Music Data Research Articles

A study on music therapy aimed at psychological trauma recovery for bereaved families driven by artificial intelligence.

This study explores the effectiveness of music therapy in repairing psychological trauma in bereaved families, aiming to provide a comprehensive understanding of its potential therapeutic impact. It begins with an analysis of the current situation faced by bereaved families, identifying the psychological challenges they experience. The research design included the recruitment of participants from bereaved families, who were then divided into an experimental group and a control group. An optimized Long Short-Term Memory (LSTM) network model was constructed to analyze music therapy data, tailored specifically to capture the nuances of this therapeutic process. The experimental procedure detailed the specific operations involved in the music therapy sessions and established a clear comparison framework between the two groups. The performance of the proposed LSTM model demonstrated high accuracy (0.85), precision (0.86), recall (0.84), and F 1-score (0.85), indicating its effectiveness in predicting treatment outcomes. When compared to the Self-Reporting Inventory-90 (SCL-90) scale, the model captured the trend of treatment effects with a high level of accuracy and reliability. Notably, participants numbered 2, 6, and 8 in the experimental group showed substantial improvement rates of 67.21%, 71.45%, and 75.67%, respectively, in their psychological health issues. The comparative analysis between the experimental and control groups confirmed that the music therapy approach, as guided by the proposed LSTM model, led to a more significant improvement in psychological health issues for bereaved families. This suggests that the model offers a promising avenue for enhancing the effectiveness of music therapy in this context.

Design and Implementation of Gesture Music Composition System based on RealSense and Recurrent Neural Network

Aiming at the problems of slow human-computer interaction and low accuracy of hand gesture recognition (HGR) in music composition systems such as human-computer interaction, gesture recognition, and algorithmic composition, this paper designs an HGR music composition system based on real-sense technology and recurrent neural network. The system uses an Intel RealSense 3D camera to shoot the user's hand and extract the information on the hand joint points with Smart Wearable Biosensors (SWBSs). The joint points are used to construct a three-dimensional model of the hand bone, and the joint points' equivalent distance and joint deflection are calculated by the joint point information to match the corresponding Curwen HGR. The matching music data is input into the recurrent neural network. GRU is combined with the Markov chain algorithm to complete the composition and avoid the phenomenon of gradient disappearance or gradient explosion. The HGR recognition function and composition algorithm are simulated and tested to verify the method's feasibility. Cohort verification investigations and efficacy evaluations of wearable biosensors are essential to support their clinical acceptability. The research results show that the HGR music composition system based on real-sense technology and recurrent neural networks can effectively identify the tester's HGRs and assist the tester in completing the composition using intelligent biosensors. The composition mode is close to the professional composition process.

Research on Multi-Modal Music Score Alignment Model for Online Music Education

As music data storage becomes increasingly diverse in the era of big data, ensuring alignment of music works with the same semantics for online music education is crucial. To achieve this, a multi-modal music score alignment algorithm model based on deep learning was developed and optimized. Experimental results demonstrated that Note + DCO feature combination yielded the best MIDI input characteristics (mean value: 13.27 ms), whereas CQT feature comparison produced the best results for audio input (average: 12.85 ms). The ResNet-34 network was noted to have the most effective music score alignment effect with alignment errors averaging less than one frame. Compared with other algorithms, the proposed algorithm had the lowest average value of 9.28 ms, median value of 5.85 ms, and standard deviation of 20.17 ms. Actual music retrieval showed a Top-1 retrieval accuracy of 10.93% that was close to 11%. Overall, the proposed algorithm is significant for score alignment and music retrieval recognition in online music education.

Measuring emotions to classify songs: The impact of the COVID-19 pandemic on music streaming data

Data from music streaming has gained increasing attention since it allowsstudying music preferences across diverse cultures and different periods of time.Indeed, the study of “music and emotion” is crucial for understanding the psychologicalrelationship between human sentiments and music. The temporal studyof musical emotions provides beneficial insights into the analysis of the mood oflisteners during periods of particular relevance and stress (e.g., the COVID-19pandemic). This study performs music streaming data analysis to retrieve themusical emotions of the top Italian streamed songs during the pandemic. To thisend, we propose two new indices for measuring anger and joy in songs. We suggesta procedure for clustering music streaming data: the DISTATIS procedureand Partitioning Around Medoids (PAM) clustering algorithm are sequentiallyapplied to identify intervals of time sharing similar sentiments. Finally, we employthe proposed procedure to investigate the relationship between the evolutionof the pandemic spread and sentiments extracted from songs. The results show that music streaming data analysis allow identifying fiveclusters of time intervals sharing similar sentiments,

An Attempt to Generate Mozart's Piano Compositions Based on an LSTM Model

LSTM, proposed by German computer scientists Sepp Hochreiter and Jürgen Schmidhuber in 1997 [3], has shown outstanding performance in various tasks, especially in tasks that require capturing long-term dependencies. These tasks include language modeling and machine translation in the field of natural language processing, as well as stock price prediction. This project aims to explore the potential of LSTM models in the field of music generation by analyzing Mozart's classical piano works using music21 and creating a training dataset. The project uses LSTM to learn this dataset, adjusting the forget gate, input gate, and different training iteration times to generate diversified outputs. Finally, the generated music data was manually selected and labeled.

The Mediating Effect of Artificial Intelligence on the Relationship Between Cultural Heritage Preservation and Opera Music: A Case Study of Shanxi Opera

Cultural heritage preservation, as the approach is known, and the enduring role it plays in safeguarding the culture and cultural values of Shanxi Opera is becoming even more important these days. Despite uncertainty and apprehension about utilising artificial intelligence, this matter is worth scrutiny in relation to the field of opera music. This may be so, as apart from these two occurrences, this field does not receive mention. This research aims to explore the effect of AI as a conduit for message emulation between the Shanxi Opera tradition and the preservation of heritage and the opera music genre. The study employed a combination of qualitative and quantitative research methods, which used the survey data and cultural heritage preservation and opera music experts' perception data. I then employed partial least squares structural equation modelling (PLS-SEM) to interpret existing AI utilisation and to understand the role of AI as a mediator in this scenario. The outcome of the study implies that the existence of AI will not only boost the contribution of cultural heritage conservation but also positively impact the early stages of the contemporary revival of Shanxi Opera music. AI not only helps in heritage preservation but also makes it easier to include modern audiences. It introduces new musical trends and styles that are more engaging with the current audience. This paper lays out certain practical applications of artificial intelligence AI as a key to appreciating the human cultural heritage. It is the AI-driven contribution to opera music superiority that stands as the hallmark of technology. The outcomes showcase a one-of-a-kind perspective that indicates the ability of policymakers, cultural heritage preservers, and opera commuters to bridge the gap between traditional and modern technologies through AI. Research has stressed the essence of enlisting AI as a typical tool today to preserve cultural heritage. This, in turn, largely contributes to the development of dramatic genres such as opera. It serves as a rather remarkable point of interface between the cutting-edge realms of technology and cultural legacy, illustrating how AI can virtually reshape the artistic world.

Guest Editorial: What Engineers Should Know About the Expanding Generative AI Toolkit

Generative artificial intelligence (AI) is the art of creating new things inspired by the old. To understand what generative AI does, ask yourself what you would do if you wanted to create a new hit song. You wouldn't want to start from scratch. Instead, you'd listen to 100 popular songs, analyze the rhythms, melodies, and chord progressions. You would learn how these elements are structured and combined. Then, with this knowledge you would use your creativity to mix and match them in new and exciting ways—resulting in a fresh, original song that may be the next big hit. That's essentially what generative AI does. It devours massive amounts of training data, whether it's music, images, text, or scientific data. It learns the underlying patterns and relationships within that data. Then, it uses this knowledge to generate entirely new content that shares characteristics with the training data, but with a unique twist. Generative AI operates like a master mimic, following a three-step process to create entirely new content. 1. Find the building blocks. As mentioned, generative AI begins by analyzing vast amounts of training data. The goal is to identify the underlying building blocks and structures that define the data. For example, different rooms in a house contain different objects—kitchens have different items than bedrooms. Think of it like understanding the grammar of a language or the architectural styles that make up different cityscapes. For example, generative AI trained on cat images would learn to recognize distinct features like ears, whiskers, and fur patterns. 2. Decipher the unwritten rules. Next, it calculates the conditional probability distribution of these structures. In other words, it finds the order and relationship between various structures and the building blocks. Imagine that kitchen again. We know that knives are more likely to be found near cutting boards than, say, pillows, and that a sofa is typically found in front of a TV in the living room. Generative AI quantifies such relationships which allows it to then understand the underlying rules of how likely certain elements are to co-occur and in what order. 3. Perform a bold and creative remix. Finally, armed with this knowledge of building blocks and the rules of their order and structure, generative AI can create entirely new samples. It combines the learned structures and their conditional probabilities in novel ways, producing something entirely new yet rooted in the representations extracted from the training data. This could be a photorealistic image of a cat with unique markings, a catchy song inspired by popular hits, or even a compelling scientific hypothesis based on existing research.

Music Similarity Ranking: Case Study Fairphonic

Fairphonic Pte Ltd is a technology company operating in the music sector. Fairphonic provides services to detect content on social media that is suspected of copyright infringement. Fairphonic utilizes audio features for the detection process. The current algorithm used by Fairphonic requires pairwise comparison, and the content to be compared is collected through a scraping process immediately after the process is run. Fairphonic has hundreds of thousands of music data in their database. Fairphonic desires a more scalable algorithm to compare an input music piece with the entire Fairphonic music catalog. This research uses features such as Harmonic Pitch Class Profile (HPCP), Chroma, and Rhythm Pattern. The study compares previously researched algorithms, namely binary similarity matrix, Euclidean distance, and similarity matrix profile. The results show that the combination of HPCP with the binary similarity matrix yields the highest Mean Average Precision of 0.989. Speed testing by performing comparisons 10 times shows that the combination of Chroma and the similarity matrix profile is 72% faster compared to the combination of HPCP with the binary similarity matrix. The author recommends the Chroma and similarity matrix profile algorithm for music similarity ranking due to its faster process.

A GAI-based multi-scale convolution and attention mechanism model for music emotion recognition and recommendation from physiological data

Due to the subjectivity of emotions and the limited number of emotion categories, existing deep learning models require assistance to achieve objective, accurate, and flexible personalized music emotion recommendations. This paper introduces a deep learning approach that combines Generative Artificial Intelligence (GAI) and explicitly leverages physiological indicators to enhance the model's intelligence, versatility, and automation. Physiological indicators such as Heart Rate Variability (HRV) and Galvanic Skin Response (GSR) can be measured using sensors placed on the body's surface, providing more precise information about human emotional changes. This research employs a three-dimensional emotion model, including the tension-arousal axis, energy-arousal axis, and valence axis, to explain the correlation and accuracy between music data and emotions. Based on this, a music emotion classifier is designed, incorporating GAI algorithms to recommend music by matching users' physiological and emotional types with the emotional features of music. The classifier uses Mel-Frequency Cepstral Coefficients (MFCC) to transform audio into Mel-spectrogram as input features. The music emotion selection module adopts a GAI framework of Variational Autoencoder (VAE) and integrates multi-scale parallel convolution and attention mechanism modules. Experimental results demonstrate that this approach is competitive compared to existing deep learning architectures on PMEmo, RAVDESS, and Soundtrack datasets. Furthermore, due to GAI's efficient classification capability, this model is suitable for resource-constrained mobile devices and other smart devices. The results of this study can be applied to emotion-based music recommendation systems, contributing to emotional interventions and improving the performance of exercise and music therapy.

A new sine-inspired probability model: Theoretical features with statistical modeling of the music engineering and reliability scenarios

It is a proven authenticity that probability-schooled methodologies have a cardinal role in making decisions under the vagueness circumstances. Thus, to reach meaningful and fruitful decisions under vagueness circumstances, numerous probability-focused methodologies have been introduced, promoted, and implemented. This paper also contributes to adding another useful probability model to the existing literature for data modeling in engineering-oriented areas. The new model is called the weighted sine exponentiated exponential (WSEE) distribution, which is formed by implementing the exponentiated exponential model together with a sine-adapted method. Certain properties of the WSEE distribution are given. The parameter estimation of the WSEE distribution along with the simulation study is also provided. Last, in order, we apply the WSEE distribution for analyzing three data sets taken from the musical engineering and reliability settings. The optimality of the WSEE distribution is proved by comparing its results with other prominent modifications of the exponentiated exponential distribution. Using 4 statistical criteria as judgment tools, it was shown numerically and pictorially that the WSEE distribution is an optimal and suitable model for the musical engineering reliability data sets.

Recruit, retain, repair: Toward diversity in the North Carolina Music Educators Association

In this article, I examine data generated from a 2020 survey of the North Carolina Music Educators Association (NCMEA) and data on North Carolina public school students and teachers as the focal point for a discussion about diversifying the music teaching profession and music educator association (MEA) membership. Statistical data indicated a significant difference between the racial identity profile of NCMEA membership and that of NC public school students, NC public school teachers, and NC-certified public school music teachers. In each case, statistical differences were driven by an underrepresentation of NCMEA members who identified as Black. The data also showed a significant difference in gender based on NCMEA section membership. Open response data suggested music teachers of color may have disengaged from NCMEA due to a negative organizational climate. Given these data, I discuss policy implications for MEAs to support diversifying membership and improving organizational culture.

Topological querying of music scores

For centuries, sheet music scores have been the traditional way to preserve and disseminate Western music works. Nowadays, their content can be encoded in digital formats, making possible to store music score data in digital score libraries (DSL). To supply intelligent services (extracting and analysing relevant information from data), the new generation of DSL has to rely on digital representations of the score content as structured objects apt at being manipulated by high-level operators. In the present paper, we propose the Muster model, a graph-based data model for representing the music content of a digital score, and we discuss the querying of such data through graph pattern queries. We then present a proof-of-concept of this approach, which allows storing graph-based representations of music scores in the Neo4j database, and performing musical pattern searches through graph pattern queries with the Cypher query language. A benchmark study, using (real) datasets stemming from the Neuma Digital Score Library, complements this implementation.

MUSIC GENERATION USING NEURAL NETWORK

This study investigates the utilization of recurrent neural networks (RNNs) for generating music through MIDI files. By encoding musical data into sequences, RNN models are trained to learn patterns and structures inherent in compositions. Through the analysis of MIDI data and the evaluation of generated sequences, the effectiveness of RNNs in autonomously creating cohesive musical pieces is explored, advancing the frontier of AI-driven musical composition. Keywords—Music Generation, Long Short-Term Memory, Recurrent Neural Network, MIDI data .

Global musical diversity is largely independent of linguistic and genetic histories

Music is a universal yet diverse cultural trait transmitted between generations. The extent to which global musical diversity traces cultural and demographic history, however, is unresolved. Using a global musical dataset of 5242 songs from 719 societies, we identify five axes of musical diversity and show that music contains geographical and historical structures analogous to linguistic and genetic diversity. After creating a matched dataset of musical, genetic, and linguistic data spanning 121 societies containing 981 songs, 1296 individual genetic profiles, and 121 languages, we show that global musical similarities are only weakly and inconsistently related to linguistic or genetic histories, with some regional exceptions such as within Southeast Asia and sub-Saharan Africa. Our results suggest that global musical traditions are largely distinct from some non-musical aspects of human history.

Generating Musical Sequences with Transformers

Transformers have significantly revolutionized the music-creation process by their ability to generate intricate and captivating musical arrangements. By analyzing patterns and connections within music data, transformers can produce new compositions with remarkable accuracy and originality. This study explores the internal mechanisms of transformers in music generation and highlights their potential for advancing the field of musical composition. The ability of transformers to capture extensive relationships and contextual information makes them highly suitable for tasks related to music generation. Through self-attention mechanisms, transformers effectively model the dependencies between different time intervals in a musical sequence, resulting in the production of coherent and melodious compositions. This paper delves into the specific architectural elements of transformers that enable them to comprehend and generate musical sequences while also exploring potential applications for transformer-based systems in various creative contexts - emphasizing on significant impact they could have on evolving techniques used during music composition.

Correlation dimension of natural language in a statistical manifold

The correlation dimension of natural language is measured by applying the Grassberger-Procaccia algorithm to high-dimensional sequences produced by a large-scale language model. This method, previously studied only in a Euclidean space, is reformulated in a statistical manifold via the Fisher-Rao distance. Language exhibits a multifractal, with global self-similarity and a universal dimension around 6.5, which is smaller than those of simple discrete random sequences and larger than that of a Barabási-Albert process. Long memory is the key to producing self-similarity. Our method is applicable to any probabilistic model of real-world discrete sequences, and we show an application to music data. Published by the American Physical Society 2024

Course genres classification of music e-learning platform based on deep learning big data intelligent processing algorithm

At present, the growth trend of digital music information is showing an exponential form. Various songs can be classified according to their unique genres and styles, forming various “genres”. So, how to effectively manage the massive amount of music data has become a problem that needs to be solved to promote the balanced development of different types and genres of music. On this basis, this article adopts deep learning technology to study the classification methods of music genres oriented towards big data. Firstly, this article studies LSTM based on long and short term memory networks and compares its advantages and disadvantages with convolutional neural network CNN. Secondly, this article calculates the drift patterns of big data intelligent processing algorithms and conducts relevant performance tests on big data intelligent processing algorithms to verify the effectiveness of the proposed algorithms. Finally, this article addresses the problems in current music genre classification research by introducing Mel filters into the extraction of sound features to further improve the efficiency and speed of the model. And deep learning technology is adopted to construct a music genre classification model based on big data intelligent analysis, further promoting the effective improvement of music genre classification effectiveness.

Differences in music appreciation between bilateral and single-sided cochlear implant recipients

ObjectiveTo compare changes in music appreciation after cochlear implant (CI) surgery for patients with bilateral and single-sided deafness (SSD). MethodsA retrospective cohort study was performed on all adult CI unilateral or bilateral recipients from November 2019 to March 2023. Musical questionnaire subset data from the Cochlear Implant Quality of Life (CIQOL) – 35 Profile Instrument Score (maximum raw score of 15) was collected. Functional CI assessment was measured with CI-alone speech-in-quiet (SIQ) scores (AzBio and CNC). Results22 adults underwent CI surgery for SSD and 21 adults for bilateral deafness (8 sequentially implanted). Every patient group had clinically significant improvements (p < 0.001) in mean SIQ scores in the most recently implanted ear (Azbio (% correct) SSD: 14.23 to 68.48, bilateral: 24.54 to 82.23, sequential: 6.25 to 82.57). SSD adults on average had higher music QOL scores at baseline (SSD: 11.05; bilateral: 7.86, p < 0.001). No group had significant increases in raw score at the first post-operative visit (SSD: 11.45, p = 0.86; bilateral: 8.15, p = 0.15). By the most recent post-implantation evaluation (median 12.8 months for SSD, 12.3 months for bilateral), SSD adults had a significant increase in raw score from baseline (11.05 to 12.45, p = 0.03), whereas bilaterally deafened (7.86 to 9.38, p = 0.12) adults had nonsignificant increases. ConclusionsSSD patients demonstrate higher baseline music appreciation than bilaterally deafened individuals regardless of unilateral or bilateral implantation and are more likely to demonstrate continued improvement in subjective music appreciation at last follow-up even when speech perception outcomes are similar.

From Music Scores to Audio Recordings: Deep Pitch-Class Representations for Measuring Tonal Structures

The availability of digital music data in various modalities provides opportunities both for music enjoyment and music research. Regarding the latter, the computer-assisted analysis of tonal structures is a central topic. For Western classical music, studies typically rely on machine-readable scores, which are tedious to create for large-scale works and comprehensive corpora. As an alternative, music audio recordings, which are readily available, can be analyzed with computational methods. With this paper, we want to bridge the gap between score- and audio-based measurements of tonal structures by leveraging the power of deep neural networks. Such networks are commonly trained in an end-to-end fashion, which introduces biases towards the training repertoire or towards specific annotators. To overcome these problems, we propose a multi-step strategy. First, we compute pitch-class representations of the audio recordings using networks trained on score–audio pairs. Second, we measure the presence of specific tonal structures using a pattern-matching technique that solely relies on music theory knowledge and does not require annotated training data. Third, we highlight these measurements with interactive visualizations, thus leaving the interpretation to the musicological experts. Our experiments on Richard Wagner's large-scale cycle Der Ring des Nibelungen indicate that deep pitch-class representations lead to a high similarity between score- and audio-based measurements of tonal structures, thus demonstrating how to leverage multimodal data for application scenarios in the computational humanities, where an explicit and interpretable methodology is essential.

Genres Classification of Popular Songs Listening by Using Keras

Listening to the music affects the brain in ways which might help to promote the human health and arrange various diseases symptoms. Music is a phenomenon that is intertwined at every stage of human life. In the modern era music is shaped by the combination of an incredible number of genres, some of which are contemporary, and some come from the previous times. The music genre represents a collection of musical works that develop according to a certain shape, expression and technique. The music genre of interest varies from person to person in society. Most listeners today do not know what kind of music they listen to. In this study, sound features were extracted from music data and the Keras model was trained using these attributes. The correct classification rate of a music genre of the trained model was determined as 71.66%. Mel Frequency Cepstral Coefficients (MFCC), Mel Spectrogram, Chroma Vector and Tonnetz methods in the Librosa library were used to extract sound properties from music data. Using the features probed by means of the library, the most listened songs with Shazam in Türkiye were categorized in with TensorFlow/Keras. Many methods can be used in classification. It is uncertain which method the researchers should opt. It has been emphasized that classification of the genres of newly released songs by using Keras in this study. At result, it is said that the study has presented a sound processing are Keras classification of musical parts.