Musical Sources Research Articles

Music source feature extraction based on improved attention mechanism and phase feature

Music source feature extraction is an important research direction in music information retrieval and music recommendation system. To extract the features of music sources more effectively, the study introduces the jump attention mechanism and combines it with the convolutional attention module. Also, a feature extraction module based on Unet + + and spatial attention module is proposed. In addition, the phase feature information of the mixed music signals is utilized to improve the network performance. Results showed that this model was studied to perform well in music source separation experiments of vocals and accompaniment. For vocal separation on the MIR-1K dataset, the model achieves 11.25 dB, 17.34 dB, and 13.83 dB for each metric, respectively. Meanwhile, for drum separation on the DSD100 dataset, the model achieves a median signal-to-source distortion ratio of 4.36 dB, which is 2.91 dB better than that of the Spectral Hierarchical Network model. For the separation of the bass sound and the human voice, the model's in the separation of bass and human voice, the median distortion ratio of the model is as high as 4.87 dB and 6.09 dB, which is better than that of the Spectral Hierarchical Network model. This indicates the significant performance advantages in feature extraction and separation of music sources, and it has important application values in music production and speech recognition.

Lully’s music in northern Europe: evidence of early circulation in Swedish libraries

Abstract At Jean-Baptiste Lully’s death in 1687, music from his stage works was already circulating within and outside France, and was used and praised by ‘all connoisseurs’ in Europe (according to Dutch music publisher Amédée Le Chevalier). This was at a point when many of Lully’s works were still not printed and the Parisian music dealers had not yet started their business with his music. Surviving manuscript sources from the dissemination of Lully’s music before his death are few and fragmentary and have sometimes survived at a geographical distance from Paris. This article investigates a handful of previously unconsidered music sources, copied or printed in France in the 1670s and early 1680s, which were acquired by various members of northern aristocratic families and have survived in Swedish libraries. Viewed as a whole, these seemingly disparate sources can throw light on the details of the early circulation of Lully’s music, as well as on musical practices of the elites in late 17th-century Europe.

Jazz Trio Database: Automated Annotation of Jazz Piano Trio Recordings Processed Using Audio Source Separation

Recent advances in automatic music transcription have facilitated the creation of large databases of symbolic transcriptions of improvised music forms including jazz, where traditional notated scores are not normally available. In conjunction with music source separation models that enable audio to be “demixed” into separate signals for multiple instrument classes, these algorithms can also be applied to generate annotations for every musician in a performance. This can enable the analysis of interesting performer-level and ensemble-level features that have often been difficult to explore. To this end, we introduce Jazz Trio Database (JTD), a dataset of 44.5 h of jazz piano solos accompanied by bass and drums, with automatically generated annotations for each performer. These annotations consist of onset, beat, and downbeat timestamps, alongside MIDI for the piano soloist. Suitable recordings, broadly representative of the “straight-ahead” jazz style, were identified by scraping user-based listening and discographic data; source separation models were applied to isolate audio for each performer in the trio; annotations were generated by applying appropriate algorithms to both the separated and the mixed audio sources. Onset annotations generated by the pipeline achieved a mean F-measure of 0.94 when compared with ground truth annotations. We conduct several analyses of JTD, including with relation to swing and inter-performer synchronization. We anticipate that JTD will be useful in a variety of music information–retrieval tasks, including artist identification and expressive performance modeling. We have made JTD, including the annotations and associated source code, available at https://github.com/HuwCheston/Jazz-Trio-Database

Music in a vanished kingdom: medieval polyphony in the Teutonic Order state in Prussia

Abstract The state of the Teutonic Order in Prussia, or Ordensstaat (1228–1525), belongs to those ‘vanished kingdoms’ which—devoid of any contemporary heirs—remain on the margins of historical narratives about music. The aim of this article is to describe polyphonic practices in medieval Prussia on the basis of archival and musical sources. Although the information they contain is of a fragmentary character, referring mainly to the first half of the 15th century, it does indicate that a variety of music was cultivated: from simply polyphony in chant notation to international Ars Nova. Outside the major ecclesiastic centres, conditions for the cultivation of polyphony could have existed at the court of the Grand Master, at which musicians—mostly instrumentalists—from across Europe appeared. Particular attention is devoted in the article to fragments from the Gdańsk Library of the Polish Academy of Sciences (Ms. 2153a) which contain works in the style of Central European polyphony, belonging to the genres of motet, cantio and rotulum. These and other sources indicate that the culture of medieval Prussia should be seen from the perspective of various European connections, and not as Germanic or Polish culture, as has often occurred in the past.

Music source separation via hybrid waveform and spectrogram based generative adversarial network

Music source separation via hybrid waveform and spectrogram based generative adversarial network

The Gates of Sky by Ede Terényi: Music Analysis

In our previous paper, we examined the genesis of the choral work, its textual and musical sources, the intellectual and cultural influences that may have played a role in its creation. Starting from this complex ideological background, in this paper we will examine, through a detailed analysis of the score, how the composition’s structure, musical language and techniques bring the text to life, where its message is directed, and what additional conceptual and expressive value they provide. The Gates of Sky is, in a certain reading, a cultural-anthropological journey, partly based on historical references, partly mythical. However, its rich musical language and symbolic meanings only gain significance if they are combined with a suitable and convincing sound dramaturgy. For the author’s basic aim is not merely to evoke a ritual, but to give the performers and the audience the opportunity to experience the metamorphosis it embodies. Keywords: Ede Terényi, Ernő Lendvai, The Gates of Sky, choir music, ritual, world tree

More on the scoring of Josquin’s Huc me sydereo and the manuscript St Gallen 464

Abstract The motet Huc me sydereo by Josquin des Prez appears in both five- and six-voice versions, having led scholars to debate which version is authentic to the composer’s original conception. The authoritative New Josquin Edition presents the motet in its six-voice version; in the critical commentary, editor Bonnie Blackburn defended it as Josquin’s original. More recently, Joshua Rifkin has demonstrated on stylistic and source-critical grounds that the five-voice version was original, with a sixth voice having been added later. In this article, I present new findings on the manuscript St Gallen 464, an important early source for Huc me sydereo, which reinforce arguments defending the authenticity of the five-voice version. I show that the origin of the sixth voice can be isolated to a trio of sources produced on the Italian peninsula in the 1510s, all but eliminating Josquin as a candidate as its author. Moreover, through a new identification of the original scribe and owner of St Gallen 464, I shed new light on that manuscript’s date and provenance. In so doing, I demonstrate how the study of musical sources and transmission can carry direct importance for essential performance decisions.

The whole is greater than the sum of its parts: improving music source separation by bridging networks

This paper presents the crossing scheme (X-scheme) for improving the performance of deep neural network (DNN)-based music source separation (MSS) with almost no increasing calculation cost. It consists of three components: (i) multi-domain loss (MDL), (ii) bridging operation, which couples the individual instrument networks, and (iii) combination loss (CL). MDL enables the taking advantage of the frequency- and time-domain representations of audio signals. We modify the target network, i.e., the network architecture of the original DNN-based MSS, by adding bridging paths for each output instrument to share their information. MDL is then applied to the combinations of the output sources as well as each independent source; hence, we called it CL. MDL and CL can easily be applied to many DNN-based separation methods as they are merely loss functions that are only used during training and do not affect the inference step. Bridging operation does not increase the number of learnable parameters in the network. Experimental results showed that the validity of Open-Unmix (UMX), densely connected dilated DenseNet (D3Net) and convolutional time-domain audio separation network (Conv-TasNet) extended with our X-scheme, respectively called X-UMX, X-D3Net and X-Conv-TasNet, by comparing them with their original versions. We also verified the effectiveness of X-scheme in a large-scale data regime, showing its generality with respect to data size. X-UMX Large (X-UMXL), which was trained on large-scale internal data and used in our experiments, is newly available at https://github.com/asteroid-team/asteroid/tree/master/egs/musdb18/X-UMX.

The ARMID@Venezia Project: Multispectral Imaging and Spectroscopic Investigations on Ancient Music Sources: Paper and Parchment Manuscripts and Printed Books

The ARMID@Venezia Project: Multispectral Imaging and Spectroscopic Investigations on Ancient Music Sources: Paper and Parchment Manuscripts and Printed Books

Application of Unet-SE-Bisru Algorithm for Music Signal Processing in Music Source Separation

At present, the use of time-domain deep learning for end-to-end neural network models has the problem of long training time and poor performance in music source separation. To address this issue, a U-network squeezing excitation bidirectional simple recursive unit model was proposed based on the deep extractor model. Replace Unet SE Bisru with Unet SE Bisru in the following text. This model improves the bidirectional long short-term memory network into a bidirectional simple recurrent unit, and then introduces attention mechanisms in the generalized encoding and decoding layers. The squeezing excitation block is used to selectively extract features based on the type of audio to be separated. Finally, group normalization is added after onedimensional convolution, And its effectiveness was verified. The experimental results show that the signal noise distortion ratio in the improved model is 5.68 decibels compared to the bidirectional simple recursive unit value, which is higher than the 5.55 decibels of bidirectional long short-term memory. After adding the squeezing excitation module, the overall increase is about 0.1-0.5 decibels. In addition, in the model comparison, the three indicators of the improved model with the same number of channels were 5.68 decibels, 5.91 decibels, and 11.28 decibels, respectively, higher than the benchmark model. Compared with other music source classification models, the improved model has better comprehensive separation performance. Although some indicators are lower than the comparison model, the signal noise distortion ratio of drum and bass is 6.11 decibels and 6.36 decibels, which is better than the comparison model. Overall, the improved model has high performance in music source separation for music signal processing and can be effectively applied in practical music source separation.

MELODY IN MEDICINE: CAN MUSIC ELEVATE EACH STAGE OF SURGERY?

Listening to music during surgery is a widespread phe-nomenon in healthcare institutions globally. Music can have both positive and negative impacts on the stressful and challenging surgical process. Scientific studies by Kahloul et al. (2017), Zybartaite and Gedrime (2021), and Ahmad (2017) confirm that music is an effective and eco-nomical tool to reduce stress. According to Boghadady and Kvist (2020), playing classical music at a moderate volume can enhance the speed and accuracy of surgical tasks. However, it’s important to acknowledge that music may hinder communication and concentration (Naraya-nan & Gray 2018; Weldon et al. 2015; Shambo, Umad-hay & Pedoto 2015), and contribute to time inefficiencies arising from the selection of music types (Sarla 2022). This qualitative study, conducted through semi-structu­red interviews, aimed to analyze how music influences te-amwork during the perioperative stages. The study an­tici-pates contributing to patient safety, work efficiency, team satisfaction, and cost reduction in the healthcare system Results and conclusions: All participants had a positive view of listening to music during surgery, with prefe-rences varying across perioperative stages. Anest­hesio-logists and operating room nurses often choose the type of music, while sometimes no specific team member is assigned to this role. Steady rhythm genres don’t dis-rupt communication and can alleviate emotional tension. High-rhythm genres may increase tension and fatigue, disrupting concentration. Fast-paced genres can improve mood, and different genres don’t necessarily affect surgi-cal duration. Slow-tempo genres may reduce emotional fatigue. High music volume can impair communication and concentration. An ideal music source in operating theaters should be compact, easily disinfected, and sim-ple to control.

An In-depth Review on Music Source Separation

The study in Music Source Separation (MSS) raises a fundamental question: Is there any benefit in considering broader contextual information, or are local acoustic features adequate? In various domains, attention-based Transformers [1] have demonstrated their capacity to assimilate information across extensive sequences. In our research, we introduce Hybrid Transformer Demucs (HT Demucs), a hybrid temporal/spectral bi-U-Net based on Hybrid Demucs [2]. Here, the innermost layers are substituted with a cross-domain Transformer Encoder, utilizing self-attention within one domain and cross-attention across domains. Although its performance is lacking when exclusively trained on MUSDB [3], we illustrate that it surpasses Hybrid Demucs (trained on the same data) by 0.45 dB of Signal-to-Distortion Ratio (SDR) when provided with an additional 800 training songs. By employing sparse attention kernels to broaden its receptive field and undertaking per-source fine-tuning, we attain state-of-the-art results on MUSDB with extra training data, achieving a remarkable 9.20 dB of SDR.

The applications of dynamic time warping in the source separation of percussive sounds

Music source separation (MSS) is the process of splitting various components of a musical piece into individual tracks. This process combines the fields of acoustics and machine learning to extract useful data from music, which assists in a variety of music information retrieval tasks. In the past decade, many methods have been employed to perform MSS with varying levels of success. This research explores the use of dynamic time warping (DTW) for MSS tasks in the time domain. DTW is an algorithm that performs a temporal alignment of two time series to measure their similarity. It is unique in that the algorithm will minimize the Euclidean distance between the two sequences by stretching or compressing them to optimize similarity. This makes DTW a distinctive method for MSS, as it operates entirely in the time domain and classifies sounds without the interference of time warping. The research performed focuses only on the separation of transient, percussive sounds. Measurements taken with a drum kit and a selection of digital drum sounds served as the foundation for tests of the algorithm. The results of this research illustrate the potential of DTW in time domain MSS applications.

Development of the 2nd Cadenza challenge for improving music listening for people with a hearing loss

The Cadenza project is an ongoing project that aims to improve music quality for those with a hearing loss. The project is running signal-processing and machine-learning challenges to address different listening issues and scenarios. During the first round, the challenge focused on non-causal music source separation to allow remixing for those with hearing loss. This fed into an ICASSP 2024 challenge, which had crosstalk from loudspeaker reproduction included. There are three potential arms to our upcoming 2024 challenge based on reported issues from hearing-impaired music listeners: (1) low-latency causal audio source separation, (2) lyric intelligibility enhancement without loss of timbre or instrumental balance, and (3) loudness/dynamic range control. Each of these potential challenges raise questions as to the appropriate reference signals, as well as the practicalities of deriving the appropriate signals for an open-source machine-learning challenge. [Work supported by UK EPSRC Grant No. EP/W019434/1]

Virtual acoustics in distributed performance over a closed audio network

We explore an application of active acoustics used to produce a shared virtual environment for live musical performance. As part of a concert given in the Immersive Media Lab at McGill University, musicians and audience members were located in adjacent but acoustically isolated spaces on the same digital audio network. With computer generated effects and live instruments, the concert consisted of electroacoustic performances that utilized dynamic virtual environments produced by our Virtual Acoustic Technology (VAT) system as an improvisatory partner and a mixing device to blend the diffusion of electronic and acoustic musical sources. The performance, including its evolving virtual environment, was captured using spatial microphone techniques and distributed in real-time to the audience over an immersive loudspeaker system in an adjacent control room. Audience members were given the opportunity to visit the musicians’ performance space in order to compare the reproduction to the original environment. Overall, the blending of computer-generated and acoustic sources created a specific use case for virtual acoustics, while the immersive capture and distribution method examined an avenue for producing a real-time shared experience. Future work in this area includes audio networks with multiple virtual acoustic environments and distributions.

The continuity of the vocal and performing heritage of the multi-genre song culture of the Kuban Cossacks

The object of the study is the continuous preservation of the multi-genre Cossack folk song, which represents a key purpose in the implementation of the preservation of the traditional mentality at the present stage. The subject of this work is the immanent complexes of traditional song culture in the folklore heritage. The purpose of this study is to structure the issue of the cultural interrelation of the ethnic canvas of the Kuban Cossack folk songs, in the originality of the genesis of the vocal and performing specifics of modern creativity. When discovering the fundamental foundations of the vocal performance of the Cossack song, special attention is paid to the study of the folklore primary sources of the Kuban folklorists, V.G.Zakharchenko, A.D.Bigdai, G.M.Kontsevich. Along with this, an expert assessment of the characteristics of the Kuban Cossack folk song according to the genre classification component is an important feature of the performance of vocal samples today. The theoretical basis is in an analytical approach to the peculiarities of the performance of a local source from the point of view of substantiating the scientific nature of the subject under consideration according to the functionally oriented elements of the report: traditions, traditional manner of performance, interpretation of the text, song melody. Methodological basis: components of the study of the local singing tradition, modernization of folklore song documents, the method of consistency-the genre diversity of Cossack performance. The author's approach to the correlation of musical sources as methodological characteristics of the Kuban Cossack singing traditions has been developed. We test the proposed system when working with archival documents, in the diagnosis of song samples recorded from informants. The key aspect is the musicological analysis of the musical collections of Kuban Cossack folk songs from the point of view of the continuously developing, multifaceted changing performing skills of the soloist and choir. The author takes into account the introduced model of performing Cossack songs since the resettlement of the Black Sea Cossacks, who brought the baggage of multi-genre sources and eventually introduced the Kuban folk singing art. The scientific novelty of the research lies in the author's analytical systematization of authentic song compositions recorded by folklorists, in the analysis of multi-genre Kuban Cossack sources (selectively) for further active performance on stage. The specific directions of performance according to characteristic song genres are determined: historical, military, everyday, marching, lyrical, wedding, ceremonial, round dance, comic. The reproduced orientation of the nature of the continuous preservation of folklore sources in the revised performance interpretation of Cossack vocal works gives rise to significant broadcasting opportunities today.

Vocal Ornamentation in Caccini: From Theory to Practice

The main purpose of the published article is to study the role and determine the possibility of using jewelry in Giulio Caccini vocal music. The composer, the creator of the “new” style, the first among his contemporaries in the preface to the collections of arias and madrigals Le nuove musiche (1602) and Nuove musiche e nuova maniera di scriverle (1614) outlined the main positions of the school of artistic singing, where he reports on the recording of his compositions how to perform. This often leads performers into confusion about the possibility of using any jewelry. As a result, today, in some cases, Caccini music sounds monotonous, uninteresting. In the Baroque era, there was a clear discrepancy between practice and musical notation. An in-depth study and comparison of musical sources, their historical understanding, evaluation based on documentary and theoretical evidence allows us to identify the real practice and features of reproducing jewelry offered by Caccini for performance. As a result, the author of the article emphasizes the need to rethink the approach to performance, in particular, concerning the application of various ornamental effects. In this regard, it becomes important to observe their main purpose: to enhance the affect and mood of the composition through expressive transmission of the word.

Research on the Integration Teaching Mode of Traditional Music Elements and College Piano under the Background of Information Technology

Abstract With the deep integration of information technology and music education, how to integrate traditional music to innovate college piano teaching mode has become a problem that must be solved for the development of the times. Based on the scaffolding teaching method, this paper integrates traditional music elements with college piano in-depth and realizes the innovation of college piano integration teaching mode by adopting online pre-study before class, offline teaching during class and timely reflection and evaluation after class. In the teaching process, traditional music signals are represented by time-frequency domain features so as to realize the digital pre-processing of traditional music signals, and traditional music fundamental tone contours are transformed by using the fundamental tone feature extraction method. Then, based on the principles of physics, we explored the string vibration equation of the piano-generating principle and constructed a mathematical model for the piano music signal. To verify the effectiveness of this paper’s method in piano teaching in colleges and universities, relevant algorithms and teaching practices are used. The results show that the GNSDR of this paper’s method on vocals is improved by 6.58% compared with Unet, and its SDR is 4.25dB and 5.21dB when separating the two music source signals of Piano and Vocals, which is improved by 0.36dB and 0.14dB compared with SHN-4, respectively. The college piano scaffolding teaching model that integrates traditional music elements has enhanced sight-reading ability by 116.44%. Under the background of information technology, it is necessary to fully combine the relevant technology to extract the characteristics of traditional music elements so as to help teachers better carry out the design of piano music teaching programs and improve the quality of colleges and universities to cultivate piano talents who inherit traditional music.

Music-oriented auditory attention detection from electroencephalogram

Music-oriented auditory attention detection (AAD) aims at determining which instrument in polyphonic music a listener is paying attention to by analyzing the listener’s electroencephalogram (EEG). However, the existing linear models cannot effectively mimic the nonlinearity of the human brain, resulting in limited performance. Thus, a nonlinear music-oriented AAD model is proposed in this paper. Firstly, an auditory feature and a musical feature are fused to represent musical sources precisely and comprehensively. Secondly, the EEG is enhanced if music stimuli are presented in stereo. Thirdly, a neural network architecture is constructed to capture nonlinear and dynamic interactions between the EEG and auditory stimuli. Finally, the musical source most similar to the EEG in the common embedding space is identified as the attended one. Experimental results demonstrate that the proposed model outperforms all baseline models. On 1-s decision windows, it reaches accuracies of 92.6% and 81.7% under mono duo and trio stimuli, respectively. Additionally, it can be easily extended to speech-oriented AAD. This work can open up new possibilities for studies on both brain neural activity decoding and music information retrieval.

Genre-Stylistic and Performance Features of O. Shchetynskyi’s Works for Wind Instruments

The purpose of the proposed article is to determine the genre-stylistic and performance features of the works for wind instruments by Oleksandr Shchetynskyi. The research methodology is based on the use of the following methods: textual, source and hermeneutical – in the study of musicological and sheet music sources on the chosen topic; analytical – to determine the genre-stylistic and performance features of the analysed compositions; the method of personalisation (scientific biography) – to outline the composer’s contribution to the works for wind instruments; interviews – during direct communication with the author. The scientific novelty of the work lies in the generalisation of significant factual material concerning the work of O. Shchetynskyi and the updating of notographic material analysed for the first time. Conclusions. The compositions for wind instruments and O. Shchetynskyi’s work in general reflect the leading trends in the development of Ukrainian music of the late 20th and early 21st centuries in the context of postmodernism and post-avant-garde as the two most traditionally established concepts for understanding modern artistic processes. On the basis of the analytical characteristics of individual works with the participation of wind instrument by O. Shchetynskyi, their immanent features were determined, such as the use of modern composition techniques (free atonality, dodecaphony, quarter-tones, seriality, and multiseries), which expand the range of performance and expressive possibilities of these instruments (use of heterogeneous glissando and vibrato, raised and lowered quarter tones, multiphonic sounds, specific articulation techniques), a special attitude to sound as a self-sufficient value, which is manifested in a thourough sound elaboration of any idea and the most delicate attitude to rhythm, timbre, dynamics, and articulation. Key words: works for wind instruments, O. Shchetynskyi, Ukrainian music.