Music Tracks Research Articles

‘Caro’: Bad Bunny and the symbolic rupture of gender

In early 2019, Bad Bunny, a leading urbano latino artist, released the music video to his song ‘Caro’. As a musical track, the song can easily be heard as standard Latin trap fare that centres the ostentatious masculinity of its protagonist. The video, however, definitively disrupts gendered/generic norms by layering the performances of Bad Bunny and Jazmyne Joy, a model featured in the role of Bad Bunny. Their dual performance of a single persona, deploying both drag and ventriloquism, challenges the perceived boundedness of gender and genre by calling into question the boundaries of the body itself. Gender and genre are treated here as conceptual sisters that afford the rupture of their respective boundaries in the elaborative act of performance. Thus, in ‘Caro’, the theories of Judith Butler and Georgina Born are generatively exemplified and mutually illuminated, affirming the contingency and performativity at the centre of both.

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.

Multiple-source dynamic range compression in hearing devices: What can we learn from music mixing?

Dynamic range compression (DRC), a form of nonlinear gain control, is widely used in both hearing devices and music production, but in very different ways. In hearing devices, DRC boosts quiet sounds more than loud sounds to match the reduced dynamic range of listeners with hearing loss. Compression is applied to the mixture of sounds captured by the hearing device microphone, so it is known to cause distortion in noisy environments where the level of one sound can affect the gain applied to another sound. In music mixing, DRC can be applied to individual vocal or instrumental tracks or to the overall mixture. It can also be applied to combinations of signals to introduce deliberate distortion effects, for example, by adjusting the level of one track based on the level of another. In a hearing device that could process different sound sources independently, real-life sounds could be mixed like musical tracks, reducing unwanted distortion and enabling new nonlinear techniques to improve intelligibility. This talk will explore multiple-source DRC architectures that are commonly used for music but could also be advantageous for hearing devices.

What users’ musical preference on Twitter reveals about psychological disorders

Previous research found a strong relation between the users’ psychological disorders and their language use in social media posts in terms of vocabulary selection, emotional expressions, and psychometric attributes. However, although studying the association between psychological disorders and musical preference is considered as rather an old tradition in the clinical analysis of health data, it is not explored through the lens of social media analytics. In this study, we investigate which attributes of the music posted on social media are associated with mental health conditions of Twitter users. We created a large-scale dataset of 1519 Twitter users with six self-reported psychological disorders (depression, bipolar, anxiety, panic, post-traumatic stress disorder, and borderline) and matched with 2480 control users. We then conduct an observational study to investigate the relationship between the users’ psychological disorders and their musical preference by analyzing lyrics of the music tracks that the users shared on Twitter from multiple dimensions including word usage, linguistic style, sentiment and emotion patterns, topical interests and underlying semantics. Our findings reveal descriptive differences on the linguistic and semantic features of music tracks of affected users compared to control individuals and among users from different psychological disorders. Additionally, we build a feature-based and an (explainable) deep learning-based binary classifiers trained on disorder and control users and demonstrate that lyrics of the music tracks of users on Twitter can be considered as complementary information to their published posts to improve the accuracy of the disorder detection task. Overall, we find that the music attributes of users on Twitter allow inferences about their mental health status.

Is social capital always “Capital”?: Measuring and leveraging social capital in online user communities for in-group diffusion

Literature shows that social capital promotes diffusion in online user communities (OUCs). This research aims to show that social capital acts as a double-edged sword by promoting or suppressing in-group diffusion depending on the compatibility of the product with group identity (i.e., a topic or subject of common interest in the community). We analyze the diffusion of newly released music tracks across multiple communities on Last.fm, a world-leading music social network website. Across all three dimensions of social capital (cognitive, relational, and structural dimensions), we consistently find that the compatibility of the product with group identity moderates the relationship between social capital and in-group diffusion; social capital promotes in-group diffusion of songs that are compatible with group identity but suppresses in-group diffusion of songs that are incompatible with group identity. The findings contribute to the social capital and OUC literature and provide interesting implications for OUC managers.

A Brief Study on Automatic Music Control System using Image Processing

The scope of our project is to control a music player using human gestures. This employs a camera along with an embedded system to segment human gestures and convert them to control signals in real-time. With the help of the Music Controller, one can simply wave or do a simple gesture of hand movement in front of the webcam which will in turn switch or pause the particular music track that was being played. Our project mainly focuses on scenarios where we are multitasking that is working on many applications at a time or running various programs at a time on our desktop and along with that listening to music in background that is music being played in one of the windows. At such times if we wish to pause or switch a particular music track we have to make some movements like switching to the music window and doing the desired operation. With the help of Music Controller, one can simply wave or do a simple gesture of hand movement in front of the webcam which will in turn switch or pause the particular music track that was being played.

Rave Racing

In the origin story of futuristic racing game WipEout (Psygnosis, 1995), co-creator Nick Burcombe talks about turning down the game audio in Super Mario Kart (Nintendo, 1992) and substituting it for his own electronic dance music. Burcombe, who was himself a keen participant in the Liverpool rave scene, argues that people who went clubbing in the 1990s were always looking for new forms of interactive entertainment. WipEout, where players take control of anti-gravity ships and race them to the electronic dance music tracks of artists like Cold Storage, The Chemical Brothers, The Prodigy, and Orbital, was that next step in interactive entertainment.For its marketing campaign, WipEout’s packaging took its inspiration from dance music records and PlayStation installed consoles in nightclubs across the UK. In the follow-up to the original, WipEout 2097 or WipEout XL in North America (Psygnosis, 1996), players could put the game disk into a CD player and hear the soundtrack play out in its entirety, separate from the gameplay. Through a close textual analysis of the first and second versions of the game released on PlayStation, created as they were at the height of electronic dance music culture in the UK in the 1990s, and grounded in popular music studies and ludomusicology, this article inquires into the construction of the video game soundtrack, arguing that WipEout’s audiovisual relationship creates a space where players can become immersed in a rave-related experience of techno in their homes.The research finds that Burcombe and the team at Psygnosis set out not to replicate the rave experience in their video game. Rather, in WipEout, dance music is used to immerse players in a mediated extension of the contemporary UK rave venue or club. As players move their racers onscreen, they engage in actions that edge them closer to the game’s soundtrack itself, in its use of repetition and pulsating beats, as an embodied or corporeal performance. Rather than dancing to rave, WipEout’s players are gaming to techno.

Video-to-Music Recommendation Using Temporal Alignment of Segments

We study cross-modal recommendation of music tracks to be used as soundtracks for videos. This problem is known as the music supervision task. We build on a self-supervised system that learns content association between music and video. In addition to adequacy of content, adequacy of structure is crucial in music supervision to obtain relevant recommendations. We propose a novel approach to significantly improve the system's performance using structure-aware recommendation. The core idea is to consider not only the full audio-video clips, but rather shorter segments for training and inference. We find that using semantic segments and ranking the tracks according to sequence alignment costs significantly improves the results. We investigate the impact of different ranking metrics and segmentation methods.

“A very special song from Queen to you!” The role of music in destination promotional videos

PurposeThis study aims to contribute to the discussion on the interplay between music and destination advertising by exploring the roles of music in destination promotional videos (DPVs).Design/methodology/approachEight focus group discussions on DPVs about Budapest (Hungary) were assessed through thematic analysis. Individuals’ interactions with and perceptions of advertising can be explored in depth through the former, whereas the latter allowed to identify the roles of music in DPVs.FindingsResults show that music plays a very important role in DPVs in which it acts as a conveyor. Viewers associate a DPV’s musical elements and genre with a destination’s character. Here, the use and remix of traditional music was felt to be controversial because of its ability to communicate cultural identity. The music caught the audience’s attention, elicited emotions in them and made them think about the destination in question. An original music track can make a video memorable.Research limitations/implicationsA convenience sample was used with international and Hungarian university students for the focus groups.Practical implicationsMusic is a powerful conveyor of the particular characteristics of a destination and if the structural elements of music, such as tempo, rhythm and dynamics, are chosen appropriately, tourism marketers can create compelling promotional videos. By recognising that different audiences are attracted by different genres of music, marketers can target specific tourist segments. Furthermore, tourism marketers are advised to ask locals’ opinions about which music best represents their city’s cultural identity.Originality/valueThrough an understanding of the important role of music in DPVs, this study provides a novel insight into assessing young people’s cognitive and affective responses to music in promotional videos.

Induced Emotion-Based Music Recommendation through Reinforcement Learning

Music is widely used for mood and emotion regulation in our daily life. As a result, many research works on music information retrieval and affective human-computer interaction have been proposed to model the relationships between emotion and music. However, most of these works focus on applications in a context-sensitive recommendation that considers the listener’s emotional state, but few results have been obtained in studying systems for inducing future emotional states. This paper proposes Moodify, a novel music recommendation system based on reinforcement learning (RL) capable of inducing emotions in the user to support the interaction process in several usage scenarios (e.g., games, movies, smart spaces). Given a target emotional state, and starting from the assumption that an emotional state is entirely determined by a sequence of recently played music tracks, the proposed RL method is designed to learn how to select the list of music pieces that better “match” the target emotional state. Differently from previous works in the literature, the system is conceived to induce an emotional state starting from a current emotion instead of capturing the current emotion and suggesting certain songs that are thought to be suitable for that mood. We have deployed Moodify as a prototype web application, named MoodifyWeb. Finally, we enrolled 40 people to experiment MoodifyWeb, employing one million music playlists from the Spotify platform. This preliminary evaluation study aimed to analyze MoodifyWeb’s effectiveness and overall user satisfaction. The results showed a highly rated user satisfaction, system responsiveness, and appropriateness of the recommendation (up to 4.30, 4.45, and 4.75 on a 5-point Likert, respectively) and that such recommendations were better than they thought before using MoodifyWeb (6.45 on a 7-point Likert).

Evolutions, Transformations and Trends in Kalenjin Traditional Songs

ABSTRACT Since the production of the earliest Kalenjin traditional albums in the 1920s, the community’s traditional songs have evolved and transformed. This article traces this historical process by considering how these songs developed from folk songs performed during Kambaget (sports competitions) and from the earliest compositions of Bekyibei arap Mosonik, Kipchamba arap Tapotuk and their contemporaries, to the modern-day Kalenjin popular hits. The article documents the earliest recordings of Kalenjin music tracks as well as the bands, and traces the legacies of Kipchamba’s Koilong’et Band from the artists of 1940s and those of the later decades through to the younger generations of the 1990s, 2000s and today. This is done in order to determine the zones of contact as well as departures from prototypical and popular Kalenjin traditional songs. Taking the 1990s liberation of the airwaves as focus, this essay analyses the extraordinary variety and complexity of “The Oldies” and compares these to contemporary artistic products that have recycled aspects of this historical canon.

Tchaikovsky Music Recommendation Algorithm Based on Deep Learning

In recent years, digital music is becoming more and more popular as mobile Internet and streaming media technology advance. Traditional music indexing technology mainly uses keywords to query. To find their favorite music, people must search through the vast amount of music available on the Internet nowadays, much like hunting for a needle in a haystack. In the era of mobile Internet, people’s pace of life is very fast. Devices can access the network anytime and anywhere. Users have the habit of listening to music in their daily work, study, or sports. Facing the vast music library, personalized music recommendation can help users quickly and accurately find music tracks that meet their interests, which is also the focus of current music recommendation technology. According to the characteristics of Tchaikovsky music, in this paper, we establish and build an approach that can understand situations and recommend by using the additional information of labels to describe Tchaikovsky music and realize a structure on this foundation. Through user involvement, the system can deliver services akin to network radio and complete the evaluation of the Tchaikovsky music recommendation algorithm’s efficacy.

Large-Scale Music Genre Analysis and Classification Using Machine Learning with Apache Spark

The trend for listening to music online has greatly increased over the past decade due to the number of online musical tracks. The large music databases of music libraries that are provided by online music content distribution vendors make music streaming and downloading services more accessible to the end-user. It is essential to classify similar types of songs with an appropriate tag or index (genre) to present similar songs in a convenient way to the end-user. As the trend of online music listening continues to increase, developing multiple machine learning models to classify music genres has become a main area of research. In this research paper, a popular music dataset GTZAN which contains ten music genres is analysed to study various types of music features and audio signals. Multiple scalable machine learning algorithms supported by Apache Spark, including naïve Bayes, decision tree, logistic regression, and random forest, are investigated for the classification of music genres. The performance of these classifiers is compared, and the random forest performs as the best classifier for the classification of music genres. Apache Spark is used in this paper to reduce the computation time for machine learning predictions with no computational cost, as it focuses on parallel computation. The present work also demonstrates that the perfect combination of Apache Spark and machine learning algorithms reduces the scalability problem of the computation of machine learning predictions. Moreover, different hyperparameters of the random forest classifier are optimized to increase the performance efficiency of the classifier in the domain of music genre classification. The experimental outcome shows that the developed random forest classifier can establish a high level of performance accuracy, especially for the mislabelled, distorted GTZAN dataset. This classifier has outperformed other machine learning classifiers supported by Apache Spark in the present work. The random forest classifier manages to achieve 90% accuracy for music genre classification compared to other work in the same domain.

Does Environmental Enrichment with Music and Strobe Light Affect Broilers’ Welfare? Analyzing Their On-Farm Reaction

The present study observed whether environmental enrichment (music and strobe light) influenced farm-housed broiler chickens’ behavior. The trial was carried out on a commercial broiler farm from 21 to 35 days of growth. The sound stimulus consisted of playing a classical music track every day for an approximate length of 6 min, played five times a day for six weeks starting from the birds’ first day of age. The light stimuli came from a colored (red and green ground-projected dots) light-emitting diode (LED) strobe projector used after the musical stimulation. The broilers’ reaction was recorded (from day 21 through day 35), and individual bird behaviors were classified into welfare and stress. The birds’ ability to walk was measured using a gait score scale, and the degree of incidence of pododermatitis was verified. Environmental enrichment with light stimulus increased natural behavior in broiler chickens, such as eating, stretching, ground pecking, and flapping wings (p < 0.05). Broiler chickens tended to walk less in the housing with music stimuli (p < 0.05). In general, the environmental stimuli provided the birds with better walking ability but increased the incidence of pododermatitis (p < 0.01). We observed that the light stimulus left the birds more active; they foraged more and lay less when compared to the birds submitted to musical stimuli and the control. However, we also observed an increase in the frequency of stress-indicating behaviors in the environment under light stimulation. It is unclear whether broilers liked the tested stimuli of music and light in the scenarios studied. The enrichment with light or music apparently increased flock stress in 21- and 28-day-old broilers, with some benefit being observed only in 35-day-old broilers.

Machine Learning–based Modeling and Prediction of the Intrinsic Relationship between Human Emotion and Music

Human emotion is one of the most complex psychophysiological phenomena and has been reported to be affected significantly by music listening. It is supposed that there is an intrinsic relationship between human emotion and music, which can be modeled and predicted quantitatively in a supervised manner. Here, a heuristic clustering analysis is carried out on large-scale free music archive to derive a genre-diverse music library, to which the emotional response of participants is measured using a standard protocol, consequently resulting in a systematic emotion-to-music profile. Eight machine learning methods are employed to statistically correlate the basic sound features of music audio tracks in the library with the measured emotional response of tested people to the music tracks in a training set and to blindly predict the emotional response from sound features in a test set. This study found that nonlinear methods are more robust and predictable but considerably more time-consuming than linear approaches. The neural networks have strong internal fittability but are associated with a significant overfitting issue. The support vector machine and Gaussian process exhibit both high internal stability and satisfactory external predictability in all used methods; they are considered as promising tools to model, predict, and explain the intrinsic relationship between human emotion and music. The psychological basis and perceptional implication underlying the built machine learning models are also discussed to find out the key music factors that affect human emotion.

Music to the individual consumer’s ears: how and why does personalizing music in advertising enhance viewing duration and ad effectiveness?

This research examines the effects of ad music personalization, which creates a fit between the ad music and consumer’s music preferences, on responses to ads. Based on the benefits of personalization and music liking, we hypothesized that ad music personalization would positively affect ad view time and attitudes toward the ad. We also explored effects on attitudes toward the advertised product. We further hypothesized that perceived ad duration plays a role in responses to personalized ad music. We conducted two experiments that simulated a natural environment of viewing skippable online ads accompanied by music tracks. Study 1 tested the effects of measured music liking, whereas Study 2 manipulated the music to either match or not match participants’ preferences. As expected, we found a consistent positive effect of ad music personalization on ad view time. Study 1 revealed that this effect counteracts the general trend of diminishing ad view time as a function of later placement in a batch. Study 2 further found that personalized ad music reduces perceived ad duration, positively affecting ad attitudes as well. Effects on attitudes toward the advertised product were less pronounced. Thus, this research, which uniquely focuses on personalization of an ad’s background factor, offers nuanced insights into an instrument that has never been studied before, and may enhance the effectiveness of marketing communications through its impact on consumer reactions.

Micro-Doppler Detection and Vibration Sensing Using Silicon-Based THz Radiators

In this paper, vibration sensing and micro-Doppler measurements are performed using THz CW and pulse radiator chips in GlobalFoundries 90-nm SiGe BiCMOS process. The pulse source radiates a frequency comb with tones ranging from 10s of GHz up to 1.1 THz, where the spacing between two adjacent tones can be tuned using an external low-frequency source. In THz frequency range, subtle vibrations on the surface of a target results in phase change of the incident beams. Therefore, compared to RF and mm-wave frequency regimes, THz band offers a higher resolution for picking up the signature of subtle sound vibrations. The phase-modulated reflected beams carry the information of the original sound waves resulting in the spectral side tones. The original sound wave is then recovered by down-conversion of THz waves and FM demodulation. In addition, the time-domain phase information is captured by performing I/Q analysis on the down-converted signal allowing us to characterize the vibrations with a high resolution. Moreover, THz interferometry for vibration sensing is demonstrated using THz Continuous Wave (CW) radiator chip enabling the detection of sub- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu \text{m}$ </tex-math></inline-formula> vibrations with a sensitivity of 30 nm. In this work, various measurements with different types of audio signals including monotone, chirp, and a music track with the frequency range of 100 Hz up to 1 kHz are performed.

Regulation of LTP at rat hippocampal Schaffer-CA1 in vitro by musical rhythmic magnetic fields generated by red-pink (soothing) music tracks

Purpose Music therapy, like red-pink (soothing) music, is an important treatment for neurological disorders associated with learning and memory. Magnetic fields have been proved to have a similar regulating effect. However, the effect of magnetic fields with musical rhythm generated by the combination of the two has not been confirmed. This study aimed to investigate the regulation of magnetic stimulation with music rhythm on LTP (long-term potentiation) of Schaffer-CA1. Materials and methods This article selected three sorts of music tracks in different frequencies (music track (1) Turkish March, music track (2) Moonlight Sonata, music track (3) Funeral March) and four sorts of pure sinusoidal tracks of four different harmonic frequency (music track (4) the frequency is 3500 Hz; music track (5) the frequency is 2500 Hz; music track (6) the frequency is 1500 Hz; music track (7) the frequency is 500 Hz). These music tracks are converted into analog signals by the external sound card and power amplifier and fed into a homemade coil that meets the demand for this frequency bandwidth. The coil can generate seven sorts of time-varying magnetic fields with musical rhythm with a mean intensity of about 2 mT. We used multi-electrode array (MEA) to record the LTP signals of Schaffer-CA1 synaptic induced by seven sorts of musical rhythmic magnetic fields and analyze the regulation of them. Results The musical rhythmic magnetic fields generated by track 1 and track 2 have a remarkable enhancing effect on the amplitude of fEPSPs (field excitatory postsynaptic potentials) (p < .05), and these effects intensify with the increase of frequency. Nevertheless, there is no significant enhancing effect on LTP of the rhythmic magnetic field generated by track 3 (p > .05). The sinusoidal magnetic fields generated by track 4 and track 5 have an enhancing effect on the amplitude of fEPSPs (p < .05), and the enhancement is better than track 1 and track 2. The sinusoidal magnetic fields generated by track 6 and track 7 have an inhibiting effect (p < .05). Conclusion We found that the enhancing effect of musical rhythmic magnetic fields generated by track 1 was the most significant. The frequency of 1500 Hz could be a turning-point frequency in the regulation of magnetic field on LTP.

Automatic Recommendation of Online Music Tracks Based on Deep Learning

It is one of the main goals of personalized music recommendation system that how to accurately recommend the songs in line with users’ interests in the huge music library. In view of the above problems, this study proposes a personalized music recommendation method based on convolutional neural network. First, this study defines a training set containing potential musical characteristics and, combined with the depth of the belief network, design a music information prediction model and the research in the music-type classification method with different dimensions. Based on selecting four different kinds of music information better describing the underlying characteristics of 40D feature vector to every song music composition, the music feature set is constructed. Then, the CNN (convolutional neural network), which is widely used in audio field, is used as the music information prediction model, and its structural parameters are redesigned to complete the multidimensional music information prediction, which solves the cold start problem to some extent.

Being recognized in an algorithmic system: Cruel optimism in gay visibility on Douyin and Zhihu

Drawing upon “algorithmic ethnography” (Christin, 2020), this article enrolls algorithms to gather qualitative data to examine how Chinese social media platforms and their algorithms intersect with gay visibility. By looking critically into the ways that gay romance and HIV-related content are generated on Douyin and Zhihu, respectively, we argue that algorithmic gay visibility serves as a form of cruel optimism, which becomes a profitable convenience for corporate social media platforms and operates in an exclusionary matrix. The content that ordinary Chinese gay men are presented with (for example, the able-bodied, romanticized normative gay relationship and overly optimistic self-help advice for gay men living with HIV) is economically viable, which produces trending and monetizable items, including music tracks, viral dance routines and challenges, personas, medicine promotions, as well as commercial healthcare training and marketing. In contrast, non-conforming bodies, non-monogamous and queer relationships, as well as the depression, stigma and discrimination experienced by gay men living with HIV are algorithmically invisible.