Digital Music Libraries Research Articles

Nkoda

nkoda is a robust digital sheet music library and sophisticated user interface for interacting with scores. The resource will be beneficial to students to professional artists, creating efficiencies in ensembles, studios, and personal practice. The vast content library sets nkoda apart from other digital score apps, as does the ability to engage an institutional license.

Construction and Sharing Mechanism of Digital Vocal Music Teaching Resource Library

Abstract With the rapid development of information technology, the construction and sharing mechanism of the teaching resource base has become an important means of informatization of vocal music education. The article proposes the construction and sharing of a personalized teaching resource system based on a collaborative filtering recommendation algorithm, constructs a personalized recommendation module through the study of collaborative filtering, and further improves the personalized recommendation algorithm. Then, it elaborates on the relevant contents of user interest modeling, records and manages the user's interest, describes the user's potential interest needs, records the user's behavior by building a model, and finally analyzes the application of the teaching resource library. When the boundary value of request concurrency does not exceed 1000, the response time of the teaching resource library page is no more than 2.5 seconds. When the teaching resource library is used to process a file of 100MB size, the upload speed of the WebSocket method is 153s faster than FancyUpload. More than 70% of the students think that the use of the teaching resource library in the vocal music class can greatly enhance the effect of vocal music learning.

Inheritance of Chinese Traditional Music Based on Markov Chain Modelling

Abstract In this paper, we first propose a Markov chain-based automatic composition method to construct a song set using classical and traditional music as a sample. Using probability matrices, experiments are conducted to generate pitch and time value sequences, and melodic segments of traditional music are generated using transformation techniques. Secondly, a traditional music digital resource library that integrates multiple functions is constructed by utilizing various information technologies. Finally, based on the existing classification dimensions, the relationship between various types of influencing factors in the inheritance of traditional music was analyzed, and the structure of the questionnaire was initially constructed. The results show that the correlation coefficients between the cultural inheritance of traditional music and its resources, environmental threats, development level, diversified values, public demand, and social cognition are 0.4235, 0.0953, 0.3594, 0.4253, 0.5348, and 0.5224, respectively, and there is a significant positive influence. This paper provides some theoretical and practical guidance for the protection and inheritance of traditional music.

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.

An Approach to Discover Similar Musical Patterns

An algorithm has been developed to find the similarity between given songs. The song pattern similarity has been determined by knowing the note structures and the fundamental frequencies of each note of the two songs, under consideration. The statistical concept namely Correlation of Coefficient is used in this work. Correlation of Coefficient is determined by applying 16 Note-Measure Method. If Correlation of Coefficient is near to 1, it indicates that the patterns of the two songs under consideration are similar. Otherwise, there exists a certain percentage of similarity only. This basic principle is used in a set of Indian Classical Music (ICM) based songs. The proposed algorithm can determine the similarity between songs, so that alternative songs in place of some well-known songs can be identified, in terms of the embedded raga patterns. A digital music library has been constructed as a part of this work. The library consists of different songs, their raga name, and their corresponding healing capabilities in terms of music therapy. The proposed work may find application in the area of music therapy. Music therapy is an area of research which is explored significantly in recent time. This work can also be exploited for developing intelligent multimedia tool that is applicable in healthcare domain. A multimedia based mobile app has been developed encapsulating the above mentioned idea that can recommend alternative or similar songs to the existing ICM based songs. This mobile app based music recommendation system may be used for different purposes including entertainment and healthcare. As a result of the applications of the proposed algorithm, similar songs in terms of raga patterns can be discovered from within the pool of a set of songs. A music recommendation system built on this algorithm can retrieve an alternative song from within the pool of songs as a replacement to a well-known song, which otherwise may be used for a particular music therapy. Results are reported and analyzed thoroughly. Future scope of the work is outlined.

IMusic: a session-sensitive clustered classical music recommender system using contextual representation learning

Music has emerged to be of paramount importance to humanity and is not only considered as a source of entertainment but also an agent that causes social and psychological influences. A large number of existing digital music libraries have improved awareness among people through the music recommendation approach. However, several critical technical challenges still require attention and must be well–addressed to provide a reliable recommendation to music listeners. In Indian Classical Music, Raga is composed of coalescing diverse musical note structures. The history of classical music unveils that every raga possesses some distinct sessions. With a vast collection of classical music files in online music libraries, locating and listening to classical music is no more a difficult task. However, searching and listening to the audio of one’s preference may not be simple as it must instinctively satisfy the listener’s preference in a precise session. In this paper, a system termed as iMusic has been proposed to classify, analyze, and recommend the session–sensitive performance of Indian classical music by analyzing the musical note structures followed by features matching. Available note-patterns in the raga performance have been illustrated using a deep neural network and a set of machine learning algorithms where raga samples have been represented as inputs in the projected network and are classified based on the performing sessions. A context-aware k-means clustering algorithm has also been illustrated, entitled as a data filtering algorithm. The proficiency of the filtering algorithm has been established in two ways. Primarily, as a data-sensitive analysis, and second as empirical studies on synthetically obtained real classical music dataset ( https://github.com/SamarjitRoy89/iMusic.git ) to put on the hybrid music recommendation. In this work, a case-study of session-sensitive Indian music recommender system has been demonstrated using key-strategies viz. listener modelling, representation learning, and music profiling. Eventually, several evaluation metrics have been discussed to characterize the effectiveness of proposed representation learning-based playing session-sensitive music recommendation strategies. The proposed iMusic system renders data classification accuracy of ~ 88%. Such a framework could provide a useful basis regarding studies on hybrid music recommendation systems based on the usefulness of end-users.

Cochleogram-based approach for detecting perceived emotions in music

Identifying perceived emotional content of music constitutes an important aspect of easy and efficient search, retrieval, and management of the media. One of the most promising use cases of music organization is an emotion-based playlist, where automatic music emotion recognition plays a significant role in providing emotion related information, which is otherwise, generally unavailable. Based on the importance of the auditory system in emotional recognition and processing, in this study, we propose a new cochleogram-based system for detecting the affective musical content. To effectively simulate the response of the human auditory periphery, the music audio signal is processed by a detailed biophysical cochlear model, thus obtaining an output that closely matches the characteristics of human hearing. In this proposed approach, based on the cochleogram images, which we construct directly from the response of the basilar membrane, a convolutional neural network (CNN) is used to extract the relevant music features. To validate the practical implications of the proposed approach with regard to its possible integration in different digital music libraries, an extensive study was conducted to evaluate the predictive performance of our approach in different aspects of music emotion recognition. The proposed approach was evaluated on publicly available 1000 songs database and the experimental results showed that it performed better in comparison with common musical features (such as tempo, mode, pitch, clarity, and perceptually motivated mel-frequency cepstral coefficients (MFCC)) as well as official ”MediaEval” challenge results on the same reference database. Our findings clearly show that the proposed approach can lead to better music emotion recognition performance and be used as part of a state-of-the-art music information retrieval system.

Extending the IFLA Library Reference Model for a Brazilian popular music digital library

Brazil is recognized as a musical country, with a diverse collection of musical resources served by many digital repositories and music libraries. Historically, those systems are supported by cataloging schemes that are insufficient because they follow standards more focused on the catalog record than on the structure of cataloged works. On the other hand, it is perceived the popularization of multi-entity bibliographic conceptual models, such as IFLA LRM, which seem to be an interesting solution because they (i) have a better capacity to represent the internal architecture of musical objects; (ii) support the creation of cataloging codes and international standards that enable interoperability between collections; and (iii) can be adapted through extension mechanisms. The purpose of this paper is to present an experiment of extending the IFLA LRM in the context of a Brazilian popular music digital library application in order to identify its power of expressivity for attending this specific domain. Instead of making direct use of the entities, attributes and relationships of IFLA LRM, the adopted method was to map concepts of a specific conceptual model (adherent to the digital library in question) that represents aspects of Brazilian popular music on IFLA LRM elements. The resulting extended model demonstrated to be aligned with users’ information needs and proved the efficiency of IFLA LRM to adapt to specific domains. In addition, the strategy of extending IFLA LRM from a specific model seemed appropriate for dealing with its level of generality.

Evaluating mobile music services in China: An exploration in user experience

Most digital music repositories and services have mobile applications (apps) that facilitate convenient access for users via smartphones. Although China has one of the largest music listener populations in the world, there is little research evaluating Chinese online or mobile music services. To bridge this gap, this study evaluated mobile apps of three of the most popular Chinese music services from the user’s perspective, using usability testing and semi-structured interviews with a sample of active users in China. Nielsen’s 10 user experience heuristics and four criteria in recommender evaluation were examined. Results identified criteria that create a positive user experience, and those that need further improvement. This study contributes to the literature in user-centred evaluation in music information retrieval (MIR) and music digital libraries (MDL), and provides practical insights for music application design, use and evaluation.

Digital Music Libraries: Librarian Perspectives and the Challenges Ahead

This paper reports the results of a survey targeting current members of the Canadian Association of Music Libraries, Archives and Documentation Centres (CAML) that investigated the extent to which the current designs and structures of digital music libraries meet the needs of librarians in collecting, preserving, organizing, and disseminating diverse types of music documents. The challenges and barriers experienced in hosting digital collections are discussed. The gap between the current and ideal functionalities, as well as the future possibilities, are explored.

Towards global music digital libraries

Purpose The purpose of this paper is to compare music mood perceptions of people with diverse cultural backgrounds when they interact with Chinese music. It also discusses how the results can inform the design of global music digital libraries (MDL). Design/methodology/approach An online survey was designed based on the Music Information Retrieval Evaluation eXchange (MIREX) five-cluster mood model, to solicit mood perceptions of listeners in Hong Kong and the USA on a diverse set of Chinese music. Statistical analysis was applied to compare responses from the two user groups, with consideration of different music types and characteristics of listeners. Listeners’ textual responses were also analyzed with content coding. Findings Listeners from the two cultural groups made different mood judgments on all but one type of Chinese music. Hong Kong listeners reached higher levels of agreement on mood judgments than their US counterparts. Gender, age and familiarity with the songs were related to listeners’ mood judgment to some extent. Practical implications The MIREX five-cluster model may not be sufficient for representing the mood of Chinese music. Refinements are suggested. MDL are recommended to differentiate tags given by users from different cultural groups, and to differentiate music types when classifying or recommending Chinese music by mood. Originality/value It is the first study on cross-cultural access to Chinese music in MDL. Methods and the refined mood model can be applied to cross-cultural access to other music types and information objects.

From Vernacular to Official—and the Spaces in Between

The shuffle function of my digital music library crafts an amusingly random soundtrack for casual household chores. As I swipe a dusty bookshelf, John Milton Hendricks’s voice pulls me into alert attention. On this track, which occurs on a four-year-old mix CD of the sort that sustains our long-term friendship, John narrates his walk to the Powerhouse to investigate a Mister Indulgence otter contest/fundraiser at this esteemed leather-and-more bar, possibly the first otter contest in the history of San Francisco. With a librarian’s training, an archivist’s instincts, and a dweller’s attention to thick description and detail, John shares the excitement of encountering the flier for the event, his characteristically brisk walking pace laboring his narration. A series of brusque edits shifts us from the street into the scene of the event and takes us across its entire span to the announcement of winner. Our intrepid reporter, himself an author of a chapter on the otter identity and its relation to the figure of the bear, probes with the important question of which came first—a celebration of the otter, or a fundraiser for the Marine Mammal Center? The two organizers and hosts of the event, Sister Anni Coque l’Doo (say it out loud, it goes without saying) and Sister Constance Craving (both members of the decades-old activist group Sisters of Perpetual Indulgence), get pulled into the proceedings. Imagining them bedecked in the frocks, habits, and garish face make-up characteristic of their order, I hear the Sisters describe one of their colleagues’ ongoing work with

Intimacy and Self-Abstraction: Radio as New Media in Aboriginal Australia

In the first decade of the twenty-first century, a number of Indigenous radio stations around Australia began to use digital programming and digital music libraries, at times pre-programming their broadcast signal days in advance through various forms of digital audio workstation (DAW). This shift initially caused both celebration and concern, and occasioned reflection by many producers on how radio ought to work and sound. For some producers the shift to digital pre-programming seemed a threat to the intimate address that Aboriginal radio entailed. On the other hand, some of these same producers began to re-imagine the audience to which such indigenous media might now aspire and to celebrate the sheer quantity of Aboriginal programming that a smaller number of producers could now produce. In challenging radio's naturalised ‘liveness’ for Aboriginal radio producers this oscillation suggests a distinct media ideology (Gershon 2010a), a sense of what radio media ought to accomplish, that draws together forms of intimate address and public abstraction. In my analysis I re-imagine John Durham Peters' heuristic dichotomy of dialogue and dissemination as a tension between intimacy and self-abstraction in order to suggest how radio as ‘new media’ continues to animate some longstanding dynamics of Aboriginal cultural production.

Classical Musicians & Copyright in the Digital Age: A Preliminary Investigation

[no abstract]

A Music Visual Interface via Emotion Detection Supervisor

For a particular emotion of the user, the System evaluates songs according to the qualification assessed by two factors which are: song’s relevancy to the user‘s preference, and song’s mental influence on the user’s feeling. In this proposed system, user’s emotion is not input manually by the user, but detected automatically by the machine. In order to do that, user’s facial expression data is captured from the webcam and then used as inputs for emotion detecting process. The motivation behind this system is the lack of a context-aware Music Recommendation System where automatically detected user’s mood plays the most important role as a contextual key. The need of such system is made obvious by the fact that digital music libraries are constantly expanding, which thus makes it remarkably difficult for listeners to recall a particular song matching their present mood.By training the system to recognize user’s emotional state by facial expression, it is made possible for listeners to generate a playlist which suits with their current emotion, and of which songs are rated also by the potentially mental influence on user‘s emotion. Keyword:Face recognition, Face detection, PCA, Emotion Extraction and detection, Euclidean Distance.

Introduction to the focused issue on music DLs

This focused issue on Music Digital Libraries of the International Journal of Digital Libraries aims at putting in tighter communication of related research areas that offer plenty of potential for combination andmutual inspiration, yet are only rarely combined froma research perspective:Music Information Retrieval (MIR) and Digital Libraries (DLs) technology. MIR is a research area that has a primary focus on content-based access and retrieval of music documents. Since the initial approaches based on the query-by-example paradigm, described also as query-by-hummingwhen themusical query was provided by the user directly by singing an excerpt of the melody, MIR research community enlarged its scope to include the recommendation (both of individual music documents and of sequences of songs organized in a playlist), genre classification, artist identification, and automatic tag generation and many other tasks. Other topics related to MIRaremore related tomusic processing, aimed at improved access to music content. To this end, research topics that are related to MIR include segmentation and structure analysis of music documents, both in symbolic and audio formats, track separation and transcription from audio, beat and tempo tracking, instrument identification.

Variations Digital Music Library System and Variations Audio Timeliner (review)

For information regarding the scope of this column, consult the headnote in the September 2011 issue. The dates of access for each review of an online source indicate the dates during which the reviewer was evaluating the resource. All Web sites were last accessed to verify availability on 1 February 2012. Variations Digital Music Library System and Variations Audio Timeliner. [Bloomington, IN]: Indiana University, 2005-. http://www.dlib.indiana.edu/projects/variations3/index.html (Accessed December 2011). [Requires a Web browser, Adobe Flash Player, and an Internet connection. Full Variations system requires installation of Linux operating system, MySQL 5 database, Java, Darwin streaming server, DjVuLibre, Apache Web server, and Tomcat Web application server. Variations Audio Timeliner requires a Pentium II 500MHz processes, 256MB RAM (512MB preferred), 2GB hard drive or better, 16-bit audio, 1024x768 resolution, and QuickTime 7.0 or higher. Required operating systems include Windows 2000, XP, or Vista for Windows or Mac OS X for Macintosh. Pricing: free.] First launched by Indiana University in the mid-1990s, Variations is a digital asset management system uniquely designed to handle music materials. The software became available to other institutions as an open source release in 2009. While there are other systems on the market that institutions have adapted to manage musicrelated assets (such as DSpace (1) and CONTENTdm (2)), none of these focus specifically on music and none handle music materials as effectively as Variations. Iii its most current incarnation, Variations offers back-end tools for digitizing audio and print materials as well as front-end interfaces for accessing streamed audio and digital scores. Since Indiana's open source release, many institutions are using Variations as a reserves system, though it has potential for much broader applications. The system could be used for delivering institutional musical performances, rare/special collection recordings, or non-music recordings such as speeches. readings, and broadcasts. In addition to providing mechanisms for digitizing and delivery, Variations also offers tools specifically designed to enrich the user experience. Such tools include customizable bookmarks, playlists, annotation options, and quizzing functions. Variations is available both as a browserbased interface and as a standalone Java application (see figures 1 and 2). Presently the Web version works only with audio (riot scores)! The stand-alone version is available for the latest Mac or Windows operating systems (Mac OS X, Windows Vista, and Windows 7) and requires QuickTime software to function. (4) Details for downloading Variations will vary by institution, as will the way in which users launch and use the system. Users who wish to explore either the standalone version or browser-based interface with sample tracks may visit the Variations Web site for more information. (5) The particular process used at Baylor University) is discussed laler in this review. [FIGURE 1 OMITTED] AUDIO PLAYER In addition to the standard playback/ control functions one would expect (volume control, play/pause.and navigation). the audio player allows users to create playlists. These playlisis are exportable as either HTML, files or native Variations files (V2P). Either Format results in a small file (approximately 4KB). Opening a playlist file or HTML document launches Variations and loads the playlist. The audio player also has a bookmarking feature that allows users to mark locations within it recording for later use. While the default name for the bookmark is taken from the track listing. users can rename and rearrange bookmarks and can also add comments to each bookmark. From the edit screen, users can manage bookmarks by organizing them into folders. sending bookmarks to a playlist, or exporting them as HTML. or Variations (V2B) files. SCORE VIEWER The Variations score viewer allows navigation of the entire score through a scrub bar. …

A spatial hypertext-based, personal digital library for capturing and organizing musical moments

We describe the design, development, and evaluation of a personal digital music library application designed to assist musicians in capturing, developing, and managing their musical ideas over time. The target user group is musicians who primarily use audio and text for composition and arrangement, rather than with formal music notation. The software design was guided by a formative user study which suggested five requirements for the software to support: capturing, overdubbing, developing, archiving, and organizing. This led to a spatial hypermedia approach forming the basis for the developed application. Furthermore, the underlying spatial data-model was exploited to give raw audio compositions a hierarchical structure, and—to aid musicians in retrieving previous ideas—a search facility was provided to support both query by humming and text-based queries. A user evaluation of the implemented environment indicated that the target musicians would find the hypermedia environment useful for capturing and managing their moments of musical creativity. More specifically, they would make use of the query by humming facility and the hierarchical track organization, but not the overdubbing facility as implemented.

MyTunes: Digital music library users and their self-images

This investigation explored the relationships between individuals’ self-images and their interactions with their digital music collections via the commercially predominant program iTunes. Sixty-nine university students completed an internet-based Musical Self-Images Questionnaire (MSIQ) along with a series of questions concerning their iTunes collections. The majority of participants were highly engaged with music, regardless of their varied musical backgrounds. Factor analysis of the MSIQ data revealed two distinct self-image groups, which we label as ‘musical practitioner’ (linking ‘overall musician’, ‘performer’, ‘composer’, ‘teacher’, and ‘listener’) and ‘music consumer’ (linking ‘listener’, ‘fan’, and ‘technology user’). Participants used an average of seven attributes to categorize their music, and most consistently used one in particular to sort their collections. Those who rated themselves as higher level performers and fans used the playlist function (which involves compiling sequences of selected tracks) more often than those with lower self-ratings on those scales.

An Efficient Identification Methodology for Improved Access to Music Heritage Collections

A comprehensive methodology for automatic music identification is presented. The main application of the proposed approach is to provide tools to enrich and validate the descriptors of recordings digitized by a sound archive institution. Experimentation has been carried out on three different datasets, including a collection of digitized vinyl discs, although the methodology is not linked to a particular recording carrier. Automatic identification allows a music digital library to retrieve metadata about music works even if the information was incomplete or missing at the time of the acquisition. Automatic segmentation of digitized material is obtained as a byproduct of identification, allowing the music digital library to grant access to individual tracks, even if discs are digitized using a single file for a complete disc side. Results show that the approach is both efficient and effective.