inhibit clinical bacterial strains with moderate or high antibacterial potency. ConclusionsThis work may benefit many aspects; for example, it would open a door for the hearing-impaired persons to ‘listen’ music in a biological vision and could be a mean of exposing students to the concepts of biomolecules at an earlier age through the use of auditory characteristics. The CoMtP would also facilitate the rational design of proteins with biological and medicinal significance.

Exploring the Evolution of GenAI in Music Composition

Crafting musical compositions presents a unique set of challenges, divergent from those encountered in visual art forms. The temporal nature of music necessitates models proficient in handling time dynamics. Moreover, compositions often encompass multiple tracks, each characterized by its own temporal intricacies, demanding an intricate approach to their interdependent evolution. Unlike static visual imagery, musical notes are sequenced, commonly organized into chords or melodies, imposing a requirement for specialized chronological structures. This paper extensively delves into the evolutionary journey of GenAI within the domain of sequential generative adversarial networks (GANs) tailored specifically for music composition. We introduce a suite of novel models meticulously crafted to address the nuances of musical generation, exploring their efficacy in producing complex multi-track compositions. Our investigation centers on a comprehensive analysis of the evolutionary trajectory of these models, scrutinizing their capacity to autonomously generate cohesive musical sequences across diverse tracks. Through rigorous empirical evaluations, we substantiate the capabilities of our models to produce compelling musical segments sans human intervention. Furthermore, we delve into intricate technical discussions, elucidating the underlying mechanisms driving the generation process, including the intricate interplay of neural architectures and training methodologies. In addition to empirical validation, we conduct detailed user studies, garnering insights into the subjective perception of the generated compositions. Moreover, we delve into the realm of human-AI collaboration in music generation, unveiling the potential of GenAI to complement human compositions by seamlessly providing harmonious accompaniment, thereby bridging the gap between artistic creativity and computational progress.

Фактор законченности музыкальной формы: к вопросу об исторической эволюции

The study aims to substantiate that already in the early epochs (the Middle Ages, the Renaissance, the Baroque), there was a gradual birth of musical form functionality, one of the first signs of which was represented by composers’ awareness of the need to achieve the structural integrity and completeness of a work. The paper shows that the role of the main formative means was played by those compositional factors that were most actively developing in a particular epoch. The scientific novelty of the study lies in the specific identification of these compositional factors: the rhythmic one in the isorhythmic motets of the 14th century, the large-scale structural one in the textual and musical forms of the Renaissance, the functional harmonic one in Baroque works. As a result, it has been found that a change towards a decrease in the tenor’s measure at the last repetition of the melody of Gregorian chant turned out to be the factor of musical form completeness in Ph. de Vitry’s isorhythmic motets; in the motets, madrigals and polyphonic songs of the Renaissance, a large-scale enlargement of the final textual and musical segment of the form performed a similar function; as for the instrumental Baroque genres (preludes, toccatas, fantasias), such was the case with the increased harmonic stability of the last section (a tonic organ point, repetition of cadence turns).

Retracted: Music Segmentation Algorithm Based on Self-Adaptive Update of Confidence Measure

Retracted: Music Segmentation Algorithm Based on Self-Adaptive Update of Confidence Measure

A Music-Driven Dance Generation Method Based on a Spatial-Temporal Refinement Model to Optimize Abnormal Frames.

Since existing music-driven dance generation methods have abnormal motion when generating dance sequences which leads to unnatural overall dance movements, a music-driven dance generation method based on a spatial-temporal refinement model is proposed to optimize the abnormal frames. Firstly, the cross-modal alignment model is used to learn the correspondence between the two modalities of audio and dance video and based on the learned correspondence, the corresponding dance segments are matched with the input music segments. Secondly, an abnormal frame optimization algorithm is proposed to carry out the optimization of the abnormal frames in the dance sequence. Finally, a temporal refinement model is used to constrain the music beats and dance rhythms in the temporal perspective to further strengthen the consistency between the music and the dance movements. The experimental results show that the proposed method can generate realistic and natural dance video sequences, with the FID index reduced by 1.2 and the diversity index improved by 1.7.

EmoMusicTV: Emotion-Conditioned Symbolic Music Generation With Hierarchical Transformer VAE

Emotion is one of the most crucial attributes of music. However, due to the scarcity of emotional music datasets, emotion-conditioned symbolic music generation using deep learning techniques has not been investigated in depth. In particular, no study explores conditional music generation with the guidance of emotion, and few studies adopt time-varying emotional conditions. To address these issues, first, we endow three public lead sheet datasets with fine-grained emotions by automatically computing the valence labels from the chord progressions. Second, we propose a novel and effective encoder-decoder architecture named EmoMusicTV to explore the impact of emotional conditions on multiple music generation tasks and to capture the rich variability of musical sequences. EmoMusicTV is a transformer-based variational autoencoder (VAE) that contains a hierarchical latent variable structure to model holistic properties of the music segments and short-term variations within bars. The piece-level and bar-level emotional labels are embedded in their corresponding latent spaces to guide music generation. Third, we pretrain EmoMusicTV with the lead sheet continuation task to further improve its performance on conditional melody or harmony generation. Experimental results demonstrate that EmoMusicTV outperforms previous methods on three tasks, i.e., melody harmonization, melody generation given harmony, and lead sheet generation. Ablation studies verify the significant roles of emotional conditions and hierarchical latent variable structure on conditional music generation. Human listening shows that the lead sheets generated by EmoMusicTV are closer to the ground truth (GT) and perform slightly worse than the GT in conveying emotional polarity.

Self-Supervised Learning of Multi-Level Audio Representations for Music Segmentation

Self-Supervised Learning of Multi-Level Audio Representations for Music Segmentation

Metaphorical Expression of Emotions in Modern Music Composition Based on Emotional Calculations

Abstract In this paper, audio and lyrics features of music are fused from the audio and lyrics attributes of modern music tracks to obtain a joint representation of music. The features such as tempo, directionality, average value of intensity, beat, and change of rhythm of each musical segment are extracted from the main audio track to form the music feature vector. Subsequently, the music was separated into multiple segments with distinct emotions, and the emotional expression of modern music was evaluated using the Hevner emotion model. Finally, the note extraction performance of this paper’s model is analyzed, and the spectral contrast features of different music pieces and the emotional expression of music pieces under different features are explored. The results show that the pitch patterns of sad emotions are mostly distributed in the range of 0.5-0.55, and the values of the pitch patterns of angry music are basically larger than 0.55. The mean values of the spectral entropy of joy and calmness are mostly distributed in the range of 0.5-0.7, and the sad emotions are mostly in the vicinity of 0.7, while the mean values of the spectral entropy of angry emotions are larger than 0.8.

Naturalistic auditory stimuli with fNIRS prefrontal cortex imaging: A potential paradigm for disorder of consciousness diagnostics (a study with healthy participants)

Disorder of consciousness (DOC) is a devastating condition due to brain damage. A patient in this condition is non-responsive, but nevertheless might be conscious at least at some level. Determining the conscious level of DOC patients is important for both medical and ethical reasons, but reliably achieving this has been a major challenge. Naturalistic stimuli in combination with neuroimaging have been proposed as a promising approach for DOC patient diagnosis. Capitalizing on and extending this proposal, the goal of the present study conducted with healthy participants was to develop a new paradigm with naturalistic auditory stimuli and functional near-infrared spectroscopy (fNIRS) − an approach that can be used at the bedside. Twenty-four healthy participants passively listened to 9 min of auditory story, scrambled auditory story, classical music, and scrambled classical music segments while their prefrontal cortex activity was recorded using fNIRS. We found much higher intersubject correlation (ISC) during story compared to scrambled story conditions both at the group level and in the majority of individual subjects, suggesting that fNIRS imaging of the prefrontal cortex might be a sensitive method to capture neural changes associated with narrative comprehension. In contrast, the ISC during the classical music segment did not differ reliably from scrambled classical music and was also much lower than the story condition. Our main result is that naturalistic auditory stories with fNIRS might be used in a clinical setup to identify high-level processing and potential consciousness in DOC patients.

Music Segmentation and Similarity Estimation Applied to a Gaze-Controlled Musical Interface

Assistive technology, especially gaze-controlled, can promote accessibility, health care, well-being and inclusion for impaired people, including musical activities that can be supported by interfaces controlled using eye tracking. Also, the Internet growth has allowed access to a huge digital music database, which can contribute to a new form of music creation. In this paper, we propose the application of Music Information Retrieval techniques for music segmentation and similarity identification, aiming at the development of a new form of musical creation using an automatic process and the optimization algorithm Harmony Search to combine segments. These techniques for segmentation and similarity of segments were implemented in an assistive musical interface controlled by eye movement to support musical creation and well-being. The experimental results can be found in [https://bit.ly/2Zl7KSC].

AAM: a dataset of Artificial Audio Multitracks for diverse music information retrieval tasks

We present a new dataset of 3000 artificial music tracks with rich annotations based on real instrument samples and generated by algorithmic composition with respect to music theory. Our collection provides ground truth onset information and has several advantages compared to many available datasets. It can be used to compare and optimize algorithms for various music information retrieval tasks like music segmentation, instrument recognition, source separation, onset detection, key and chord recognition, or tempo estimation. As the audio is perfectly aligned to original MIDIs, all annotations (onsets, pitches, instruments, keys, tempos, chords, beats, and segment boundaries) are absolutely precise. Because of that, specific scenarios can be addressed, for instance, detection of segment boundaries with instrument and key change only, or onset detection only in tracks with drums and slow tempo. This allows for the exhaustive evaluation and identification of individual weak points of algorithms. In contrast to datasets with commercial music, all audio tracks are freely available, allowing for extraction of own audio features. All music pieces are stored as single instrument audio tracks and a mix track, so that different augmentations and DSP effects can be applied to extend training sets and create individual mixes, e.g., for deep neural networks. In three case studies, we show how different algorithms and neural network models can be analyzed and compared for music segmentation, instrument recognition, and onset detection. In future, the dataset can be easily extended under consideration of specific demands to the composition process.

Soft Computing for Music Generation using Genetic Algorithm

Creating good music is truly a laborious task since it requires lots of effort, extended time, and many instruments. When the tune of music does not sound good after being composed with much toil, then composers must discard it, which is a hectic job. Hence, an easy way to compose the music which will require less time and less effort is required. Genetic algorithm is a possible way of searching the solution to the problem in large dimension search space. Genetic algorithm (GA), a part of soft computing in the field of music composition can be used to solve this issue. This paper proposes the use of GA for composing music and the use of fitness function to select more melodious music. In GA, for music creation, two musical segments will act as parent nodes for creating new music, and by applying genetic operators, there is a change in the music such that breaks are modified between the tunes. Music which sounds pleasing is chosen with the user’s help using fitness function, and if the user is satisfied with the generated tune, then the process of generating the music is terminated; otherwise, the selected musical tune by the fitness function will act as the parent node for the next generation of musical tune. Moreover, this work explains which fitness function to be applied on the specific problem.

Extraction and recognition of music melody features using a deep neural network

The music melody can be used to distinguish the genre style of music and can also be used for retrieving music works. This paper used a deep learning algorithm, the convolutional neural network (CNN), to extract the features of musical melodies and recognize genres. Three-tuple samples were used as training samples in the training process. Orthogonal experiments were conducted on the number of music segments and the type of activation function in the algorithm in the simulation experiments. The CNN algorithm was compared with support vector machine (SVM) and traditional CNN algorithms. The results showed that there were obvious differences in the pitch and melody curves of different genres of music; the recognition performance was best when the number of music segments was six and the activation function was relu; the CNN algorithm trained by three-tuple samples had better recognition accuracy and spent less recognition time.

Involuntary, Limited, and Contiguously Repeating Musical Imagery (InLaCReMI): Reconciling Theory and Data on the Musical Material Acquired by Earworms

“Earworms” have been proposed as a particular type of involuntary musical imagery (INMI) where musical material is repeated in the mind. The structure of the repetition is investigated by proposing a spreading activation model (SAM), where mental experience consists of priming and activation of nodes that represent objects, events, and relationships, including music. Music consists of chaining together nodes representing small music segments within hierarchical structures. Listening to music at a point in time activates the music's represented segment, which then primes the node representing the segment that follows. Repeating musical segments are coded recursively, with an additional layer of “context” nodes tracking global, structural location. From this basis, two hypotheses were proposed: H1 “Contiguous repetition at encoding” and H2 “Low environmental focus.” H1 predicts that when an INMI episode is a contiguously repeating segment, it must be based on music that contains contiguous repetition: it will be perceived as a subset of INMI – involuntary, limited, and contiguously repeating musical imagery (InLaCReMI). H1 challenges current views about preferred segments for looping, such as the “hook” of a tune. H2 predicts that InLaCReMI occurs when an individual is not focused on the immediate environment. In such a state there is less social imperative to activate high attentional-demand contextual information and so adherence to contextual integrity in thought is relaxed, leading to looping of recurrently activated nodes that were encoded with contiguous repetition. Additional predictions were made using SAM, demonstrating the potential for SAM to provide a unifying understanding of INMI. InLaCReMI is proposed as a frequently occurring species of INMI and confirmation of this phenomenon through more structured empirical investigation will provide novel insights into mental operation, and the nature of INMI.

Retracted: Recognition of Continuous Music Segments Based on the Phase Space Reconstruction Method.

[This retracts the article DOI: 10.1155/2022/4099505.].

Recognition of Continuous Music Segments Based on the Phase Space Reconstruction Method.

Piano score recognition is one of the important research contents in the field of music information retrieval, and it plays an important role in information processing. In order to reduce the influence of vocals on the progress of piano notes and restore the harmonic information corresponding to piano notes, the article models the harmonic information and vocal information corresponding to piano notes in the frequency spectrum. We use the phase space reconstruction method to extract the nonlinear feature parameters in the note audio and use some of the parameters as the training set to construct the support vector machine (SVM) classifier and the other part as the test set to test the recognition effect. Therefore, the method of adaptive signal decomposition and SVM is introduced into the signal preprocessing link, and the corresponding recognition process is established. In order to improve the performance of the support vector machine, the article uses measurement learning method to obtain the measurement learning and uses the measurement learning to replace the Euclidean distance of the Gaussian kernel function of the support vector machine. The SVM method of adaptive signal decomposition and the SVM method of principal component analysis are introduced into the preprocessing process of the note signal, and then the preprocessed signal is reconstructed in phase space, and the corresponding recognition process is established. The method of directly reconstructing the phase space of the original signal has higher accuracy and can be applied to the note recognition of continuous music segments. The final experimental results show that, compared with the current popular piano score recognition algorithm, the recognition accuracy of the proposed piano score recognition algorithm is improved by 3.5% to 12.2%.

A large TV dataset for speech and music activity detection

Automatic speech and music activity detection (SMAD) is an enabling task that can help segment, index, and pre-process audio content in radio broadcast and TV programs. However, due to copyright concerns and the cost of manual annotation, the limited availability of diverse and sizeable datasets hinders the progress of state-of-the-art (SOTA) data-driven approaches. We address this challenge by presenting a large-scale dataset containing Mel spectrogram, VGGish, and MFCCs features extracted from around 1600 h of professionally produced audio tracks and their corresponding noisy labels indicating the approximate location of speech and music segments. The labels are several sources such as subtitles and cuesheet. A test set curated by human annotators is also included as a subset for evaluation. To validate the generalizability of the proposed dataset, we conduct several experiments comparing various model architectures and their variants under different conditions. The results suggest that our proposed dataset is able to serve as a reliable training resource and leads to SOTA performances on various public datasets. To the best of our knowledge, this dataset is the first large-scale, open-sourced dataset that contains features extracted from professionally produced audio tracks and their corresponding frame-level speech and music annotations.