Song Segments Research Articles

Verse1-Chorus-Verse2 Structure: A Stacked Ensemble Approach for Enhanced Music Emotion Recognition

In this study, we present a novel approach for music emotion recognition that utilizes a stacked ensemble of models integrating audio and lyric features within a structured song framework. Our methodology employs a sequence of six specialized base models, each designed to capture critical features from distinct song segments: verse1, chorus, and verse2. These models are integrated into a meta-learner, resulting in superior predictive performance, achieving an accuracy of 96.25%. A basic stacked ensemble model was also used in this study to independently run the audio and lyric features for each song segment. The six-input stacked ensemble model surpasses the capabilities of models analyzing song parts in isolation. The pronounced enhancement underscores the importance of a bimodal approach in capturing the full spectrum of musical emotions. Furthermore, our research not only opens new avenues for studying musical emotions but also provides a foundational framework for future investigations into the complex emotional aspects of music.

Goal-directed and flexible modulation of syllable sequence within birdsong

Songs constitute a complex system of vocal signals for inter-individual communication in songbirds. Here, we elucidate the flexibility which songbirds exhibit in the organizing and sequencing of syllables within their songs. Utilizing a newly devised song decoder for quasi-real-time annotation, we execute an operant conditioning paradigm, with rewards contingent upon specific syllable syntax. Our analysis reveals that birds possess the capacity to modify the contents of their songs, adjust the repetition length of particular syllables and employing specific motifs. Notably, birds altered their syllable sequence in a goal-directed manner to obtain rewards. We demonstrate that such modulation occurs within a distinct song segment, with adjustments made within 10 minutes after cue presentation. Additionally, we identify the involvement of the parietal-basal ganglia pathway in orchestrating these flexible modulations of syllable sequences. Our findings unveil an unappreciated aspect of songbird communication, drawing parallels with human speech.

Time to Document

In recent years, Björk has defied pop music criticism’s persistent myth of male genius by asserting her authorship as a singer, songwriter, composer, and producer. She expressed these concerns during a 2015 Pitchfork interview with Jessica Hopper by reflecting on the press’s minimization of her production work throughout her career and her desire to reclaim her creative authority as a model for younger female-identified artists. During this portion of the conversation, she mused, “I’ve sometimes thought about releasing a map of all my albums and just making it clear who did what.” Her impulse to challenge masculinist creation myths through documentation became the catalyst for Björk: Sonic Symbolism, a 2022 podcast miniseries sponsored by Mailchimp in which she discussed her albums’ creative processes with friends Oddný Eir and Ásmundur Jónson in a series of interviews. The title, which Björk defines as “a visual shortcut to describe sound,” provides the podcast’s framework for her articulation of authorial control, which she examines through album art that illustrates each cover’s mood and character; poetic synopses of each album’s unique audiovisual language; and references to her various studio, video, and stage collaborators. By using close listening to examine Björk’s conversations with Eir and Jónson and the episodes’ illustrative song segments, this article posits that Björk’s engagement with podcasting as an audio storytelling medium allows her to foreground her distinct speaking and singing voice as both a feminist intervention upon the recording industry and as a sonic metaphor for authorial control.

Historical Types of Folklore Thinking in the Lyrical Songs of Sloboda Ukraine

The aim of the article is to identify historical types of folklore thinking: the modal-tune and integration-melodic types in song lyrics based on the folk song tradition of Sloboda Ukraine. Results. The figurative content of archetypes of folklore thinking is expressed by rhythmic and melodic codes as a sound embodiment of symbolic and logical figures of thinking. In the process of development, they were assigned to certain song forms and acquired features of functional differentiation into ritual, epic, and lyrical with a predominance of a certain modality: exclamatory, persuasive, and later narrative. On the basis of the narrative modality, which prevails in the genre of lyrical songs and ballads, the lyrical mode of thinking emerges within the local folklore environment. Song examples representing the drawling type of chanting of lyrical songs can be attributed to the modal-tune type of folklore thinking. The integration-melodic type of folklore thinking is characterised by fundamental changes in the process of musical development based on logical figures of grouping and classification. The transfer of the main function to the highest solo voice, the concentration of the intonation content in it, affected the creation of melody. The scientific novelty consists in substantiating the modal-tune and integration-melodic types of folklore thinking on the material of the song lyrics of Sloboda Ukraine. Conclusions. Lyrical songs of modal-tune type create the song stanza by alternating autonomous song segments caesurated according to the logic of musical development. In the chants of integration-melodic types, the highest voice of sub-chant polyphonic structure acquires the properties of a melody thanks to the concentration of the intonation content and the character of the caesura. The structure of the chant becomes more symmetrical, with the features of a responsive stanza.

Stalin's Houses on Lenin Street: Late Soviet Underground Rock in Patriotic Discourse (1981-1991)

The subject of the study is the late Soviet underground rock song both in the general context of Soviet popular culture and in the context of patriotic discourse in the Soviet popular song of the 1960s-1980s. The correlation of various segments of Soviet popular music and their access to mass communication media, the phenomenon of the transformation of rock music from a marginal subculture into one of the segments of popular Soviet song is considered. Concrete examples demonstrate the content versatility of an uncensored Soviet rock song, in particular, its contribution to patriotic discourse. The duration and stability of the existence of the considered variations of patriotic discourse are considered. The main conclusions of the study include: -the development of mass/popular songs is directly dependent on the development of mass communication and access to them; -in the 1960s-1980s, the Soviet state lost its monopoly on the ownership of means of delivering music content to the listener; - by the early 1980s Soviet rock music ceased to be a copy of the Western model and became a Soviet/Russian song genre based on domestic melodics, Russian literary poetic tradition, etc.; -the access to the means of delivering song content turned rock song into a segment of Soviet popular music, both censored and in uncensored versions; -the socio-political content in general and the patriotic theme in particular were not an attribute exclusively of the official Soviet song, but found their expression in the work of the authors of the underground rock scene; - the Soviet popular uncensored song made the patriotic discourse much more diverse, rich, sharp, etc. - the identified interpretations of patriotic discourse have a stable existence, being actualized in the modern media environment.

EXPLORING THE CONJUNCTION OF CHILDHOOD AND RITUALS: AN ANALYTICAL STUDY OF KUTHIYOTTAM BASED ON SELECT TEMPLES IN KERALA

Kerala has a rich repertoire of folk arts and forms. The diverse culture of the place gives expression to these forms. Kuthiyottam is a ritualistic offering unique to the Devi temples of Kerala. It is a mélange of physical and religious facets. Though the performance has its basis on human sacrifice, it entails a perfect synchronization of song and dance movements. Despite exhibiting certain common traits, the practice varies markedly across various regions. The study primarily focuses on the Kuthiyottam performance prevalent in Pulimath Devi Temple in Thiruvananthapuram, while also examining the regional variations at Attukal and Chettikulangara temples. Kummi and Kavithavum are distinct segments of Kuthiyottam songs. The songs are predominantly focused on the veneration of the deity but also encompass characters from the epic. Boys aged eight to twelve are chosen for the ritual. Accompanied by percussion, children are led in front of the deity and the ritual of ‘chooralkuthu’, piercing by cane is done on the flanks of the children. The paper intents to explore the conjunction of childhood and rituals concerning the performing folk art, Kuthiyottam.

Hip Hop Mun Ikjeom

Research Article| March 01 2023 Hip Hop Mun Ikjeom: The Life and Music of Hyun Jin Young Myoung-Sun Song Myoung-Sun Song Dr. Myung-Sun Song is an assistant professor in the Department of East Asian Languages and Cultures at the University of Illinois, Urbana-Champaign. Her research focuses on the representations of race, gender, sexuality, class, and national identity in Korean media and popular culture. She is the author of Hanguk Hip Hop: Global Rap in South Korea (2019, Palgrave Macmillan), the first scholarly book-length study in English or Korean on the subject of Korean hip hop. Search for other works by this author on: This Site PubMed Google Scholar Journal of Popular Music Studies (2023) 35 (1): 4–19. https://doi.org/10.1525/jpms.2023.35.1.4 Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Share Icon Share Facebook Twitter LinkedIn MailTo Tools Icon Tools Get Permissions Cite Icon Cite Search Site Citation Myoung-Sun Song; Hip Hop Mun Ikjeom: The Life and Music of Hyun Jin Young. Journal of Popular Music Studies 1 March 2023; 35 (1): 4–19. doi: https://doi.org/10.1525/jpms.2023.35.1.4 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentJournal of Popular Music Studies Search In the early to mid-1990s, groups such as Hyun Jin Young and Wawa, Seo Taiji and Boys, and DEUX helped introduce hip hop to Korean audiences by incorporating rap into mainstream dance music and performance. This style will later be labelled “rap dance,” a precedent to K-pop, where rap is frequently formulated into segments of dance songs.1 During this period, television—particularly channels like AFKN and later MTV—served as a gateway to American hip hop for Korean youth. An important coinciding moment is the 1992 LA Riots, which would have an impact on how Koreans viewed Black American communities and how hip hop was perceived in South Korea during its formative years. These sociocultural and historical conditions set the backdrop for the rise of Hanguk hip hop [Korean hip hop] from the mid- to late-1990s, when Korean fans of American hip hop—through the help of technology, most notably personal computer... You do not currently have access to this content.

Песенные вставки в сказочном фольклоре лесных юкагиров

This paper analyzes the song inclusions in the tales of Forest Yukaghirs, the content of such pieces, their purposes, and origin. Song segments are found in animal tales, including mythological ones, fairy tales about a Fabulous Old Man-eater, and everyday fairy tales. The song inclusions mostly convey the monological speech of the characters and include lexical repetitions. The song inclusions considered are mainly the magical appeal of one hero to another, a personal story, or a real personal situation. Some of them can be characterized as personal songs. Characters endowed with supernatural powers use the song as a magical ritual. These characters include heroes with shamanic powers and the ogre giant, the Fabulous Old Man. The magical potential of the song, aimed at summoning and embodying something, can also be evoked by ordinary people, even unintentionally. Songs-appeals of some characters to others are performed in magical situations, facilitating their manifestation. The fairy tales provide indirect indications of the shamanic power of the singing characters. Alternatively, the songs addressed to other persons can be performed by ordinary characters, usually represented by animals. Songs as personal narratives or real personal situations can be found mainly in the tales about animals. The song inclusions are based on the representations of shamanic activity, magical abilities, and the song type of storytelling, as evidenced by the existence of both non-fairy and fairy tale Yukaghir prose.

A Meditation on Loss

A Meditation on Loss

Enhancing the Detection of Misogynistic Content in Social Media by Transferring Knowledge From Song Phrases

Misogyny is a severe social problem that affects women’s mental and physical health or even leads to femicide. This cultural problem is visible and prevalent in different communication channels, such as music and social media, confirming or inciting this behavior. Hence, the automatic detection of misogynistic content in social media using computational methods that analyze the language is of increasing interest. Most approaches follow a supervised machine learning strategy, with the main challenge of capturing the diversity and complexity of the offensive language directed at women. Therefore, the size and quality of the training data play essential roles. In this context, we designed a novel data augmentation approach that leverages song phrases to increase the models’ ability to generalize and improve their performance. In addition, this paper introduces a methodology to compile a labeled dataset with song segments conveying misogyny, which can be used to enrich different techniques in this field. The proposed approach was evaluated using English and Spanish benchmark datasets. It successfully overcomes conventional transfer learning techniques and achieves high competitiveness compared with state-of-the-art methods, outperforming them on the Spanish dataset. These encouraging results demonstrate the usefulness of the proposed approach.

Unsupervised classification to improve the quality of a bird song recording dataset

Open audio databases such as Xeno-Canto are widely used to build datasets to explore bird song repertoire or to train models for automatic bird sound classification by deep learning algorithms. However, such databases suffer from the fact that bird sounds are weakly labelled: a species name is attributed to each audio recording without timestamps that provide the temporal localization of the bird song of interest. Manual annotations can solve this issue, but they are time consuming, expert-dependent, and cannot run on large datasets. Another solution consists in using a labelling function that automatically segments audio recordings before assigning a label to each segmented audio sample. Although labelling functions were introduced to expedite strong label assignment, their classification performance remains mostly unknown. To address this issue and reduce label noise (wrong label assignment) in large bird song datasets, we introduce a data-centric novel labelling function composed of three successive steps: 1) time-frequency sound unit segmentation, 2) feature computation for each sound unit, and 3) classification of each sound unit as bird song or noise with either an unsupervised DBSCAN algorithm or the supervised BirdNET neural network. The labelling function was optimized, validated, and tested on the songs of 44 West-Palearctic common bird species. We first showed that the segmentation of bird songs alone aggregated from 10% to 83% of label noise depending on the species. We also demonstrated that our labelling function was able to significantly reduce the initial label noise present in the dataset by up to a factor of three. Finally, we discuss different opportunities to design suitable labelling functions to build high-quality animal vocalizations with minimum expert annotation effort.

Should more effortful utterances map to more elaborate signals?

Many songbirds tune the frequency of their whistled vocalizations by varying the length of their vocal tract. To do this, they must open their bills wider to produce higher tones and then close them again for lower pitches. The time course of frequency variation in such a bird's song, thus, maps directly to the time course of motor effort by its bill. In 2016, Podos et al. described frequency excursion as “for any given song or song segment, the sum of frequency modulations both within and between notes on a per-time basis.” As predicted from the previous work, birds with larger bills are constrained to produce less frequency excursion than birds with smaller bills. After reviewing this result, I will elaborate on ways to extend the idea of a map between motor effort and signal characteristic from one-to-one to many-to-many.

Song Imitation in Congenital Amusia

Congenital amusia is a neurogenetic disorder of pitch perception that may also compromise pitch production. Despite amusics’ long documented difficulties with pitch, previous evidence suggests that familiar music may have an implicit facilitative effect on their performance. It remains, however, unknown whether vocal imitation of song in amusia is influenced by melody familiarity and the presence of lyrics. To address this issue, thirteen Mandarin speaking amusics and 13 matched controls imitated novel song segments with lyrics and on the syllable /la/. Eleven out of these participants in each group also imitated segments of a familiar song. Subsequent acoustic analysis was conducted to measure pitch and timing matching accuracy based on eight acoustic measures. While amusics showed worse imitation performance than controls across seven out of the eight pitch and timing measures, melody familiarity was found to have a favorable effect on their performance on three pitch-related acoustic measures. The presence of lyrics did not affect either group’s performance substantially. Correlations were observed between amusics’ performance on the Montreal Battery of Evaluation of Amusia and imitation of the novel song. We discuss implications in terms of music familiarity, memory demands, the relevance of lexical information, and the link between perception and production.

Multifractal analysis of birdsong and its correlation structure.

The time series recordings of typical songs of songbirds exhibit highly complex and structured behavior, which is characteristic of their species and stage of development, and need to be analyzed by methods that can uncover their correlation structure. Here we analyze a typical song of a canary using Hurst exponents and multifractal analysis, which uncovers the correlation structure of typical song segments. These are then compared with the corresponding quantities from shuffled data, which destroys the temporal correlations and iterative amplitude-adjusted Fourier transform (IAAFT) data. It is seen that temporal correlations are responsible for the multifractal behavior seen in the data and that two-point correlations, which are preserved by the transform, are important in the high-fluctuation regime. Higher-order correlations and intersyllabic gaps dominate the behavior of the low-fluctuation regime. These observations are supported by the simplicial characterization of the corresponding time series networks. Complexity measures are also used to analyze the amplitude envelope time series. These indicate that intersyllabic gaps contribute a significant fraction to the complexity of the birdsong. Our method provides a detailed characterization of the data, which can enable the comparison of real and synthetic birdsong and comparisons across stages of development and species. A brief comparison with the song of the zebra finch supports this.

O Canto Livre de Nara Leão: Engajamento Artístico, Sonoridade e Gesto Vocal

Nara Leão, a name immediately associated with bossa nova, though little of her production was really associated with bossa nova during the 1960s. At the beginning of the decade, Nara and some of her colleagues changed the directions of Brazilian popular music by approaching more intellectual artists of theater and cinema as well as sectors of the Brazilian left. They effectively established a new song segment, setting the stage for what would be later called "Brazilian protest song". In this article, we take O canto livre de Nara (her third LP) as a privileged object to understand the way in which the interpreter's vocal gesture seems to converge with certain poetic and political perspectives prevailing in the period.

The Effects of Odd Time Signatures on Pop Song Enjoyment

Odd time signatures are a music theory concept and are not used often in modern pop music. Additionally, a significant issue of unoriginality is occurring in the modern pop song genre, and very little research has been conducted on time signatures. A study was conducted on how the time signature of a song impacts the enjoyment of a pop song in order to find a solution for artists to improve the quality of their songs. High school music students listened to both previously released pop songs and self-composed variations on a single pop song, rating each song after each listen in order to find this solution. The average enjoyment of all of the ratings of common time signature pop songs were statistically compared to the average enjoyment of all of the ratings of odd time signature pop songs. The previously released pop song segment of the study found that previously released common time signature pop songs were enjoyed significantly more than previously released odd time signature pop songs, but this part may have been subject to dramatic confounding variables. The second part of the study found that there was no significant difference in the average enjoyment of odd time signature variations than the average enjoyment of common time signature variations. These results imply that fans of pop artists would enjoy their songs no less depending on the time signature, and thus pop song artists can increase the originality of their songs by utilizing odd time signatures with almost no consequence.

Mechanisms of Cultural Evolution in the Songs of Wild Bird Populations.

Young songbirds draw the source material for their learned songs from parents, peers, and unrelated adults, as well as from innovation. These learned songs are used for intraspecific communication, and have well-documented roles for such functions as territory maintenance and mate attraction. The songs of wild populations differ, forming local “dialects” that may shift over time, suggesting that cultural evolution is at work. Recent work has focused on the mechanisms responsible for the cultural evolution of bird songs within a population, including drift, learning biases (such as conformity and rare-form copying), and selection (including sexual selection). In many songs or song repertoires, variability is partitioned, with some songs or song segments being stable and consistent, while others vary within the population and across time, and still others undergo population-wide transitions over time. This review explores the different mechanisms that shape the cultural evolution of songs in wild populations, with specific reference to a long-term investigation of a single population of philopatric Savannah sparrows. Males learn a single four-segment song during their 1st year and sing the same song thereafter. Within this song, the buzz segment is a population marker, and may be stable for decades – variant forms occur but eventually disappear. In contrast, the middle segment is highly variable both within the population and over time; changes in relative prevalence of different forms may be due to cultural drift or a rare-form learning bias. Within the introductory segment, a high note cluster was replaced by a click train between 1982 and 2010, following an S-shaped trajectory characteristic of both selective sweeps in population genetics and the replacement of one form by another in human language. In the case of the Savannah sparrows, this replacement may have been due to sexual selection. In subsequent generations, the number of clicks within trains increased, a form of cultural directional selection. In contrast to the narrowing of a trait's range during directional selection in genetic systems, variation in the number of clicks in a train increased as the mean value shifted because improvisation during song learning allowed the range of the trait to expand. Thus, in the single short song of the Savannah sparrow, at least four different mechanisms appear to contribute to three different types of cultural evolutionary outcomes. In the future, it will be import to explore the conditions that favor the application of specific (and perhaps conditional) learning rules, and studies such as the ongoing song seeding experiment in the Kent Island Savannah sparrow population will help in understanding the mechanisms that promote or repress changes in a population's song.

Deep embedded clustering of coral reef bioacoustics.

Deep clustering was applied to unlabeled, automatically detected signals in a coral reef soundscape to distinguish fish pulse calls from segments of whale song. Deep embedded clustering (DEC) learned latent features and formed classification clusters using fixed-length power spectrograms of the signals. Handpicked spectral and temporal features were also extracted and clustered with Gaussian mixture models (GMM) and conventional clustering. DEC, GMM, and conventional clustering were tested on simulated datasets of fish pulse calls (fish) and whale song units (whale) with randomized bandwidth, duration, and SNR. Both GMM and DEC achieved high accuracy and identified clusters with fish, whale, and overlapping fish and whale signals. Conventional clustering methods had low accuracy in scenarios with unequal-sized clusters or overlapping signals. Fish and whale signals recorded near Hawaii in February-March 2020 were clustered with DEC, GMM, and conventional clustering. DEC features demonstrated the highest accuracy of 77.5% on a small, manually labeled dataset for classifying signals into fish and whale clusters.

Deep embedded clustering of coral reef bioacoustics

Deep clustering was applied to unlabeled, automatically detected signals in a coral reef soundscape to distinguish fish pulse calls from segments of whale song. Deep embedded clustering (DEC) learned latent features of the signals and formed clusters using fixed-length power spectrograms of the signals. Handpicked spectral and temporal features were also extracted and clustered with Gaussian mixture models (GMM) and conventional clustering. DEC, GMM, and conventional clustering were tested on simulated datasets of fish pulse calls and whale song units with randomized bandwidth, duration, and SNR. Both GMM and DEC achieved high accuracy and identified clusters with fish calls, whale song units, and simultaneous fish calls and whale song units. Conventional clustering methods K-means and hierarchical agglomerative clustering had low accuracy in scenarios with unequally sized clusters or multiple signals. Experimentally detected fish pulse calls and whale song units recorded near Hawaii in February–March 2020 were clustered with DEC, GMM, and conventional clustering. DEC demonstrated the highest accuracy on a small, manually labeled dataset and successfully separated clusters of fish calls and whale song units. GMM achieved high recall for detecting whale song units but accuracy. Both GMM and DEC overpredicted the number of whale song unit signals.

PopMash: an automatic musical-mashup system using computation of musical and lyrical agreement for transitions

Musical-mashup is a popular form of music re-creation, aiming at combining multiple pieces of music to create new music artworks. Presently, it is also a challenge in the field of music information study. In this work, an effective framework for harmonious musical-mashup generation is provided. In the experiment, lyrics, melody, and rhythm of music were synthetically analyzed. The “harmony” of mashup transition was evaluated in view of the similarity scores of rhythm, melody and lyrics rhyme. “Mashupable” song segments were selected based on the transition harmony evaluation. Then, the musical-mashup output was carried out by adjusting the rhythm, tone and loudness of each segment. Finally, we created PopMash based on the proposed method, an automatic musical-mashup system that can make smooth and harmony transitions from multiple perspectives, which can efficiently reduce the manual work of music recreation.