Music Library Research Articles

Eugène Bozza: A Thematic Index by Lois Kuyper-Rushing

Reviewed by: Eugène Bozza: A Thematic Index by Lois Kuyper-Rushing David Floyd Eugène Bozza: A Thematic Index. By Lois Kuyper-Rushing. (Music Library Association Index and Bibliography Series, vol. 42.) Middleton, WI: Music Library Association and A-R Editions, 2020. [xxxvi, 581 p. ISBN 9780895798879 (paperback), $150.] Indexes. Eugène Bozza: A Thematic Index by Lois Kuyper-Rushing is the first comprehensive thematic catalog of the music of Eugène Bozza (1904–1991). It offers both [End Page 91] a stepping-stone to future investigations of Bozza’s life and work and a reassessment of Bozza as much more than a composer of wind chamber music. The book, available exclusively in paperback, is a substantial volume in both its content and impact. Creating a detailed, accurate, and comprehensive thematic catalog for Bozza—a prolific composer who often reused melodies and rearranged works with new instrumentations, sometimes under new titles—is a lengthy, circuitous, and difficult task, and one which necessitates a dedicated scholar to carry it through to completion. The author, Lois Kuyper-Rushing, is singularly qualified for such an undertaking, considering her experience researching Bozza’s music. Two highlights of her previous work include a doctoral dissertation, “A Thematic Index of the Works for Woodwinds by Eugene Bozza (b. 1905)” (DMA diss., Louisiana State University, 1989), which was the first to comprehensively document this portion of the composer’s oeuvre, as well as an article detailing archival research in France that led to the discovery of several unpublished works (“Reassessing Eugène Bozza: Discoveries in the Bibliothèque Municipale de Valenciennes Archive,” Notes 69, no. 4 [June 2013]: 706–20). Overall, the index is a success. Its greatest strengths are the thoroughness of the indexing for unpublished and undated works, the novel inclusion of references to thematic similarities, and the biographical sketch of Bozza. The index, however, also has some issues. The impact of occasional typos in entries and minor errors in the notation of the incipits is relatively insignificant to the work as a whole. The more significant issues are the errors in cross-referencing between entries and the lack of a general index. Despite these oversights, its strengths as a contribution to the scholarship generally outweigh its weaknesses. Preceding the thematic index is a biographical sketch that offers both a well-rounded presentation of Bozza’s life and a look at the relationships between the events of his life and his compositional output. Bozza, primarily known in the United States for his woodwind chamber music, in fact composed for a wide variety of ensembles and genres throughout his career. His works include symphonies, vocal music, concertos, etudes, and an abundance of solo and chamber works for brass, strings, piano, percussion, and yes, woodwinds. Although most often remembered as a composer, he was also a violinist and conductor. From 1939 to 1948, Bozza served as the conductor of the Opéra-Comique in Paris. Having held a leadership role in the Opéra-Comique during the Nazi occupation, he faced intense scrutiny from the Parisian arts establishment after the war, and it is suggested in historical research that his termination in 1948 may have been a consequence of this. In 1950, he was appointed director of the École nationale de musique in Valenciennes, where he remained until his retirement in 1975. He continued to live in Valenciennes until his death in 1991. The preface to the index explains the structure of the catalog and the contents of a standard entry. The index lists 298 distinct pieces, 258 of which are “dated and/or published” and 40 of which are undated. They are organized chronologically and assigned “KR” (Kuyper-Rushing) numbers. KR 1 to KR 258 are the dated and/or published works, and KR 259 to KR 298 are the undated works. Each entry includes the title as it appears on the source, brief version descriptions where multiple versions exist, the instrumentation, the names or number of movements, the dates for composition and publication, the author of any lyrical or spoken text, dedications, and any general notes needed to add clarity. [End Page 92] The incipits provided for each entry are transcribed from manuscripts and...

Prediction Model of Music Popular Trend Based on NNS and DM Technology

The popular trend of today’s music can be obtained by deep excavation, analysis, and prediction of the audience’s preferences. Using huge music library resources and user behavior to form music big data and truly realizing the aggregation of audience preferences determine the popular development trend of music. Therefore, this paper will apply data mining (DM) technology, introduce neural network (NNS) theory, establish a prediction model of music fashion trend, predict and evaluate the music fashion trend according to the selected evaluation index, find the change of music fashion trend in time, and provide decision-making basis for music fashion trend. In this paper, the prediction of music popularity trend based on NNS and DM technology is studied. In the prediction of the number of songs played by 10 artists, the NNS algorithm proposed in this paper reduces the prediction effect from the original 0.074 and 0.045 to 0.044 and 0.032, respectively, and the error rates are reduced by 35.7% and 29.4%, respectively, compared with the learning algorithm and the decision tree algorithm. Among the three methods, the NNS algorithm in this paper has the highest accuracy. Therefore, it can be proved that the model proposed in this paper is more suitable for predicting the trend of music popularity. In the end, it can accurately control the trend of pop music and also realize the aggregation of user preferences to determine the trend of pop music.

From “Sound” to “Sound and Audiovisual”

IASA emerged in 1969 from IAML, the International Association of Music Libraries, Archives and Documentation Centres. The interests of IAML’s members largely focused on music as manuscript or score, and musical sound recordings were dealt with in the Record Library Committee. IASA was founded to consider additional types of sound recordings, including research and oral history. From the frst years of IASA’s existence, the question of the organisation’s relationship to the moving image arose, represented by the International Federation of Film Archives (FIAF). But as early as 1979, a delegate from the United States also brought video into play. With independence from IAML in the late 1980s, an intensive discussion began about the future of IASA and the expansion of the scope of the association to include audiovisual documents. Finally in 1999, the constitution and the name of the association were adapted. The transformation process triggered by this name change is still underway today. It could prove to be an advantage for IASA because it opens possibilities of adaptation to the rapidly changing world of audiovisual production due to digitisation and online media.

Wireless Play Music Beep Sensor to Assist in Music Fountain Control

Musical water landscape combines landscape design with audiovisual art and is loved by the general public. However, the performance control form of musical water landscape generally adopts the manual offline preprogramming method, which needs to use the human subject’s consciousness to perceive the style, emotion, and other advanced features of the music first and then choreographs the corresponding landscape performance, which is a high-cost design form and low usage rate of the landscape and is not conducive to the expansion of the music library. In this paper, we design and implement a musical water landscape simulation system using OpenGL and 3Dmax technology in combination with wireless music buzzer sensors, extract and analyze the music features based on this system, and study the system control of musical water landscape. Open GL particle system technology is used to realize the dynamic simulation of weather and fountain inside the landscape and improve the drawing scheme from both modeling and rendering aspects. For the fountain, the physical model and the wireless music beep sensor are combined to design a variety of water type actions for a single spout, and the parameter interface to control the water type changes is reserved. We propose a style recognition method based on CRNN and residual network, which has a higher accuracy rate compared with the existing methods; we use the DP algorithm to segment the pitch sequence of the music to reduce the redundancy of information and improve the calculation speed of the system.

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.

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.

Application of Big Data Mining Technology in the Digital Construction of Vocal Music Teaching Resource Library

In recent years, vocal music is becoming more and more important to daily life, which can cultivate emotion and adjust pressure, but at present, vocal music teaching is faced with an increasingly serious shortage of teacher resources. Therefore, it is particularly important to develop a vocal music teaching system using the computer-aided teaching function. First, the algorithm flow of the system is designed in detail according to the principle of computer neural network technology, the performance characteristics of vocal music are extracted by using Fourier transform and its improved function, and the key modules of the system are designed according to the system frame structure and data processing flow and gave the key design code. Finally, taking piano performance as an example, players with different steel bar grades were selected to test the accuracy of the system evaluation. The test results show that the system can reflect the real level of the performers, which is beneficial to vocal music teaching. The improvement of the vocal music teaching system is of great practical significance to adjust the traditional music teaching mode and make the education system more reasonable.

Musical Monticello: Classical Music and America

Thomas Jefferson’s Monticello plantation is here used as a case-study examiningclassical music’s foundations in the United States. Among other titles, Jefferson was a statesman, diplomat, slave master, and avid violinist. He is remembered as the principal author of the Declaration of Independence and third U.S. President. Early documentation suggests he was a gifted musician, reading notation at age nine and practicing “no less than three hours a day” for “a dozen years”. Music played an important role in the courtship of his wife, Martha Skelton Wayles, a harpsichordist and singer. They parented six children, of which two daughters survived to adulthood. Both received substantial keyboard training and their eldest inherited her father’s “taste and talent for music”. Upon their mother's death in 1782, Thomas began a complicated relationship with his late wife’s enslaved half sister, Sally Hemings. She became pregnant at sixteen and bore six of Jefferson’s children, four of which survived to adulthood. While Jefferson’s white daughters learned keyboard, two of his enslaved black sons were taught violin. It is likely that Jefferson himself taught them using the treatises of his expansive musical library, notably Geminani’s “Art of Playing the Violin”. A year after Jefferson’s death, the two sons were given their freedom; the youngest’s profession is listed as “musician” in the 1850 census; he is remembered as an “accomplished caller of dances”. These sons span the full stylistic gamut available in 19th century American music: from fiddle to violin. Thomas Jefferson and his family represent the kernels of America’s musical traditions, and the way they have morphed in parallel with America itself. The musical ecosystem of Monticello plantation is a dynamic location to discuss colonial music’s intersections with class, race, gender, and national identity.

Reflections of the Activities of the Vocal-Instrumental Chapel of the Carmelites of the Ancient Observance of Bialyničiai in Several Manuscript Sources of the Second Half of the Eighteenth–the First Half of the Nineteenth Century

So far, a separate musicological work on the musical activities in the church of the Carmelites of the Ancient Observance of Bialyničiai (Belarusian Бялы́ нічы, Polish Białynicze) has not been prepared. The lack of a sheet music library prompted the study into several manuscript sources from the second half of the eighteenth century to the first half of the nineteenth century, which are stored in manuscript libraries in Vilnius and Minsk. Using the book of registration of income and expenses of the Carmelites of the Ancient Observance of Bialyničiai, which was the primary source of information, a list of the members of the chapel of the Carmelite Order of Bialyničiai, who were paid in the second half of the eighteenth century, was compiled, with their names, surnames, time of service, and positions. The exact information on the size and the composition of the chapel that used to play in the church of the Carmelites of the Ancient Observance in Bialyničiai in 1824–1825 and in 1832, found in the inventory, the visitation, and the audit, is also provided. With the help of sheet music lists, attempts were made to determine the musical genres predominant in the chapel’s performances and the composers whose vocal-instrumental works were performed. The names of the composers are often distorted in the manuscript lists found, but it is possible to identify some of them or to make assumptions. The seventeenth-to-nineteenth-century heritage of the vocal-instrumental chapels of the Catholic monasteries of the Grand Duchy of Lithuania requires further research in order to produce a synthetic summary of this phenomenon.

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.

Resource Management and Optimization Method of Music Audio-Visual Archives under the Background of Big Data

With the development of music and video, music and video management has been in a relatively backward state. This study uses the logistic regression algorithm based on sigmoid functions to analyze and process the music audio-visual library of a music software and establishes the logistic regression dynamic model, which provides a scientific research method for this complex system. The LPC characteristic coefficient is extracted, and then the logistic regression model of music audio-visual archives resources is established. After completing the model, this study obtains the logistic regression model through a series of experiments, which effectively optimizes the management of music audio-visual archives. The specific experimental conclusions are as follows: through genre classification and emotion classification, users can search more music audio-visual archives resources. The comparison shows that the recommendation effect after filtering by the logistic regression model is better than that of the nonstandard collaborative filtering recommendation system. Finally, after practical applications, it is concluded that the model based on the logistic regression algorithm has made a good optimization conclusion for the resource management of music audio-visual archives.

A Deep Learning-Based Piano Music Notation Recognition Method.

In the era of rapid development of computer technology, piano music notation and electronic synthesis system can be established using computer technology, and the basic laws of music score can be analyzed from the perspective of image processing, which is of a great significance in promoting piano improvement and research and development, etc. In this paper, the Beaulieu analysis method is used to analyze the piano music notation and electronic synthesis system module. For piano sheet music, sheet music recognition is the main problem in the whole system. Through the digital recognition method, the piano sheet music feature matrix is extracted to get the piano sheet music multiplication frequency points and the envelope function needs to be extracted for better electronic synthesis of piano sheet music. The envelope function can represent the relationship between piano sound intensity and time change and finally achieve the recognition of the piano score. We extract the music information from the digital score, thus converting the music information into MIDI files, reconstructing the score, and providing an audio carrier for the score transmission. The experimental results show that the system has a correct rate of 94.4% in extracting music information from piano scores, which can meet the needs of practical applications and provide a new way for music digital libraries, music education, and music theory analysis.

Contributors’ Notes

Contributors’ Notes

"The Mother of Us All"

This paper presents extensive new biographical information, assembled from newspaper articles, about Ogreta McNeill, Canada’s first professional music librarian: pianist, singer, teacher, single mother, Toronto Public Library branch director, writer and bibliographer, impresario, founder and first chair of the Canadian Music Library Association. 
 The early accomplishments and influences of her formative years in Victoria BC offer were fully realized in her later identity as a generous contributor to the wider musical community.

Spotlight on Music Collections

CAML Review is published three times per year. It is concerned with music and music materials and strives to promote a better understanding of the cultural importance of music libraries, archives and documentation centres locally, regionally and nationally.

CAML Milestones

CAML Review is published three times per year. It is concerned with music and music materials and strives to promote a better understanding of the cultural importance of music libraries, archives and documentation centres locally, regionally and nationally.

Contemporary Musical Expressions in Canada – edited by Anna Hoefnagels, Judith Klassen and Sherry Johnson (Book)

CAML Review is published three times per year. It is concerned with music and music materials and strives to promote a better understanding of the cultural importance of music libraries, archives and documentation centres locally, regionally and nationally.

Editors' Column

CAML Review is published three times per year. It is concerned with music and music materials and strives to promote a better understanding of the cultural importance of music libraries, archives and documentation centres locally, regionally and nationally.

Music Research Data Management – by Amy S. Jackson and Sean Luyk (Book)

CAML Review is published three times per year. It is concerned with music and music materials and strives to promote a better understanding of the cultural importance of music libraries, archives and documentation centres locally, regionally and nationally.

Message from the President

CAML Review is published three times per year. It is concerned with music and music materials and strives to promote a better understanding of the cultural importance of music libraries, archives and documentation centres locally, regionally and nationally.