Music Emotion Research Articles

"The Little Prince" Ballet Performed by Radu Poklitaru: Features of Implementation of Classics

The purpose of the article is to reveal artistic images in "The Little Prince" ballet performance by Radu Poklitar with music by V. A. Mozart and Ukrainian lullabies performed by Maria Pylypchak. The methodology of the work is based on cultural analysis with elements of musicological analysis. The performed analysis provides familiarity with the ballet performance, the production of which took place on the theatre stage. Based on the synthesis of the obtained research results, the regularities of stage development in the interaction of choreography, music, and visualisation were established. The method of generalisation helped to record the sequence of formation of ballet images, disclosure of events in dialogue with music and visual series. The scientific novelty of the work lies in the fact that the analysis of the said ballet by Radu Poklitaru has been conducted. The interaction of choreography, music, and visual series in the embodiment of the philosophical fairy tale by Antoine Saint-Exupéry is revealed. The text of the article can be used when preparing a lecture on teaching music-theoretical and music-historical disciplines. Conclusions. Based on the analysis of "The Little Prince" ballet performance, the musical characteristics of the Little Prince, Rose, Snake and other actors were revealed by Radu Poklitaru. The stage unity of choreography, music, and visual series helped embody artistic images in the music-theatre genre. Choreography (elements of classics, free movements, imagery in movements) is supported by musical emotion and visualisation. The visual series significantly influenced the transmission of the philosophy and content of the literary source. The dramaturgy of the ballet is subordinated to the plot development. The musical basis of ballet became the basis for the realisation of artistic images in ballet: Mozart's works (Symphony No. 1, Fantasia in D minor, Piano Concerto with Orchestra No. 23, Part 2) and Ukrainian lullabies.
 Key words: embodiment of the classics, literary source, piano music, symphony, fantasy, artistic image, Radu Poklitaru’s "The Little Prince" ballet, Wolfgang Amadeus Mozart, Ukrainian lullabies.

An emotional perspective of music festival experience evaluation: a new model of emotional analysis

PurposeThe aim of this paper is to test a new proposal of a model to analyze emotional outcomes in relation to the key factors constituting the experience of a music festival.Design/methodology/approachThis article first examines how emotions and intangible impacts are conceptualized and analyzed by different disciplines; secondly, this article exposes the relevance of musical emotions and the contextual elements in the generation of the music festival experience; the article then proposes a new model to assess the emotional impacts of music festivals, named the Emotional Impact of Music Festivals (EIMF). Finally, this article shows the test of the model through quantitative and qualitative analysis.FindingsThe findings reveal that perceived emotions in the music festival context should be based on the definition of musical emotions. At the same time, the model combines the different sources of emotions taken from validated tools in multiple academic disciplines. The new proposal enables the emotional outcome of the music festival experience to be identified and helps to understand the weight of the experience's main elements.Practical implicationsThe new proposed model facilitates the research on music festivals and illuminates the key role of music when organizing festivals to enhance attendee experience. Finally, this model reveals the main elements required to obtain an intense emotional outcome in these types of events.Originality/valueThe study expands the different scales and model proposals in live events and combines existent musical emotion models from the psychological perspective with theoretical models from the intangible impact evaluation. This study shows a genuine test for a theoretical model that can be further developed. Finally, this study shows how the new tool EIMF can help music festival organizers to understand the weight of the constituting factors of festival experience and the results in applied studies.

Music listening as an emotion regulation strategy of students during COVID-19 lockdown

Τhe purpose of the current study was to examine the positive impact of music listening and musical emotion regulation strategies as predictors of students’ affect during COVID-19 lockdown. Two hundred and three students from University of Western Macedonia completed an on-line self-report questionnaire consisting of Positive Music Listening Experience Scale, Music Uses and Gratifications Scale, Positive and Negative Affect Schedule. Results indicate that students’ positive affect is positively related with positive impact of music listening as well as with negative mood management, whereas negative affect is negatively related with negative mood management. Furthermore, positive impact of music listening was the only predictor of students’ positive affect, while both emotion regulation strategies were predictors of students’ negative affect. Results indicate the importance of music listening as an emotion regulation strategy of students during pandemic. The practical applications and limitations of the research are discussed.

Investigations on the Performance of Pre-established CNN Model in Music Emotion Detection

Music is a medium for emotional artistic expression. Different people have different understandings of music. Music emotion recognition (MER) has thus become a novel branch in computer music. The goal of this essay is to investigate in the performance of established CNN architectures, such as AlexNet and VGG16, to recognize emotions contained in a song. CAL500 dataset is used as it covers a variety of genres. The dataset is transformed to spectrograms, which can be understood by computers through image recognition. The result of this investigation turned out to be that previous architectures would lead to overfitting within the training of a few batches. Possible explanations for this are that the parameters used in the model are too large for a simple regression task. This research provides some understanding of how CNN works as a network initially designed for image classification. Understanding emotions using spectrograms might require less complex CNN models or new models that are specialized in such tasks.

Emotion Recognition of Music based on Machine Learning Scenarios

As the rapid development of computer music, the technique for recognizing the emotion of music also have many progresses. After the brief introduction of the history of computer music, this paper mainly discusses about the current existing machine learning models for the emotion recognition in music. The complexity of emotion has been emphasized in this paper for several reasons. In addition, by comparison different models, this paper summarizes common features, metrics and steps used in music emotion analyzation. Moreover, this study finds out the limitations and disadvantages of different classifications and feature extracting method for different models, pointing out the living problems, e.g., the difficulty of emotion recognition for experimental music. To sum up, this paper summarizes and analyzes the primary studying in the field of music emotion recognition, offering a guideline for implementations of different machine learning approaches in the field. These results shed light on paving a path for further exploration of emotion recognition in computer music.

The role of listener features in musical emotion induction: The contributions of musical expertise, personality dispositions, and mood state.

The role of listener features in musical emotion induction: The contributions of musical expertise, personality dispositions, and mood state.

Examining Emotion Perception Agreement in Live Music Performance

Current music emotion recognition (MER) systems rely on emotion data averaged across listeners and over time to infer the emotion expressed by a musical piece, often neglecting time- and listener-dependent factors. These limitations can restrict the efficacy of MER systems and cause misjudgements. In a live music concert setting, fifteen audience members annotated perceived emotion in valence-arousal space over time using a mobile application. Analyses of inter-rater reliability yielded widely varying levels of agreement in the perceived emotions. A follow-up lab study to uncover the reasons for such variability was conducted, where twenty-one listeners annotated their perceived emotions through a recording of the original performance and offered open-ended explanations. Thematic analysis reveals many salient features and interpretations that can describe the cognitive processes. Some of the results confirm known findings of music perception and MER studies. Novel findings highlight the importance of less frequently discussed musical attributes, such as musical structure, performer expression, and stage setting, as perceived across different modalities. Musicians are found to attribute emotion change to musical harmony, structure, and performance technique more than non-musicians. We suggest that listener-informed musical features can benefit MER in addressing emotional perception variability by providing reasons for listener similarities and idiosyncrasies.

Digital Music Emotion Recognition Technique Using Multi-Class Support Vector Machine

This research presents a recognition method for digital music emotion, specifically focusing on addressing the challenge of recognizing sampling-based digital music formats. The proposed method combines sound feature parameters and music theory feature parameters and employs a multi-class support vector machine (SVM) based sorting technology. The method involves four key steps: preprocessing, feature extraction, training the multi-class SVM, and recognition. Emotions such as happiness, impassion, sadness, and relaxation are classified within a sampling-based digital music format file. In addition to extracting common sound features used in speech recognition, a range of music theory features are also extracted. The adoption of the SVM-based sorting method results in rapid learning speed, high sorting precision ratio, and improved recognition efficiency.

Efficacy of the Tuned In music emotion regulation program in international university students

Objective Moving overseas to study can be exciting, however many international students find this transition stressful. Therefore, empirically supported strategies to assist with managing stress and supporting well-being are needed. Motivated music listening is an effective stress management strategy, and is linked with international student well-being. Tuned In is a group program designed to increase emotion awareness and regulation using motivated music listening. Methods and measures We evaluated a 4-session online version of Tuned In for motivated music use, emotion regulation, and well-being in international students. The study used a 2 (Treatment; Waitlist) x 3 (timepoints: pre = T1; +4 weeks = T2; +8 weeks = T3) randomised controlled cross-over design. Treatment participants (n = 23) completed Tuned In between T1 and T2, Waitlist participants (n = 27) completed Tuned In between T2 and T3. Results Between T1 and T2, motivated music use increased in Treatment participants but not for the Waitlist. Treatment participants were also more confident in maintaining happiness and in having healthy ways of managing emotions at T2. All participants enjoyed Tuned In. Conclusions Tuned In, a group-based music listening program, even when delivered online, provides benefits for international students. With student well-being at risk as they begin university, enjoyable programs that help develop skills for students’ academic journey should be a priority.

Music sentiment classification based on an optimized CNN-RF-QPSO model

PurposeMusic sentiment analysis helps to promote the diversification of music information retrieval methods. Traditional music emotion classification tasks suffer from high manual workload and low classification accuracy caused by difficulty in feature extraction and inaccurate manual determination of hyperparameter. In this paper, the authors propose an optimized convolution neural network-random forest (CNN-RF) model for music sentiment classification which is capable of optimizing the manually selected hyperparameters to improve the accuracy of music sentiment classification and reduce labor costs and human classification errors.Design/methodology/approachA CNN-RF music sentiment classification model is designed based on quantum particle swarm optimization (QPSO). First, the audio data are transformed into a Mel spectrogram, and feature extraction is conducted by a CNN. Second, the music features extracted are processed by RF algorithm to complete a preliminary emotion classification. Finally, to select the suitable hyperparameters for a CNN, the QPSO algorithm is adopted to extract the best hyperparameters and obtain the final classification results.FindingsThe model has gone through experimental validations and achieved a classification accuracy of 97 per cent for different sentiment categories with shortened training time. The proposed method with QPSO achieved 1.2 and 1.6 per cent higher accuracy than that with particle swarm optimization and genetic algorithm, respectively. The proposed model had great potential for music sentiment classification.Originality/valueThe dual contribution of this work comprises the proposed model which integrated two deep learning models and the introduction of a QPSO into model optimization. With these two innovations, the efficiency and accuracy of music emotion recognition and classification have been significantly improved.

Arousal but not valence: Music emotion categorization in normal hearing and cochlear implanted participants

Perceiving acoustic cues that convey music emotion is challenging for cochlear implant (CI) users. Emotional arousal (stimulating/relaxing) can be conveyed by temporal cues such as tempo, while emotional valence (positive/negative) can be conveyed by spectral information salient to pitch and harmony. It is however unclear the extent to which other temporal and spectral features convey emotional arousal and valence in music, respectively. In 23 normal-hearing participants, we varied the quality of temporal and spectral content using vocoders during a music emotion categorization task—musical excerpts conveyed joy (high arousal high valence), fear (high arousal low valence), serenity (low arousal high valence), and sorrow (low arousal low valence). Vocoder carriers (sinewave/noise) primarily modulated temporal information, and filter orders (low/high) primarily modulated spectral information. Improvement of temporal- (using sinewave carriers) and spectral content (using high filter order) both improved categorization. Vocoder results were compared to data from 25 CI users performing the same task with non-vocoded musical excerpts. The CI user data showed a similar pattern of errors as observed for the vocoded conditions in normal-hearing participants, suggesting that increasing the quality of temporal information, and not only spectral details, could prove beneficial for CI users’ music emotion perception.

Perception of emotional music by children with cochlear implants reveals developmental plasticity

Cochlear implants provide poor access to the frequency components needed to accurately identify emotional music and speech. Nonetheless, a series of studies revealed that children with cochlear implants develop unique strategies to identify emotion in music. Although musical changes were difficult for them to detect, children with cochlear implants responded most accurately to rhythmic changes and also relied mainly on temporal information to judge whether music was happy or sad. By contrast, mode (frequency) information dominated perception of musical emotion in typically developing children and was used more clearly by bimodal device users (cochlear implant in one ear with acoustic hearing in the other) than children with bilateral deafness using unilateral or bilateral cochlear implants. Mode became the more dominant cue with increasing residual hearing in the non-implanted ear. Children with unilateral cochlear implants showed prolonged response times relative to a control group of normal hearing peers while judging whether music was happy or sad. Response times in children with bimodal devices and bilateral cochlear implants were more similar to controls. Together, these results demonstrate development of novel strategies for music listening and perception of emotion in music based on available cues in children with cochlear implants and suggest that these strategies require cognitive resource.

Instrumental Music Emotion Recognition with MFCC and KNN Algorithm

Every piece of music contains emotion in every sound presented. Detection of the music emotion is quite difficult to do because the emotions felt are subjective. Based on this problem, it is necessary to have an automatic classification system to detect the emotions produced in music. In this paper, an explanation of the result to develop an emotional classification system of instrumental music. This system described the process starting with the receiving an input in the form of a music file in the format wav. Furthermore, the feature extraction process is carried out using Mel-Frequency Cepstral Coefficients (MFCC). The result of the extraction of such features are used in the classification process using the K-Nearest Neighbor (K-NN). The system produced output in the form of happy, relaxed, and sad emotions. The output of the system has a classification achieved an accuracy of 97.5% for the value of k = 1, reaching an accuracy of 95% for the value of k = 2.95% and for k = 3, reaching an accuracy of up to 90%.

The design of intelligent fuzzy cognitive system of music emotion by product supply chain management

AbstractThe classification of musical emotion is a challenging problem due to the subjectivity of human perception. In order to analyse the emotion contained in music from the perspective of product supply chain management, the psychological model and characteristics of music emotion are introduced. Additionally, the current product supply chain and the composition of the two contracts are analysed based on the characteristics of online music products. Finally, a speech emotion recognition model based on a Fuzzy Cognitive Map (FCM) is proposed. Two corpora containing five emotions (sadness, anger, happiness, surprise, and boredom) are selected to test the performance and characteristics of the network. In order to evaluate the system performance, different acoustic features are extracted, including prosodic features, formant features, marginal spectral features, and Mel‐Frequency Cepstral Coefficients (MFCC). The results show that the average recognition rate of MFCC features on the Berlin emotional speech database is 70.36%, which is 0.75% higher than the second‐highest edge spectrum features and achieves better results. Meanwhile, on this database, the Musical Emotion Recognition System based on FCM (MERS‐FCM) is improved by 20.36%, 7.34%, and 4.12% compared with Back Propagation, K‐nearest neighbour, and support vector machine, respectively, which shows that MERS‐FCM has better performance. The research of the music emotion recognition system based on FCM can provide more reference paths for the use and development of music emotion information.

Affective Responses to Music: An Affective Science Perspective

Music has strong emotional powers. How are we to understand affective responses to music? What does music teach us about emotions? Why are musical emotions important? Despite the rich literature in philosophy and the empirical sciences, particularly psychology and neuroscience, little attention has been paid to integrating these approaches. This extensive review aims to redress this imbalance and establish a mutual dialogue between philosophy and the empirical sciences by presenting the main philosophical puzzles from an affective science perspective. The chief problem is contagion. Sometimes, listeners perceive music as expressing some emotion and this elicits the same emotion in them. Contagion is perplexing because it collides with the leading theory of emotions as experiences of values. This article mostly revolves around the critical presentation of the philosophical solutions to this problem in light of recent developments in emotion theory and affective science. It also highlights practical issues, particularly the role of musical emotions in well-being and health, by tackling the paradox of sad music, i.e., the question of why people enjoy sad music. It thus bridges an important gap between theoretical and real-life issues as well as between philosophical and empirical investigations on affective responses to music.

Music Emotion Recognition Based on a Neural Network with an Inception-GRU Residual Structure

As a key field in music information retrieval, music emotion recognition is indeed a challenging task. To enhance the accuracy of music emotion classification and recognition, this paper uses the idea of inception structure to use different receptive fields to extract features of different dimensions and perform compression, expansion, and recompression operations to mine more effective features and connect the timing signals in the residual network to the GRU module to extract timing features. A one-dimensional (1D) residual Convolutional Neural Network (CNN) with an improved Inception module and Gate Recurrent Unit (GRU) was presented and tested on the Soundtrack dataset. Fast Fourier Transform (FFT) was used to process the samples experimentally and determine their spectral characteristics. Compared with the shallow learning methods such as support vector machine and random forest and the deep learning method based on Visual Geometry Group (VGG) CNN proposed by Sarkar et al., the proposed deep learning method of the 1D CNN with the Inception-GRU residual structure demonstrated better performance in music emotion recognition and classification tasks, achieving an accuracy of 84%.

Modeling Emotion Dynamics in Song Lyrics with State Space Models

Abstract Most previous work in music emotion recognition assumes a single or a few song-level labels for the whole song. While it is known that different emotions can vary in intensity within a song, annotated data for this setup is scarce and difficult to obtain. In this work, we propose a method to predict emotion dynamics in song lyrics without song-level supervision. We frame each song as a time series and employ a State Space Model (SSM), combining a sentence-level emotion predictor with an Expectation-Maximization (EM) procedure to generate the full emotion dynamics. Our experiments show that applying our method consistently improves the performance of sentence-level baselines without requiring any annotated songs, making it ideal for limited training data scenarios. Further analysis through case studies shows the benefits of our method while also indicating the limitations and pointing to future directions.

Multimodal music emotion recognition in Indonesian songs based on CNN-LSTM, XLNet transformers

Music carries emotional information and allows the listener to feel the emotions contained in the music. This study proposes a multimodal music emotion recognition (MER) system using Indonesian song and lyrics data. In the proposed multimodal system, the audio data will use the mel spectrogram feature, and the lyrics feature will be extracted by going through the tokenizing process from XLNet. Convolutional long short term memory network (CNN-LSTM) performs the audio classification task, while XLNet transformers performs the lyrics classification task. The outputs of the two classification tasks are probability weight and actual prediction with the value of positive, neutral, and negative emotions, which are then combined using the stacking ensemble method. The combined output will be trained into an artificial neural network (ANN) model to get the best probability weight output. The multimodal system achieves the best performance with an accuracy of 80.56%. The results showed that the multimodal method of recognizing musical emotions gave better performance than the single modal method. In addition, hyperparameter tuning can affect the performance of multimodal systems.

Effect of music emotion on mu and beta oscillations

That music elicits motor signals has been suggested as the key to understanding how emotion may be experienced from it. While previous studies have demonstrated that music both induces movement and affects ongoing motor activities, little is known about the effect of its emotional content on neural-motor representation and how such an effect may be modified by concurrent movement. To fill this gap, we asked participants to tap their right index finger following flashes of a dot (movement) or just to count the flashes silently (no-movement) while listening to happy versus emotionally neutral music, when EEG was recorded. Results showed that happy music induced greater mu (8–13 Hz) suppression than neutral music in the no-movement but not the movement condition. For beta oscillations (16–24 Hz), happy music induced greater suppression than neutral music irrespective of concurrent movement. These findings suggest a close association between music emotion and motor representation at a neural level, supporting theories stipulating that emotion in music is experienced through motor representation, such as embodied music cognition and the Shared Affective Motion Experience model.

Music emotion recognition based on a modified brain emotional learning model

Music emotion recognition based on a modified brain emotional learning model