=Paper=
{{Paper
|id=Vol-3806/S_58_Fuks_Tsurkan_Zhebka_Novikov
|storemode=property
|title=
Application for Working with Musical Notes Using Artificial Intelligence
|pdfUrl=https://ceur-ws.org/Vol-3806/S_58_Fuks_Tsurkan_Zhebka_Novikov.pdf
|volume=Vol-3806
|authors=Viktoriia Fuks,Anastasiia Tsurkan,Viktoriia Zhebka,Yuriy Novikov
|dblpUrl=https://dblp.org/rec/conf/ukrprog/FuksTZN24
}}
==
Application for Working with Musical Notes Using Artificial Intelligence
==
https://ceur-ws.org/Vol-3806/S_58_Fuks_Tsurkan_Zhebka_Novikov.pdf
Application for Working with Musical Notes Using Artificial
Intelligence
Viktoriia Fuks1, Anastasiia Tsurkan1, Viktoriia Zhebka 2 and Yuriy Novikov3
1
National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, 37, Prospect
Beresteiskyi, Kyiv, 03056, Ukraine
2
State University of Information and Communication Technologies, 7, str. Solomyanska, Kyiv, 03110, Ukraine
3
Institute of Software Systems of the National Academy of Sciences of Ukraine, Akademik Hlushkov Avenue,
40, building 5, Kyiv, Ukraine, 03187
Abstract
In the work, existing software solutions and successful IT projects were analyzed and their advantages
and disadvantages were identified, which helped determine the requirements for a product that would
be competitive and meet the requirements of the modern market. Modeling and designing of the
software were carried out, the client-server architecture of the application was described, as well as the
interaction of subsystems. The mobile application was developed and tested, and further directions for
improvement and development of the application were determined. The ap-plication processes a PDF
file with a given metronome speed in mp3 and mp4, which gives the user the opportunity to see and
listen to the sheet music. The project includes an Android application with a clear and convenient
interface, integration with external utilities and libraries. In the work, the processing of files from pdf
format to such music and playback files as midi, musicxml, mp3, mp4 is collected in one stream. The
process of parsing and playing with full-cycle processing of music files has been improved, by providing
the user with all software modules, and the process of processing visual notes and bringing them to
easy-to-use files, such as videos that combine notes with sound, has been improved. The work is
important because it contributes to the development of digital music processing methods. The
introduction of modern technologies for note recognition and visualization of musical elements
contributes to techno-logical progress in the field of music development.
Keywords 1
mobile application, sheet music processing, interpretation, score, metronome, client-server
architecture, computer musicology; music recommendation system; music therapy
1. Introduction
In today's high-tech world, where artificial intelligence is defining new horizons of possibility, the
music industry is not only adapting to these changes, but actively using them to achieve higher
standards of creativity and efficiency. In this context, the development of a universal tool aimed
at working with musical notes represents an important step in the automation of tasks related to
the creation and mastering of music.
The relevance of this work is determined by the urgent need to adapt the music industry to
modern requirements through the use of advanced technologies. The use of artificial intelligence
in musical creativity opens up new opportunities for artists and audiences, making the creative
process more accessible and exciting.
14th International Scientific and Practical Conference from Programming UkrPROG’2024, May 14-15, 2024, Kyiv,
Ukraine
*
Corresponding author.
†
These authors contributed equally.
fuksvik@gmail.com (V. Fuks); nastianegrienko@gmail.com (A. Tsurkan); viktoria.zhebka@ukr.net (V. Zhebka);
ynovikov@gmail.com (Y. Novikov)
0009-0007-2721-2424 (V. Fuks); 0009-0002-6725-4198 (A. Tsurkan); 0000-0003-4051-1190 (V. Zhebka); 0009-
0006-9800-8765 (Y. Novikov)
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
At the current stage of technology development, it is already possible to observe significant
achievements in the use of artificial intelligence in the musical field [1-2]. Algorithms for
analyzing musical structures, creating new compositions, and automating sound recording
processes are important stages in the evolution of this field.
The current state of affairs is that there are not many resources with a full cycle of processing
music files, so there is a need for a universal and convenient resource that would provide the user
with all the software modules necessary for analyzing works and playing.
The new universal tool for working with musical notes can become not only an innovative
solution for artists, but also a crucial element for analyzing, organizing and creating music. Its
capabilities find application in various aspects of creativity, providing automation of key basic
processes and space for creative disclosure of musicians. The mobile application is a step towards
musicians, music teachers, composers; it is a help both for those who are just starting their career
in the music world, and for those who have conquered the stage more than once with their
playing. This development, by processing sheet music, enables a person to play a musical
instrument without being distracted by extraneous tasks that this musical assistant will do for
him.
The proposed work can find application in the field of music therapy. Music therapy is an area
of research that has been greatly explored recently. This work can also be used to develop an
intelligent multimedia tool that can be applied in the field of health care. As part of this work, a
digital music library can be created. Developed a multimedia-based mobile application that can
play music by sheet music. This application, which should be expanded with a music
recommendation system based on a mobile application, can be used for various purposes,
including education, entertainment and healthcare.
2. Artificial intelligence in music
Humanity has always counted on artificial intelligence to facilitate many aspects of our lives,
including managing systems, solving complex mathematical problems, programming, and
diagnostics. However, few could have imagined that AI could show creative abilities, becoming a
poet, artist, writer or musician. Such a turn in the development of technology emphasizes that the
boundaries between what was considered exclusively human are constantly being erased, and
artificial intelligence turns out to be not only a tool in our hands, but also a real creator, capable
of surprising with its creative achievements.
Today, the music industry is willing to experiment with the use of AI in their creative
processes.
Many people who are interested in music, even those who are considered to be experienced
musicians, can face difficulties in learning new pieces of music, enriching their musical experience
or finding creative inspiration. In particular, the constant distraction of flipping notes, the
difficulty in recognizing them, the use of separate applications for a metronome or listening to
compositions, and the need for a convenient place to store creative efforts become factors that
require an elegant and functional solution. In an effort to simplify and facilitate the musical
process, there is a need for a universal application that combines all these aspects.
Let's consider in more detail the main advantages of such an application:
• Note recognition and learning: The application includes functionality for note recognition,
which will make learning new pieces of music much easier. It can provide visual and audio
processing for correct performance of notes and chords.
• Metronome and tempo: The built-in metronome and the ability to adjust the tempo will
allow musicians to keep a stable rhythm while performing works. This is especially
important for training and practice.
• Storage and organization of works: The application can store recordings and creative
works of a musician in an organized format. This allows you to quickly find and replay
previous versions or variations of works.
• Organization of the creative process: The application can include functions for creating
lists of compositions, tracking activity and progress. This will make it easier to organize
and motivate the musician.
• Playback and listening: The built-in ability to play audio files will allow you to listen to
variations of works, which will facilitate experiments and creative development.
• Intuitive and accessible design: A clear and intuitive design that makes it easier for users
to navigate and use the various features of the application.
• Personalization of the interface: The possibility of personalizing the interface according
to the individual preferences of the user, such as choosing a theme, setting the activity, etc.
• Graphic indicators and animations: Use of graphic indicators, instructions for visual
display of application status.
3. Application of the mobile application in music therapy
The music recommendation system plays an important role in music therapy. A music
recommendation system recommends music for users based on various factors such as human
mood, human behavior, choice, similarity, fundamental frequencies, time intervals, etc. Figure 1
depicts the general connection between the music recommendation system and music therapy
[3].
Figure 1: General relationship between music recommendation system and music therapy.
Music has the ability to heal some diseases of the human body [4]. Therefore, they say that
music has therapeutic properties [5]. Music therapy is an area of the paramedical field in which
music is used for a variety of therapeutic purposes. Music therapy can be used to treat even
psychological and physiological problems such as mesothelioma, peritoneal mesothelioma,
asthma, asbestos cancer, depression, etc. [5-6].
In turn, such a mobile application can be used in the field of electronic healthcare. The
developed application can act as an electronic health care system for certain purposes based on
music therapy.
Music and emotions are directly related to each other and this has already been established.
In [7], a model of a music recommendation system based on a specific culture was proposed.
Article [8] describes a research project that aims to develop a music analysis system that
represents the analysis of clinical music therapy. Music is a very effective way of mental healing,
and the management of a person's psyche can be controlled through music therapy
Article [9] is a link to a website that illustrates the different raga names and their respective
healing powers. The work described in [10] presents a music recommendation technique based
on the analysis of content and context information. The work described in [11] presents a context-
sensitive mobile music recommendation system.
The work described in [12] is a modeling technique and a useful tool that formalizes the rules
of music composition; the technique increases the speed of music analysis using musical Petri
nets that introduce Schoenberg's rules. The work presented in [13] is a method of generating a
list of songs for listening; songs can be downloaded according to the age factor of online users. It
is a web application that recommends different songs based on the listener's choice and also
based on their age group. Songs are downloaded from the music library and unknown songs are
classified based on user feedback.
The work presented in [14] presents a model of musical creativity rather than algorithmic
musical variations using genetic algorithms. The implementation of this model is based on the
Genome software. A statistical approach was used to find similar song patterns using the
coefficient of variance [15]. Using neural networks, a time-based recommendation system was
developed in [16]. [17] describes a music recommendation system that classifies different songs
suitable for different times of the day. An intelligent mechanism for automatic identification of
the density of a certain musical rhythm and the complexity of this musical rhythm was proposed
in [18]. Various areas of music research and their applications are illustrated in [19]. A reference
to the chi-square table is given in [20].
The music recommendation system was studied in [19]. The robot provides a personalized
music recommendation service using polyphonic musical objects using the MIDI (Musical
Instrument Digital Interface) format. User analyzes profiles to group users based on user
behavior and interests. They use the pitch density to select the track that contains the melody,
which can be calculated as:
𝑁𝑃 (1)
𝑃𝑖𝑡𝑐ℎ 𝐷𝑒𝑛𝑠𝑖𝑡𝑦 = ,
𝐴𝑃
where NP – the number of different tones in the track, AP – the number of all different tones in
the MIDI standard.
The pitch entropy (PE) can be obtained as follows:
𝑁𝑃 (2)
𝑃𝐸 = − ∑ (𝑃𝑗 𝑙𝑜𝑔𝑃𝑗 ),
𝑗=1
where 𝑃𝑗 presented as follows:
𝑁𝑗 (3)
𝑃𝑗 = ,
𝑇
where Nj – the total number of notes with the corresponding pitch in the representative track, T
– the total number of notes in the representative track.
A music group containing widely accessible music objects has a higher weight than other
groups. The weight of a musical group (GWi) can be calculated as:
𝑛
(4)
𝐺𝑊𝑖 = − ∑ 𝑇𝑊𝑗 × 𝑀𝑂𝑗,𝑖 ,
𝑗=1
where TWj – the weight of the transaction Tj, n - the number of the last transactions used to analyze
MOj, i – the number of music objects that belong to the music group Gi in the transaction Tj.
Different numbers (Ri) of musical objects from musical groups are calculated (also
recommended) according to GWi as follows [11]:
𝐺𝑊𝑖 (5)
𝑅𝑖 = ⌈𝑁 × 𝑚 ⌉.
∑𝑘=1 𝐺𝑊𝑘
There are quite a lot of research works that encourage us to work further and even discover
new dimensions of musicological research. Computational musicology is the fastest growing field
and depends on various concepts of computer science.
4. Analysis of known algorithmic and technical solutions
Modern requirements for software for processing musical notes require developers to carefully study
existing algorithms, their adaptation for use in specific conditions. This section will analyze advanced
algorithms and technical solutions that ensure a high level of accuracy and productivity in working with
musical data. Let's consider the key aspects that shape the technical landscape in this industry.
MIDI (Musical Instrument Digital Interface):
1. Used to encode musical information, such as sheet music, into a technical format.
2. Allows you to store and transfer information about notes, their dynamics, tempo, etc.
3. Widely used in music programs and applications.
MusicXML:
Defines a standard for exchanging musical information in text format.
Allows you to save and transfer data about notes, chords, tempo, but in text form.
Provides a clear structure for analyzing and processing notes.
Optical Music Recognition (OMR):
Used to recognize notes and other symbols on paper sheet music using an image.
Requires the use of computer vision to analyze the sheet music image.
It is used in situations where it is necessary to recognize notes from physical sheet music.
Operational Note Recognition (OCR):
Uses optical recognition algorithms to convert sheet music images into text with notes.
Requires accurate imaging for effective operation.
Algorithms are used to recognize frequencies and time parameters of sound.
Can take into account the dynamics and characteristics of various musical instruments.
FFT (Fast Fourier Transform):
It is used to analyze the frequencies in the audio signal and determine the main notes.
Helps in converting the audio signal from the sheet music file into frequency characteristics.
Wavelet Transform:
Used to analyze amplitudes and frequencies at different levels of deployment.
Provides detailed audio signal analysis results.
These algorithmic and technical decisions are important for the development of a mobile
application for note recognition and interpretation, as they determine the efficiency, accuracy and
functionality of such an application. The combination of these methods can provide a high-quality
and versatile tool for musicians and creative individuals.
This project focuses on the implementation of optical musical note recognition (OMR),
software for editing and playing music, image rendering based on music files, and technologies
for sound synthesis and video creation based on audio tracks and images. Key tools covered
include Audiveris for OMR, MuseScore as a tool for editing MusicXML files, and SoundFont for
sound synthesis.
Audiveris is defined as an advanced OMR tool capable of converting scanned sheet music into
digital formats. This is especially useful for musicians, composers and music archivists who work
with large volumes of paper sheet music.
MuseScore is an intuitive and powerful sheet music editing tool used by musicians, composers
and arrangers around the world. This software makes it easy to make changes and visualize
musical works, making it ideal for detailed work on musical compositions after their initial
recognition, for example with Audiveris. In this development, MuseScore was used to make
changes to the MusicXML format file.
SoundFont is a key tool in the field of digital audio, as it provides diverse and high-quality
sounds for music synthesis. It is a technology that allows musicians and producers to use an
extensive set of sound libraries that simulate various musical instruments, from traditional to
electronic. In this development, SoundFont is used to sound the notes, which were originally
submitted by the user in PDF format.
Each of these instruments plays a key role in various stages of the development of a musical
project. Taking into account the specifics of the project, Audiveris was used for initial note
recognition, MuseScore for further music editing, and SoundFont for final sound synthesis. This
combination provides an efficient workflow from sheet music scanning to music playback.
5. Software requirements
Development of reliable software systems requires effective activities for implementing of
software development lifecycle processes. One of the activities, which helps to raise an
effectiveness of software development lifecycle processes (requirement analysis, software
designing, development and testing), is reusing of software development artifacts [21-22].
Technologies of voice assistants or assistants are actively used in modern solutions. They are
implemented on the basis of software that can perform tasks or provide services based on given
voice commands by processing and interpreting human speech [23-24]. The main function of the
software is to process musical notes for further playback in response to a given metronome
speed. More features can be viewed in Figure 2.
Figure 2: Use case diagram.
The process of developing functional requirements is a key stage in the creation of software
focused on the implementation of specific functions and tasks. In this section, we will take a
detailed look at the necessary functions and properties that our mobile application for processing
musical notes should have.
Based on the analysis of the subject area, a list of requirements was determined:
Note recognition:
a. Ability to recognize sheet music from PDF files.
b. Recognition accuracy at a high level.
Metronome:
c. Integrated metronome with the ability to adjust the tempo and rhythms.
Storage and Organization of Creative Works:
d. Ability to create and store music notes, as well as listen to them.
e. Cataloging and easy searching by name, description, etc.
i. Sorting your own library of works.
ii. Customization of saved files.
Interactive User Interface:
f. Convenient and intuitive interface for users of different experience levels.
g. Ability to personalize settings and appearance.
Innovative Functions:
h. Additional features to enhance the creative process and provide unique
functionality.
Free feature list:
i. Availability for all users, providing all features for free.
This list of requirements forms the basis for the development of a software system that not
only meets the needs and expectations of users in this subject area, but also offers a
comprehensive and advanced tool for improving and developing musical skills.
Let's consider the non-functional requirements for the application. The implementation must
satisfy the following theses:
• The application should be easy to use and have a pleasant design;
• The application must be adapted to different mobile devices;
• The application should be adapted for different latest versions. The software should be
adaptable to easily add new functionality;
• The interface should be simple, intuitive for the user;
• The interface must support ways of behaving in case of internal service failures or user
errors;
• The interface should display the library in a convenient format (divided into
subcategories).
• Through a detailed study of the research area, a list of requirements was determined,
which is an important component in the development of a software system. The analysis
of these requirements is a key stage in the formation of the characteristics and scope of
the future product. This list of requirements covers both the functional and non-functional
aspects necessary to successfully implement business objectives and respond to user
needs. The analysis carried out at this stage lays a solid foundation for further steps in the
design and development of the software system.
6. Software modeling and analysis
The UML Sequence Diagram shown in Figure 3 is used to define and further describe the
software business process.
Figure 3: UML Sequence Diagram.
Description of the sequence of the basic communication flow of the server and the mobile
application:
• The application sends a request with the file and metronome speed for processing
• The server checks the correctness of the input data
• The server (Flask) processes the file according to the set speed
• The server sends a confirmation that the file was processed successfully
• The mobile application sends a request to receive data
• Server (Flask) checks data availability
• Data is sent to the mobile application
• The application unpacks the archive with files
• The application displays ready-made files on the user's screen.
This system is an example of a client-server architecture where the server is implemented
using the Flask web framework and hosted on localhost. To provide access to the server from the
outside, Ngrok is used, a service that allows you to tunnel external requests to a local web server.
The mobile application acts as a client interacting with the server through HTTP requests.
Let's consider the components of the developed system.
Mobile Application (Client):
• Sends requests to the server.
• Uses the API provided by the Flask server to send and receive data.
Flask Server (localhost):
• Accepts and processes HTTP requests from the client.
Server Processor:
• The main component that handles server logic.
• Processes PDF files sent by the mobile application.
Ngrok:
• Tunnels requests from the Internet to the Flask server on localhost.
• Provides the public URL that the mobile application uses to access the server.
The architecture is visually depicted in Figure 4.
Figure 4: Application architecture.
Interaction between Components
Client-server interaction:
• The mobile application initiates HTTP requests to the server via the URL provided by
Ngrok.
• The Flask server takes the request, processes the data, and sends the response back to the
client.
Using Ngrok:
• Ngrok creates a secure tunnel from the public domain to localhost.
• Allows a mobile application to interact with a server that is physically located locally.
This architecture allows for flexible and efficient interaction between a mobile application and
a server located locally. Using Ngrok facilitates access to a local server without the need to deploy
it to an external environment. Flask as a lightweight web framework provides flexibility and ease
of development of server-side logic.
Next, we will provide a detailed description of utilities, libraries and other third-party software
used in the development of this client-server system. Using these tools, you can efficiently convert
musical notes from PDF to various digital formats, process music data, and generate audio files.
The main utilities covered in this section include Audiveris, MuseScore, and SoundFont.
Audiveris is a high quality Optical Music Recognition (OMR) that converts scanned sheets of
music into MusicXML format. It is a software that can automatically recognize, analyze and
convert musical notes from PDF files.
PDF to MusicXML conversion: Audiveris efficiently converts scanned sheet music or PDF files
to MusicXML format, a standard for music data exchange.
Accuracy and Reliability: The program has a high accuracy of recognition of musical symbols,
which ensures high-quality conversion of notes.
Automation: Audiveris is able to automate many steps of the conversion, minimizing the need
for manual intervention.
CLI: Audiveris provides convenient commands for use via the command line or in
subprocesses of another application
MuseScore is one of the most popular notation programs that allows you to work with
MusicXML files. It is used in this system for further processing of MusicXML files received from
Audiveris.
Let's consider the key features of MuseScore:
Editing MusicXML: MuseScore allows you to conveniently edit and export MusicXML files.
CLI: provides the ability to access the program through subprocesses with commands
SoundFont is a technology used to play MIDI files. It contains recordings of real instrument
sounds that can be used to generate audio files from MIDI.
Let's consider the main aspects of SoundFont.
Sound Quality: SoundFont provides high-quality sound that is close to real instruments.
Use with MIDI: Ideal for converting MIDI files into realistic audio files.
Compatibility: Compatible with many audio processing programs.
These utilities and technologies play a key role in the process of converting, processing and
playing music on the system. They allow you to efficiently process music data, convert it between
different formats and create high-quality audiovisual materials.
Figure 5 shows a diagram of the components of this developed server.
Figure 5: Diagram of components.
The component diagram shows the architecture of the server, which includes the Flask web
server and the my_funcs module, as well as interactions with external components such as the
file system, SoundFont, Audiveris, and MuseScore. Each of these components plays a role in the
overall system architecture.
Since the server uses a file system to store files, we need to be clear. Which files the program
has access to and which files it sends to the client. This control involves the creation of a unique
code based on a timestamp, which is updated and assigned to each new PDF file submitted for
processing. A directory is created for all files for a specific case, files are stored under this unique
number.
7. Directions for further research
At this stage, there are many areas of development of the proposed application. There are plans
to expand the application in the direction of a larger number of file formats, additional auxiliary
functions (tool calibration, etc.), adding a community and the ability to share developments.
Regarding the software itself, it is primarily an acceleration of operations, improvement of
visualization and the way of interaction with the server. Also, an important aspect is the further
improvement of music processing algorithms to increase accuracy and efficiency.
The direction of further research may be the development of an approach for determining
musical patterns and recommending songs for music therapy.
Develop a music recommendation system that takes into account the general connection
between the music recommendation system and music therapy. The music recommendation
system plays an important role in music therapy. A music recommendation system recommends
music for users based on various factors such as human mood, human behavior, choice, similarity,
fundamental frequencies, time intervals, etc.
8. Conclusions
As a result of this work, the mobile application "Liszt" musical assistant for note recognition
and musical interaction was developed. The application processes a PDF file with a given
metronome speed in mp3 and mp4, which allows the user to see and listen to the musical
notation. The project includes Android applications with a clear and convenient interface,
integration with external utilities and libraries. Research results can contribute to the
development of technologies for working with music data on mobile devices. This may include
improving note recognition algorithms, improving the accuracy of music playback, and other
technical aspects.
The state of solving the tasks. All defined tasks in the work were successfully completed.
After implementation, the application was tested on a mobile device and in test programs that
were used to interact with the server.
Evaluation of the obtained results. The obtained results prove the competitiveness of the
application, compliance with the specified requirements and the level of compliance with
technical knowledge in the field of software development. The system successfully operates with
data and skillfully visualizes them.
Scientific and socio-economic significance. The work is important because it contributes to
the development of digital music processing techniques. It also has socio-economic significance,
simplifying processes that traditionally require considerable effort and time, and opening
opportunities for wider access to musical culture. Ensuring accessibility for all interested
persons, regardless of the level of musical training.
Using the application can become part of music education in educational institutions and
additional courses. This tool can be used to improve the process of learning music and provides
opportunities for creative expression. The introduction of modern technologies for note
recognition and visualization of musical elements contributes to technological progress in the
field of music development. Creates a positive music learning experience that can support and
maintain users' interest in the world of music for a long time.
Using a mobile application can facilitate the process of creating music, arranging, learning new
compositions, and also facilitate quick access to sheet music and other musical resources.
References
[1] Artificial intelligence and musicians: helper or competitor? URL:
https://www.neformat.com.ua/ articles /shtuchniy-intelekt.html
[2] How AI is Changing the Music Industry. URL: https://www.rollingstone.com/music/music-
features/how-ai-is-changing-the-music-industry-204120/
[3] AI in Music: How Artificial Intelligence is Changing the Way We Create and Listen to Music
URL: https://syncedreview.com/ 2021/07/22/ai-in-music-how-artificial-intelligence-is-
changing-the-way-we-create-and-listen-to-music/
[4] S. Chakrabarty, R. Islam, E. Pricop and H. K. D. Sarma, "An Approach to Discover Similar
Musical Patterns," in IEEE Access, vol. 10, (2022) 47322-47339. URL: doi: 10.1109/
ACCESS.2022.3169362.
[5] J. Vasudha, G. Iyshwarya, A. T. Selvi, S. Iniya and G. Jeyakumar, "Application of computer-
aided music composition in music therapy", Int. J. Innov. Manage. Technol., vol. 2, no. 1,
(2011) 55-57.
[6] G. K. Koduri and B. Indurkhya, "A behavioral study of emotions in south Indian classical music
and its implications in music recommendation systems", Proc. ACM Workshop Social Adapt.
Personalized Multimedia Interact. Access (SAPMIA’10), (2010) 55-60.
[7] J. Erkkila, O. Lartillot, G. Luck, K. Rikkila and P. Toiviainen, "Intelligent music systems in music
therapy", Music Therapy Today, vol. 5 (2004) 1-21.
[8] S. Bashetti, N. Kundoor, K. V. Desai, K. N. Radha and A. V. Bhongir, "Indian music therapy:
Could it be helpful in the management of mental", Int. J. Med. Res. Health Sci., vol. 3, no. 2,
(2014) 354-357.
[9] J.-H. Su, H.-H. Yeh, P. S. Yu and V. S. Tseng, "Music recommendation using content and context
information mining", IEEE Intell. Syst., vol. 25, no. 1, (2010) 16-26.
[10] X. Wang, D. Rosenblum and Y. Wang, "Context-aware mobile music recommendation for daily
activities", Proc. 20th ACM Int. Conf. Multimedia (MM) (2012) 99-108.
[11] B. Adriano, M. A. Davide, H. Goffredo and L. L. Andrea, "Formalizing Schoenberg’s
fundamentals of musical composition through Petri nets", Proc. 15th Sound Music Comput.
Conf. (SMC) (2018) 254-258.
[12] S. Chakrabarty, M. R. Islam and H. K. Debsharma, "An approach towards the modeling of
pattern similarity in music using statistical measures", Proc. 5th Int. Conf. Parallel Distrib.
Grid Comput. (PDGC) (2018) 436-441, 2018.
[13] A. Vsevolod and A. Alexey, "Genetic algorithms for music variation on genom platform", Proc.
9th Int. Conf. Theory Appl. Soft Comput. Words Perception (ICSCCW) (2017) 24-25.
[14] S. Chakrabarty, M. R. Islam and D. De, "Modelling of song pattern similarity using coefficient
of variance", Int. J. Comput. Sci. Inf. Secur., vol. 15, no. 1 (2017) 388-394.
[15] R. Samarjit, C. Sudipta and D. Debashis, "Time-based raga recommendation and information
retrieval of musical patterns in Indian classical music using neural networks", IAES Int. J.
Artif. Intell., vol. 6, no. 1 (2017) 33-48.
[16] C. Sudipta, R. Samarjit, D. Debashis, S. Bhattacharyya, H. Bhaumik, S. De, et al., Handbook of
Research on Intelligent Analysis of Multimedia information (Hardcover), Hershey, PA, USA:
IGI Global, 2016.
[17] S. Chakrabarty, G. Karmakar, M. R. Islam and D. De, "Reckoning of music rhythm density and
complexity through mathematical measures" in Advanced Computational and
Communication Paradigms, Singapore: Springer, vol. 475(2017) 387-394.
[18] S. Chakrabarty, S. Roy and D. De, "A foremost survey on state-of-the-art computational music
research", Proc. Int. Sci. Congr. Assoc (2015) 16-25.
[19] H.-C. Chen and L. P. A. Chen, "A music recommendation system based on music and user
grouping", J. Intell. Inf. Syst., vol. 24 (2005) 2-3.
[20] Table: Chi-Square Probabilities, URL: https://people.richland.edu/james/lecture /m170/
tbl-chi.html.
[21] O. Chebanyuk, Investigation of Drawbacks of the Software Development Artifacts Reuse
Approaches based on Semantic Analysis / Lecture Notes on Data Engineering and
Communications Technologies, 2023, 181, 514–523
[22] O. Chebanyuk, Software Reuse Approach Based on Review and Analysis of Reuse Risks from
Projects Uploaded to GitHub / Lecture Notes of the Institute for Computer Sciences, Social-
Informatics and Telecommunications Engineering, LNICST., 514 LNICST (2023) 144–155
[23] S. Kulibaba, S. Popereshnyak, Y. Shcheblanin, O. Kurchenko, N. Mazur, Advanced
Communication Model with the Voice Control and the Increased Security Level / CEUR
Workshop Proceedings, 3288 (2022) 64–72.
[24] S. Popereshnyak, V. Zhebka, A. Vecherkovskaya, Methodology for Countering Malicious
Information on Social Networks / CEUR Workshop Proceedings, 3688 (2024) 108–121