Pair Of Songs Research Articles

TruMuzic: A Deep Learning and Data Provenance-Based Approach to Evaluating the Authenticity of Music

The digitalization of music has led to increased availability of music globally, and this spread has further raised the possibility of plagiarism. Numerous methods have been proposed to analyze the similarity between two pieces of music. However, these traditional methods are either focused on good processing speed at the expense of accuracy or they are not able to properly identify the correct features and the related feature weights needed for achieving accurate comparison results. Therefore, to overcome these issues, we introduce a novel model for detecting plagiarism between two given pieces of music. The model does this with a focus on the accuracy of the similarity comparison. In this paper, we make the following three contributions. First, we propose the use of provenance data along with musical data to improve the accuracy of the model’s similarity comparison results. Second, we propose a deep learning-based method to classify the similarity level of a given pair of songs. Finally, using linear regression, we find the optimized weights of extracted features following the ground truth data provided by music experts. We used the main dataset, containing 3800 pieces of music, to evaluate the proposed method’s accuracy; we also developed several additional datasets with their own established ground truths. The experimental results show that our method, which we call ‘TruMuzic’, improves the overall accuracy of music similarity comparison by 10% compared to the other state-of-the-art methods from recent literature.

An adaptive meta-heuristic for music plagiarism detection based on text similarity and clustering

Plagiarism is a controversial and debated topic in different fields, especially in the Music one, where the commercial market generates a huge amount of money. The lack of objective metrics to decide whether a song is a plagiarism, makes music plagiarism detection a very complex task: often decisions have to be based on subjective argumentations. Automated music analysis methods that identify music similarities can be of help. In this work, we first propose two novel such methods: a text similarity-based method and a clustering-based method. Then, we show how to combine them to get an improved (hybrid) method. The result is a novel adaptive meta-heuristic for music plagiarism detection. To assess the effectiveness of the proposed methods, considered both singularly and in the combined meta-heuristic, we performed tests on a large dataset of ascertained plagiarism and non-plagiarism cases. Results show that the meta-heuristic outperforms existing methods. Finally, we deployed the meta-heuristic into a tool, accessible as a Web application, and assessed the effectiveness, usefulness, and overall user acceptance of the tool by means of a study involving 20 people, divided into two groups, one of which with access to the tool. The study consisted in having people decide which pair of songs, in a predefined set of pairs, should be considered plagiarisms and which not. The study shows that the group supported by our tool successfully identified all plagiarism cases, performing all tasks with no errors. The whole sample agreed about the usefulness of an automatic tool that provides a measure of similarity between two songs.

Vertical Vafa–Witten invariants

We show that vertical contributions to (possibly semistable) Tanaka–Thomas–Vafa–Witten invariants are well defined for surfaces with $$p_g(S){>}0$$ , partially proving conjectures of Tanaka and Thomas (Pure Appl Math Q 13:517–562, 2017) and Thomas (Commun Math Phys 378(2):1451–1500, 2020). Moreover, we show that such contributions are computed by the same tautological integrals as in the stable case, which we studied in Laarakker (Geom Topol 24(6):2781–2828, 2020). Using the work of Kiem and Li, we show that stability of universal families of vertical Joyce–Song pairs is controlled by cosections of the obstruction sheaves of such families.

Two-layer similarity fusion model for cover song identification

Various musical descriptors have been developed for Cover Song Identification (CSI). However, different descriptors are based on various assumptions, designed for representing distinct characteristics of music, and often differ in scale and noise level. Therefore, a single similarity function combined with a specific descriptor is generally not able to describe the similarity between songs comprehensively and reliably. In this paper, we propose a two-layer similarity fusion model for CSI, which combines the information carried by different descriptors and similarity functions organically and incorporates the advantages of both early fusion and late fusion. In particular, in the early fusion, the similarities obtained by the same descriptor and different similarity functions are integrated with the Similarity Network Fusion (SNF) technique. Then, in the late fusion, the learning method selected by sparse group LASSO algorithm is applied on each early fused similarity to obtain the probability that the corresponding song pair belongs to the reference/cover pair. Lastly, the final fused similarity is achieved by averaging all the obtained probabilities. Extensive experimental results on the music collection that is composed of samples provided by the SecondHandSongs (SHS) verify that the proposed scheme outperforms state-of-the-art fusion based CSI schemes in terms of identification accuracy and classification efficiency.

Walk Away Michael Brown (1950–2015)

The Left Banke’s “Walk Away Renee” and “Pretty Ballerina” are arguably the most exquisite pair of songs about unrequited love from the prolific pop playlist of the mid-1960s. Their qualities endure...

Watch Your Tone: Social Conditions Modulate Singing Strategies

AbstractBird song is typically depicted as a male singing a long‐distance signal to potentially unknown receivers to (1) deter males and (2) attract females. Nevertheless, many songbirds sing from close distances to a known receiver; males of these species may be under more intense selective pressure to modify their songs depending on the sex of the receiver in order to convey different motivational states (aggression versus courtship) to the different sexes. In a laboratory setting, we examined how receiver sex affected within‐song variation of the close‐range singing behavior in the brown‐headed cowbird (Molothrus ater). Although we know that cowbird song is influenced by flock composition, it is still unclear as to how the cowbird modifies his song based on social context. Using a cross‐correlation analysis of each male's different song types, we found that pairs of songs were significantly more dissimilar if they were directed to females compared with songs directed to males. We subsequently tested whether there were any consistent spectral or temporal patterns in the songs males gave to females versus to males. Our results lend support for the Motivational Structural Rules Hypothesis as songs directed toward males had higher entropy (i.e., harshness) than the same song type directed toward females. Our results suggest that cowbirds may have evolved the ability to alter multiple dimensions of their singing behavior based on receiver sex.

Wall-crossing and invariants of higher rank Joyce–Song stable pairs

We introduce a higher rank analog of the Joyce–Song theory of stable pairs. Given a nonsingular projective Calabi–Yau threefold $X$, we define the higher rank Joyce–Song pairs given by ${O}^{\oplus r}_{X}(-n)\rightarrow F$ where $F$ is a pure coherent sheaf with one dimensional support, $r>1$ and $n\gg0$ is a fixed integer. We equip the higher rank pairs with a Joyce–Song stability condition and compute their associated invariants using the wallcrossing techniques in the category of “weakly” semistable objects.

Developmental stressors that impair song learning in males do not appear to affect female preferences for song complexity in the zebra finch

A number of recent studies have provided evidence that the environmental factors experienced during development contribute to variation between females in the direction and strength of their mating preferences. The developmental stress hypothesis suggests that the complex male songs of many songbirds and female preferences for those complex songs have evolved because song quality reflects how well an individual was able to cope with suboptimal developmental conditions. In this study, we tested whether female preferences for song complexity are affected by developmental stress. Female zebra finches, Taeniopygia guttata, were raised under conditions of nutritional stress or control conditions. In adulthood, their song preferences were tested in an operant setup where females could trigger playback of song recordings by landing on different perches. The subjects could choose between pairs of songs that were digitally manipulated to ensure that they varied only in the number of syllables in the song. Across all subjects, there was a significant preference for the more complex song of the song pair, but there was no difference between the treatment groups in the direction or strength of their preference. These results suggest that adverse developmental conditions do not impair females' ability or motivation to discriminate between songs on the basis of complexity and thus to obtain information about potential mates' developmental history. Copyright 2011, Oxford University Press.

Song Variation In Buff-Breasted Flycatchers (Empidonax fulvifrons)

I examined song variation within and among 23 individual Buff-breasted Flycatchers (Empidonax fulvifrons) recorded in the Chiricahua and Huachuca mountains of Arizona in 1999. I recorded two distinct song types from each individual during intense pre-dawn singing. I used both spectrographic cross correlation (SPCC) of entire songs and discriminant function analysis (DFA) of temporal and frequency measurements to examine whether songs were individually distinctive, and whether songs differed between the two localities. Similarity values of pairs of songs from SPCC were significantly greater for within-male than for between-male comparisons for both song types. Mean similarity values for the two song types did not overlap between these comparison categories. Similarity values between songs of pairs of males from the same mountain range were not greater than for comparisons between pairs of males from different ranges. All temporal and frequency measures for both song types varied significantly more among than within individuals. DFA of principal component scores derived from these measures assigned 85% of Type 1 and 86% of Type 2 songs to the correct individual. Only three frequency variables measured from Type 1 songs differed significantly between birds from the two mountain ranges. DFA assigned only 61% of songs of either type to the correct mountain range, not significantly greater than expected by chance. Thus, both techniques demonstrate significant individual distinctiveness in songs of this species, and neither suggests any geographic structuring of song variation between the two mountain ranges. However, SPCC is considerably more efficient and has greater potential to assign unknown recordings to known individuals correctly, and to detect recordings of “new” individuals not included in the reference sample.

“Reinventing the Wheel”: A Novel Approach to Music Player Interfaces

We present a novel interface to (portable) music players that benefit from intelligently structured collections of audio files. For structuring, we calculate similarities between every pair of songs and model a travelling salesman problem (TSP) that is solved to obtain a playlist (i.e., the track ordering during playback) where the average distance between consecutive pieces of music is minimal according to the similarity measure. The similarities are determined using both audio signal analysis of the music tracks and Web-based artist profile comparison. Indeed, we show how to enhance the quality of the well-established methods based on audio signal processing with features derived from Web pages of music artists. Using TSP allows for creating circular playlists that can be easily browsed with a wheel as input device. We investigate the usefulness of four different TSP algorithms for this purpose. For evaluating the quality of the generated playlists, we apply a number of quality measures to two real-world music collections. It turns out that the proposed combination of audio and text-based similarity yields better results than the initial approach based on audio data only. We implemented an audio player as Java applet to demonstrate the benefits of our approach. Furthermore, we present the results of a small user study conducted to evaluate the quality of the generated playlists

Developmental stress affects the attractiveness of male song and female choice in the zebra finch (Taeniopygia guttata)

Developmental stress has recently been shown to have adverse effects upon adult male song structure in birds, which may well act as an honest signal of male quality to discriminating females. However, it still remains to be shown if females can discriminate between the songs of stressed and non-stressed males. Here we use a novel experimental design using an active choice paradigm to investigate preferences in captive female zebra finches (Taeniopygia guttata). Nine females were exposed to ten pairs of songs by previously stressed and non-stressed birds that had learned their song from the same tutor. Song pairs differed significantly in terms of song complexity, with songs of stressed males exhibiting lower numbers of syllables and fewer different syllables in a phrase. Song rate and peak frequency did not differ between stressed and non-stressed males. Females showed a significant preference for non-stressed songs in terms of directed perching activity and time spent on perches. Our results therefore indicate that developmental stress affects not only the structure of male song, but that such structural differences are biologically relevant to female mate choice decisions.

Taking it seriously: intertextuality and authenticity in two covers by the Pet Shop Boys

When musicians ‘cover’ a previously recorded song, they provide an intertextual commentary on another musical work or style. This paper considers several ways in which such commentaries engage constructions of authenticity, focusing on two covers by the Pet Shop Boys: ‘Where the Streets Have No Name’, originally by U2, and ‘Go West’, first recorded by the Village People. I analyse the musical sound, performance style, and lyrical themes of each pair of songs, as well as the discourse surrounding their production and reception. I also consider how scholars have theorised authenticity in the interpretive traditions engaged by these songs. I argue that the Pet Shop Boys’ version of ‘Where the Streets Have No Name’ is subversive, poking fun at certain common ways of expressing authenticity in 1980s rock, while their cover of ‘Go West’ repositions disco - a genre that has widely been construed as inauthentic - as a type of ‘roots music’ for the gay community of the 1990s.

Song types as fundamental units in vocal repertoires

We investigated whether song types function as fundamental units of song variation in song sparrows,Melospiza melodia . As the size of a male song sparrow’s repertoire increases, so does the mean similarity of his song types, as measured by the sharing of minimal units of production (MUPs). It follows that if MUP similarity is important perceptually, then small repertoires (of dissimilar song types) may be functionally equivalent to large repertoires (of similar song types). We performed two experiments to test whether MUP similarity is important perceptually to male song sparrows. Both experiments used a habituation/recovery design, in which recovery in response at a switch in stimuli is used to gauge the subject’s perception of the similarity of the stimuli. The results of both experiments indicate that the level of perceived similarity between pairs of songs does not depend on their level of MUP similarity, within the range of MUP similarities found between song types. Songs with high enough MUP similarity to be judged as variants of the same song type are, however, perceived to be much more similar than are any two song types. The results are compatible with a categorical model of song type perception.

Auditory scene analysis by songbirds: stream segregation of birdsong by European starlings (Sturnus vulgaris).

Three experiments examined the capacity of European starlings to segregate perceptually 2 superimposed, intermixed auditory stimuli. The stimuli were 10-s song samples from 2 of 4 songbird species: European starling, brown thrasher, mockingbird, and nightingale. The birds first learned a discrimination between the intermixed song pairs. Then, they maintained the discrimination with novel song exemplars in the mixtures and when song stimuli for each species were presented alone. Performance fell, but remained above chance, when song pairs were mixed with the dawn chorus of bird song. The results show that starlings were identifying the songs of individual species within the baseline superimposed song pairs, a process of auditory stream segregation and scene analysis (A. S. Bregman, 1990).

Song Perception in the Song Sparrow: Importance of Different Parts of the Song in Song Type Classification

AbstractSong sparrow (Melospiza melodia) males have repertoires of 6 to 12 song types, each song consisting of four or five contrasting phrases. Song types vary both within individuals (a singer varies successive renditions of a type within a singing bout) and between individuals (neighbors sing slightly different versions of a type), and in both cases this variation is concentrated in the later parts of the song. We speculated that type variation in the later parts of the song might be correlated with a perceptual tendency to classify song types primarily on the basis of the earlier parts of the song. We tested this hypothesis using a laboratory conditioning technique, supplemented by a field playback experiment. In the lab, song sparrows and white crowned sparrows were trained to discriminate between two distinct song types. In test sessions, they were presented with hybrid songs synthesized from varying proportions of the two training song types. For most birds and most song pairs, song classification was influenced by all parts of the song, with the beginning elements being most important. The field playback experiment used song type matching as the response measure. Each subject was presented a hybrid stimulus song consisting of the first half of one of his song types and the second half of another of his song types. Subjects replied with both ‘front matches’ and ‘back matches’ (60% were front matches).

A Brief History of The Sunken Bell, Carl Ruggles's Unfinished Opera

Carl Ruggles is remembered primarily as the crusty New England composer of a handful of brief but massive orchestral works, fashioned in an intense, rugged, atonal style. The most celebrated of these are Men and Mountains (1927) and Sun-treader (1927-31), generally regarded as his masterpiece. Portals, for strings (ca. 1924), and Organum, for full orchestra (1944) are also considered major works. In addition, he produced several chamber pieces of importance, which include Evocations: Four Chants for Piano (1935-43); Angels, for six muted trumpets (1925), later revised for four trumpets and two trombones (1939); a song for voice and piano, Toys (1919), his first acknowledged composition; and a cycle of three songs, entitled Vox Clamans in Deserto, for voice and chamber orchestra (1923), based on texts by Robert Browning, Charles Henry Meltzer, and Walt Whitman. Although the orchestral works are the most famous of his repertoire, the dates above reveal that his first recognized compositions involve the voice. In addition, most of Ruggles's known juvenilia are for voice. The collections of the Music Division of the Library of Congress preserve the earliest of these, a pair of songs written at the turn of the century. One of them is Ruggles's first published work. It was copyrighted December 29, 1899, and published by C. W. Thompson. The text is a poem by Robert Bums. The printed title page indicates that there were actually three songs by Ruggles slated to be published: How Can I

Memory Does Not Constrain Individual Recognition in a Bird With Song Repertoires

Summary We tested the hypothesis that memory or perceptual limitations imposed by song repertoires contrain the ability of song birds to recognize their neighbours by song. Using operant conditioning procedures, we trained male song sparrows (Melospiza melodia) (median repertoire size = 8) to discriminate between two artificial song sparrow repertoires of 32 songs each (64 songs total). Both song sparrows learned to discriminate concurrently between all 32 song pairs. The birds learned later songs as quickly as they learned earlier songs. These results suggest that song sparrows are capable of memorizing the full song repertoire of their neighbours under natural conditions. In a second experiment we found that song sparrows readily generalize from one exemplar of a song type to other variations of that song type. We conclude that the evolution of song repertoires of song sparrows have neither constrained nor been constrained by individual recognition of neighbours by song.

My Lady's Tears: a pair of songs by John Dowland

It is a curious feature of Dowland's Second Booke of Songs (1600oo) that 'Flow my teares', his texting of the Lachrimae Pavan, is placed second. One might expect that a work already admired, emulated and bowdlerized would more naturally have headed the collection whose melancholy tone it so perfectly encapsulates.1 Wonderful as the preceding song, 'I saw my Lady weepe', may be, is it so special as to deserve pride of place? And why is this song, and not 'Flow my teares', dedicated 'To the most famous, Anthony Holborne', given that it was the Lachrimae Pavan that Holborne had emulated in his own Pavana Ploravit, published the previous year? What has 'I saw my Lady weepe' to do with 'Flow my teares'? An answer bringing with it several more questions lies, barely concealed, in the music. 'I saw my Lady weepe', uniquely among the songs of the Second Booke, ends a 5th away from its tonal focus (on E, in relation to the focal A).' Although at first glance this relationship might seem easily explicable in traditional modal terms, the harmonic language of the song cannot sensibly be read as mode 4 (a-a', but with the final on e). The concluding E-chord needs resolution through a return to A, not just because of Dowland's use of sharpward chord changes (at 'in those faire eies' and 'hir face was full of woe') which destabilize the A-focus of the song, but crucially because the cantus line ends on g' sharp, which is modally indefensible as a full close. Whether read modally or tonally, the piece is incomplete. Both in theory and in terms of the listener's experience of the song, 'I saw my Lady weepe' not only ends 'in the wrong place' relative to the final (or tonic), but that final has itself been disrupted: a need remains for its confirmation and firm re-establishment if the song is not to seem to some degree incomplete. When the first two songs are performed in sequence, 'Flow my teares' provides the essential resolution. The need for such resolution is intensified by Dowland's making similar play with metrical instability. The last phrase of 'I saw my Lady weepe' ('then mirth can doe, with hir intysing parts') disrupts the listener's grasp of both large and small scale rhythm by introducing syncopation across the semibreve beat, followed by two 'extra' notes requiring text repetition, all of which can be heard in relation to the underlying beat in conflicting ways. The whole phrase totals seven semibreve beats, following two regular phrases of six each. For both reasons further music is required in order to settle the metre; and 'Flow my teares' duly provides a comforting series of fo r-beat phrases to restore the listener's equilibrium. Similarly, the melodic ascent which closes 'I saw my Lady weepe', e' f g' a', pausing on the neighbour-note g' sharp as a pivot between the two songs, is answered at the start of 'Flow my teares' by the complementary descent a' g' f e', which is itself both anticipated in augmentation in the bass at the end of 'I saw my Lady weepe' (a relationship evident in the unusual duet form in which the first eight songs are published) and echoed immediately at the beginning of 'Flow my teares' in the lowest line of the lute (ex.1). The model for this symmetrical join was perhaps that between the second and third sections of 'Flow my teares'. There the melodic material is c b' a' g' sharp (pause) g' sharp a' b' c, the constituents of the second limb ('fall from your springs') of the opening phrase (ex.2). It is these two melodic gestures (designated 'a' and 'b' in the musical examples) that provide much of the material of both songs.