Music Database Research Articles

Continuous Hidden Markov Algorithm-Based Multimedia Melody Retrieval System for Music Education

Education professionals receive instruction in Music Education (ME) to prepare for prospective jobs like secondary or primary music teachers, schools ensembles executives, or ensembles directors at music institutions. In the discipline of music education, educators do original research on different approaches to teaching and studying music. The most accurate and effective method of extracting music from huge music databases has become one of the most frequently discussed participants in contemporary multimedia information retrieval development. The essence of multimedia material is presented within a range of techniques since it is not bound to a single side. These several categories could consist of the song’s audio components and lyrics for musical information. Retrieving melodic information, subsequently, becomes the main focus of most recent studies. Aside from being an expensive deviate from academics, music programs are neither a viable profession neither a valid pastime. Therefore, in this study, we offer a Continuous Hidden Markov Algorithm (CHMA) related a novel method for recovering melodies from musical multimedia recordings. CHMA is considered to be the most basic dynamic Bayesian network. Two various types of audio frame features and audio example features are extracted throughout the feature extraction procedure from the audio signal according to unit length. Every music clip receives a unique approach that we implement with concurrently using various CHMA. The initial music gets processed using a trained CHMA that monitors fundamental frequencies, maps states, and generates retrieval outcomes. The training time for Traditional opera reached 455.76 minutes, the testing time for Narration achieved 56.10 minutes, and the recognition accuracy for advertisement reached an impressive 98.02%. A subsequently experimental result validates the applicability of the proposed approach.

A Multi-sentence Music Humming Retrieval Algorithm Based on Relative Features and Deep Learning

This project will study a fast retrieval method for music humming speech recognition based on sentence features and deep learning. The method proposed in this paper can realize the fast extraction of songs. According to the characteristics of the natural pause mode of the song, the song database and the song fragments provided by the user are divided into different sentences. The deep learning algorithm of BDTW is used to calculate the similarity of the song's pitch, and users can set matching conditions according to their preferences. It can identify the most significant differences between music fragments and the order of queries in the database. Then, a retrieval method of a music database based on DIS is proposed. It can shorten the acquisition time. Experiments show that the algorithm can recognize humming songs quickly and efficiently.

Face Melody-Mood-Aware Music Recommendation System with Facial Recognition

Abstract: The proposed Face Melody analyzes the user’s facia l expressions in real time. Through the user’s webcam, the system captures emotional cues, such as joy, sadness, or excitement, and processes this data to understand the user’s current mood. Face Melody leverages a sophisticated recommendation engine that correlates the detected mood with a vast music database, ensuring that the music selection aligns with the user’s emotional context. The recommendation engine considers a variety of factors, including tempo, genre, lyrics, and historical preferences to provide a personalized and emotionally resonant playlist. The system also adapts in real-time, allowing users to change their music selection as their mood evolves. Whether a user is looking to lift their spirits, relax, or reflect, face Melody is designed to cater to these emotional shifts

The Emotion-to-Music Mapping Atlas (EMMA): A systematically organized online database of emotionally evocative music excerpts

Selecting appropriate musical stimuli to induce specific emotions represents a recurring challenge in music and emotion research. Most existing stimuli have been categorized according to taxonomies derived from general emotion models (e.g., basic emotions, affective circumplex), have been rated for perceived emotions, and are rarely defined in terms of interrater agreement. To redress these limitations, we present research that served in the development of a new interactive online database, including an initial set of 364 music excerpts from three different genres (classical, pop, and hip/hop) that were rated for felt emotion using the Geneva Emotion Music Scale (GEMS), a music-specific emotion scale. The sample comprised 517 English- and German-speaking participants and each excerpt was rated by an average of 28.76 participants (SD = 7.99). Data analyses focused on research questions that are of particular relevance for musical database development, notably the number of raters required to obtain stable estimates of emotional effects of music and the adequacy of the GEMS as a tool for describing music-evoked emotions across three prominent music genres. Overall, our findings suggest that 10–20 raters are sufficient to obtain stable estimates of emotional effects of music excerpts in most cases, and that the GEMS shows promise as a valid and comprehensive annotation tool for music databases.

Multidimensional Scale Analysis and Modeling of Emotional Space in Yao Music

Abstract The research content of this paper gives a detailed analysis of the system structure of the music emotion recognition system. In the process of music feature extraction and recognition, the system first reads the note queue and tempo information queue of the format music and then analyzes and calculates the basic features of the music, tonal and melodic features, etc., respectively. The content of the text set is projected into a three-dimensional visual space using the multidimensional scale analysis method, and then the emotional theme is obtained by dividing the class groups. The samples from the Yao music database are selected as the data source for music emotion research, and performance analysis is performed. The results prove that the method of this paper can effectively perform feature extraction on Yao music files, with an average misdetection rate of only 0.09% and a recognition rate of more than 83% in all cases. The musical structure of Yao Village Impression can be broken down into five parts. The musical melodies mostly consist of major second and minor third intervals. The emotional labeling of structures 1 and 4 in the cluster analysis is distributed in four quadrants, with a preference for pleasurable emotions. Structure 2 was more concentrated in quadrants 1, 4. These emotion distribution results are consistent with the music depicting the beauty of Yao village and the emotional life of Yao people.

Spotivey: A web application for simplified use of the Spotify application programming interface in online questionnaire studies

Everyday music listening has become an important research topic during the last decades. However, self-reporting through questionnaire surveys, the received approach for studying individual music consumption, presents methodological challenges. The rise of mobile music streaming and open application programming interfaces introduces new opportunities to address these productively. Spotivey is a free research software that integrates music streaming provider API functionalities into online surveys and in this way allows to connect digital behavioral traces with self-reported questionnaire data. The current version effortlessly retrieves comprehensive information about respondents’ past music listening on Spotify while they fill an online survey. Through an informed consent procedure, General Date Protection Regulation compliance for this new form of digital data donation is ensured. Methodical challenges include participant dropout and the need for robust statistical analysis methods. Planned future enhancements encompass expanding application programming interfaces support, enriching retrieved data with information from other music databases, and compatibility with diverse online survey design systems.

Review on Facial Expression Based Music Recommendation System

The Emotion-Aware Smart Music Recommendation System represents a pioneering venture in the realm of music technology, aiming to revolutionize the way we connect with music. This system employs advanced emotion recognition techniques, including facial expression analysis, voice sentiment analysis, and biometric sensors, to continuously assess the user's emotional state. Complemented by a meticulously curated music database with songs categorized based on emotional attributes, the system's recommendation engine utilizes machine learning and deep learning models to offer music that aligns with the user's current emotional profile. The integration of a feedback loop ensures that the system adapts and refines its recommendations, improving the user's experience over time. Accessible across a variety of platforms, including mobile apps, web interfaces, and smart speakers, this system aspires to offer a profoundly personalized and emotionally resonant listening experience, redefining the relationship between music and emotion.

Automatic music emotion classification model for movie soundtrack subtitling based on neuroscientific premises

The ability of music to induce emotions has been arousing a lot of interest in recent years, especially due to the boom in music streaming platforms and the use of automatic music recommenders. Music Emotion Recognition approaches are based on combining multiple audio features extracted from digital audio samples and different machine learning techniques. In these approaches, neuroscience results on musical emotion perception are not considered. The main goal of this research is to facilitate the automatic subtitling of music. The authors approached the problem of automatic musical emotion detection in movie soundtracks considering these characteristics and using scientific musical databases, which have become a reference in neuroscience research. In the experiments, the Constant-Q-Transform spectrograms, the ones that best represent the relationships between musical tones from the point of view of human perception, are combined with Convolutional Neural Networks. Results show an efficient emotion classification model for 2-second musical audio fragments representative of intense basic feelings of happiness, sadness, and fear. Those emotions are the most interesting to be identified in the case of movie music captioning. The quality metrics have demonstrated that the results of the different models differ significantly and show no homogeneity. Finally, these results pave the way for an accessible and automatic captioning of music, which could automatically identify the emotional intent of the different segments of the movie soundtrack.

Design of a Music Recommendation Device Using Mini-Xception CNN and Facial Recognition

Due to the emerging developments in Artificial Intelligence and Machine Learning Technologies, various prediction systems are been developed based on human emotions and real time aspects of human psychology as well. Facial recognition system is one such mechanism which is the most vibrant strategy used for predicting human emotions. It is extensively applied in surveillance systems, fault identification and other security related aspects. Based on the human emotions researchers have already proposed several music recommendation systems. This paper aims to propose a Facial recognition-based music recommendation system to treat the psychology patients. This helps to recover the patients from mental stress, anxiety, and depression. The suggested method aims to take into account the limitations of the face recognition system in current frameworks, such as the requirement to lower the processing delay for deep feature extraction and the necessity to design a Mini exception technique based on Deep Convolutional Neural Network (DCNN) architecture. The FER- 2013 image dataset, which consists of 35000 face photos with automated labelling is considered. It is used to determine how well the proposed approach would detect the various emotion classes. In comparison to other states of methods, the Mini exception technique utilised in CNN layers acts as a lightweight system. The proposed solution has a 92% accuracy rate and removes the barrier between the current frameworks. The suggested music is taken from a music database and then further mapped in accordance with the algorithm's output.

Music Segmentation and Similarity Estimation Applied to a Gaze-Controlled Musical Interface

Assistive technology, especially gaze-controlled, can promote accessibility, health care, well-being and inclusion for impaired people, including musical activities that can be supported by interfaces controlled using eye tracking. Also, the Internet growth has allowed access to a huge digital music database, which can contribute to a new form of music creation. In this paper, we propose the application of Music Information Retrieval techniques for music segmentation and similarity identification, aiming at the development of a new form of musical creation using an automatic process and the optimization algorithm Harmony Search to combine segments. These techniques for segmentation and similarity of segments were implemented in an assistive musical interface controlled by eye movement to support musical creation and well-being. The experimental results can be found in [https://bit.ly/2Zl7KSC].

Neural Networks And Ensemble Based Architectures To Automatic Musical Harmonization: A Performance Comparison

ABSTRACT Harmony can be defined in a musical way as art that combines several musical notes reproduced simultaneously to create sounds that are coherent to human ears and serve as accompaniment and filling. However, working out harmony is not a simple task. It requires knowledge, experience, and an intense study of music theory, which takes time to reach good skills. Thus, systems capable of automatically harmonizing melodies are beneficial for experienced and novice musicians. In this paper, a comparative study between distinct architectures and ensembles of Artificial Neural Networks was proposed to solve the problem of musical harmonization, seeking consistent results with rules of music theory: Multilayer Perceptron (MLP), Radial Basis Function network (RBF), Echo State Network (ESN), Extreme Learning Machines (ELM), and Long Short-Term Memory (LSTM). For this, a processed and defined melody with symbolic musical data serves as input to the system, having been trained from a musical database that contains melody and harmony. The output is the chord sequence to be applied to the melody. The results were analyzed with quantitative measures and the ability to melody adaptation. The performances were favorable to the MLP, which could generate harmonies according to the objectives.

A Descriptive Survey of Atmospheric Music Broadcasting in Hot Spring Hotels and Its Further Marketing Strategy

The survey purposes are to preliminarily understand the current situation of atmospheric music broadcast in hot spring hotels and why these choices of music were made. We reviewed literatures regarding applied music and music types, and applied questionnaire, participant observation and unstructured interviews with hotel staff who broadcast music in the unique, famous and historic Guanzihling hot spring region of Taiwan. Results show that music is often broadcast in public areas, such as lobby and restaurants. On the contrary, there was no music broadcast in private areas, such as guest rooms and private thermal baths. Light music is the primary music choice. Music types is chosen without rules by staff who have no basic trainings in music. Possible marketing strategies for future studies include the staff trainings and construction of hotel’s own hot spring music database, and better marketing of hotel’s unique multi-sensory brand image through its distinctive and pleasant music.

Music Genre Classification Using African Buffalo Optimization

In the discipline of Music Information Retrieval (MIR), categorizing music files according to their genre is a difficult process. Music genre classification is an important multimedia research domain for classification of music databases. In the proposed method music genre classification using features obtained from audio data is proposed. The classification is done using features extracted from the audio data of popular online repository namely GTZAN, ISMIR 2004 and Latin Music Dataset (LMD). The features highlight the differences between different musical styles. In the proposed method, feature selection is performed using an African Buffalo Optimization (ABO), and the resulting features are employed to classify the audio using Back Propagation Neural Networks (BPNN), Support Vector Machine (SVM), Naïve Bayes, decision tree and kNN classifiers. Performance evaluation reveals that, ABO based feature selection strategy achieves an average accuracy of 82% with mean square error (MSE) of 0.003 when used with neural network classifier.

A Robust Emotion Detection and Music Recommendation System using Mini Xception CNN

Abstract: Due to the emerging developments in artificial intelligence(AI) and machine learning(ML) Technology various systems are developed in recent days that late the human emotions and real time aspects of human psychology detection. Facial recognition based music recommendation system (MRS) is a interesting area of research where he plays an important role in handling the psychology patients. Face recognition system is extensively applied in security systems surveillance systems fault identification etc. Based on Emotion of the human, the music recommendation needs to be provided to analyse the phycology changes with the patients. The proposed approach is focused on considering the constraints available with the facial recognition system in existing frameworks such as deep feature extraction processing delay need to be reduce the hair using deep convolutional neural network(DCNN) architecture based Mini exception algorithm is developed. The system considered FER2013 image dataset that contains 35000 face images with automated labels that would be helpful for the presented approach to identify the emotion class accurately. The Mini exception algorithm used in CNN layers act as a lightweight system compared with various states of approaches. The proposed system removes the barrier between the existing frameworks and achieved the accuracy of 92%. The recommended music is derived from the music database and further mapped with respect to the algorithm result.

Past, Present, and Future of the Collections of Cinema and Media Music Database

For many scholars, critical analysis of film and media music is stymied by a lack of published or manuscript materials, and discoverability of such materials is many times hampered by how archival materials are cataloged. While numerous composers have deposited their papers at libraries and archives across the globe, discovery of these collections has occurred via citations in books and articles, or word-of-mouth between scholars. This is because archival collections are cataloged with a focus on the creator of the collection and not the individual object (such as a book or manuscript score). Therefore, if the score or other materials for a film are in a collection of a studio, or someone other than the composer themselves, they might be hard, if not impossible, to find without a lot of searching or a stroke of luck. Adding to the difficulty is that some of these collections are not fully indexed or searchable, so many materials remain hidden under a century of backlogged archival processing. In order to address this problem, the Collections of Cinema and Media Music (C2M2) has been designed, built, and populated by a small team spread across the United States. This paper will discuss the design and implantation of C2M2, with a focus on the task of creating a custom metadata schema that addresses the unique issues of film and media music, and the myriad of ways a researcher might try to access a particular score. It will also show the reader how the metadata functions and displays within the database, with discussions of the challenges inherent in a project of this scope. As research into film and media music continues to expand, scholars are clamoring for access to materials to expand their research beyond the realm of music–film relationships and into areas reliant on archival materials. In such a world, tools such as C2M2 will be critical in creating the ease of access that will eliminate the barriers that hamper such work.

Machine Learning for Music Genre Classification Using Visual Mel Spectrum

Music is the most convenient and easy-to-use stress release tool in modern times. Many studies have shown that listening to appropriate music can release stress. However, since it is getting easier to make music, people only need to make it on the computer and upload it to streaming media such as Youtube, Spotify, or Beatport at any time, which makes it very infeasible to search a huge music database for music of a specific genre. In order to effectively search for specific types of music, we propose a novel method based on the visual Mel spectrum for music genre classification, and apply YOLOv4 as our neural network architecture. mAP was used as the scoring criterion of music genre classification in this study. After ten experiments, we obtained a highest mAP of 99.26%, and the average mAP was 97.93%.

Large-Scale Music Genre Analysis and Classification Using Machine Learning with Apache Spark

The trend for listening to music online has greatly increased over the past decade due to the number of online musical tracks. The large music databases of music libraries that are provided by online music content distribution vendors make music streaming and downloading services more accessible to the end-user. It is essential to classify similar types of songs with an appropriate tag or index (genre) to present similar songs in a convenient way to the end-user. As the trend of online music listening continues to increase, developing multiple machine learning models to classify music genres has become a main area of research. In this research paper, a popular music dataset GTZAN which contains ten music genres is analysed to study various types of music features and audio signals. Multiple scalable machine learning algorithms supported by Apache Spark, including naïve Bayes, decision tree, logistic regression, and random forest, are investigated for the classification of music genres. The performance of these classifiers is compared, and the random forest performs as the best classifier for the classification of music genres. Apache Spark is used in this paper to reduce the computation time for machine learning predictions with no computational cost, as it focuses on parallel computation. The present work also demonstrates that the perfect combination of Apache Spark and machine learning algorithms reduces the scalability problem of the computation of machine learning predictions. Moreover, different hyperparameters of the random forest classifier are optimized to increase the performance efficiency of the classifier in the domain of music genre classification. The experimental outcome shows that the developed random forest classifier can establish a high level of performance accuracy, especially for the mislabelled, distorted GTZAN dataset. This classifier has outperformed other machine learning classifiers supported by Apache Spark in the present work. The random forest classifier manages to achieve 90% accuracy for music genre classification compared to other work in the same domain.

The WASABI song corpus and knowledge graph for music lyrics analysis

We present the WASABI Song Corpus, a large corpus of songs enriched with metadata extracted from music databases on the Web, and resulting from the processing of song lyrics and from audio analysis. More specifically, given that lyrics encode an important part of the semantics of a song, we focus here on the description of the methods we proposed to extract relevant information from the lyrics, such as their structure segmentation, their topics, the explicitness of the lyrics content, the salient passages of a song and the emotions conveyed. The corpus contains 1.73M songs with lyrics (1.41M unique lyrics) annotated at different levels with the output of the above mentioned methods. The corpus labels and the provided methods can be exploited by music search engines and music professionals (e.g. journalists, radio presenters) to better handle large collections of lyrics, allowing an intelligent browsing, categorization and recommendation of songs. We demonstrate the utility and versatility of the WASABI Song Corpus in three concrete application scenarios. Together with the work on the corpus, we present the work achieved to transition the dataset into a knowledge graph, the WASABI RDF Knowledge Graph, and we show how this will enable an even richer set of applications.

Music Data Feature Analysis and Extraction Algorithm Based on Music Melody Contour

Music is a way to reflect people’s real-life emotions, and listening to music has become an inseparable habit of the daily life. Text-based music information retrieval is still the main way for people to find music, but this method has obvious shortcomings and deficiencies, and it is a relatively cumbersome and inefficient method. In order to solve this problem, this paper proposes a feature extraction LAM algorithm based on the contour of music melody. Melody is the most important extraction feature in content-based music retrieval. Users can hum a song according to their own memory and then extract the rhythm, melody, and other information of the hummed audio information to match and identify the rhythm and melody features of the original song stored in the database. The retrieval method is based on the melody, rhythm, and other musical features of music and involves many issues such as the expression of musical melody, feature extraction of musical melody, user query construction, music melody matching, and music database construction. With the help of the customized query interface, media information can be retrieved. Finally, the experiment proves that the top-ten hit rate of the LAM algorithm after clustering is 91.3%, the top-three hit rate is 78.8%, and the first hit rate is 71.2%. The approximate symbol matching DP algorithm has a top-ten hit rate of 83.6%, a top-three hit rate of 66.4%, and a first hit rate of 63.6%. The method proposed in this paper has a high retrieval hit rate.

Note Detection in Music Teaching Based on Intelligent Bidirectional Recurrent Neural Network

Music education is an essential and significant link in a quality education, as it can assist pupils improve their integrity and nurture noble character. The evident distinction between music teaching and teaching in other disciplines is that music teaching can provide aesthetic education to students in order to improve students’ self-cultivation and overall temperament and basically play a role in developing people in a holistic fashion. Note detection is an important content in music teaching. Instrument tuning, computerized score recognition, music database search, and electronic music synthesis all benefit greatly from note detection technologies. In note detection, there are problems such as difficult one-to-one correspondence between estimated pitches and standard frequencies, a narrow range of identifiable pitches, poor robustness of the recognition process, and low recognition rate. In this context, this work proposes an automatic note detection in music teaching based on deep learning. It uses a convolutional neural network (CNN) and a bidirectional long-short-term memory (BiLSTM) network to build a deep neural network model, called convolutional neural network Bidirectional Long Short-Term Memory (CNN-BiLSTM), using this network to conduct in-depth research on note detection. First, based on the current research status, a deep neural network model based on CNN and BiLSTM is proposed to detect musical notes. The network can independently mine and learn the deep-level features of music signals and has better feature extraction and generalization capabilities. Second, the experimental results are evaluated using different evaluation metrics. Experiments show the network model can significantly improve detection accuracy and can efficiently detect notes in music teaching.