New trends in musical genre classification using optimum-path forest

Musical genre classification has been paramount in the last years, mainly in large multimedia datasets, in which new songs and genres can be added at every moment by anyone. In this context, we have seen the growing of musical recommendation systems, which can improve the benefits for several applications, such as social networks and collective musical libraries. In this work, we have introduced a recent machine learning technique named Optimum-Path Forest (OPF) for musical genre classification, which has been demonstrated to be similar to the state-of-the-art pattern recognition techniques, but much faster for some applications. Experiments in two public datasets were conducted against Support Vector Machines and a Bayesian classifier to show the validity of our work. In addition, we have executed an experiment using very recent hybrid feature selection techniques based on OPF to speed up feature extraction process. © 2011 International Society for Music Information Retrieval.

Short-term Feature Space and Music Genre Classification

In music genre classification, most approaches rely on statistical characteristics of low-level features computed on short audio frames. In these methods, it is implicitly considered that frames carry equally relevant information loads and that either individual frames, or distributions thereof, somehow capture the specificities of each genre. In this paper we study the representation space defined by short-term audio features with respect to class boundaries, and compare different processing techniques to partition this space. These partitions are evaluated in terms of accuracy on two genre classification tasks, with several types of classifiers. Experiments show that a randomized and unsupervised partition of the space, used in conjunction with a Markov Model classifier lead to accuracies comparable to the state of the art. We also show that unsupervised partitions of the space tend to create less hubs.

Unsupervised automatic music genre classification

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial para obtenção do grau de Mestre em Engenharia Informática

Exploring different approaches for music genre classification

In this letter, we present different approaches for music genre classification. The proposed techniques, which are composed of a feature extraction stage followed by a classification procedure, explore both the variations of parameters used as input and the classifier architecture. Tests were carried out with three styles of music, namely blues, classical, and lounge, which are considered informally by some musicians as being “big dividers” among music genres, showing the efficacy of the proposed algorithms and establishing a relationship between the relevance of each set of parameters for each music style and each classifier. In contrast to other works, entropies and fractal dimensions are the features adopted for the classifications.

Towards a classification scheme for musical sounds

Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2013

Musical genres: beating to the rhythms of different drums

Online music databases have increased significantly as a consequence of the rapid growth of the Internet and digital audio, requiring the development of faster and more efficient tools for music content analysis. Musical genres are widely used to organize music collections. In this paper, the problem of automatic single and multi-label music genre classification is addressed by exploring rhythm-based features obtained from a respective complex network representation. A Markov model is built in order to analyse the temporal sequence of rhythmic notation events. Feature analysis is performed by using two multi-variate statistical approaches: principal components analysis (unsupervised) and linear discriminant analysis (supervised). Similarly, two classifiers are applied in order to identify the category of rhythms: parametric Bayesian classifier under the Gaussian hypothesis (supervised) and agglomerative hierarchical clustering (unsupervised). Qualitative results obtained by using the kappa coefficient and the obtained clusters corroborated the effectiveness of the proposed method.

Contribuições da inserção musical para a qualidade de vida no trabalho em ambiente laboral fabril

The present thesis aimed at understanding how the insertion of music in the work environment contributes to achieving Quality of Work Life. - QWL, under the perspective of biopsychosocial and organizational well-being. As to music insertion we considered the theoretical-empirical perception about how music is inserted at work and its functions on such place. The context where the study was taken was the manufacturing area of a major textile company, located in Natal, state of Rio Grande do Norte, Brazil, in which music is used during labor activities. The only study case was the research strategy adopted, with exploratory and descriptive purposes. The primary data were collected through the focus group technique, applied to the collaborator in the manufacturing sector. The semi-structured interview was done as a complementary tool, directed to the supervisor in that sector. Respecting the theoretical saturation criterion, we formed four focus groups, each one composed of eight members randomly selected, among the seventy-six collaborators in the sector. The data were analyzed qualitatively, through the content analysis technique, more specifically the category analysis. We identified twenty-eight QWL attributes. Six of them were found present in the four focus groups and in the interview. Among these ones, the attribute of Interpersonal Relationship at Work, contemplating the Psychological and Organizational dimensions, was the only one anticipated in four out of fifteen theoretical models here listed. The attribute Music at Work Environment could be inserted in the four QWL dimensions, highlighting the power and relevance of this attribute for the research participants. The way music has been inserted in the labor environment contributes to promoting well-being at work, which goes against theoretical conceptions, especially when it comes to musical genre. We identified nine functions of music at work, among which, Improving Work Conditions, Improving Interpersonal Relationship at Work and Favoring Motivation for Work had to be emphasized for being associated to three QWL attributes. In the total, we highlighted seven associations. The most affected QWL dimension through the insertion of music at work was the Psychological one, followed by the Organizational one. We conclude that music insertion provides biological, social and, above all, psychological and organizational well-being to the contributors, thus contributing to obtaining QWL at the labor environment researched. However, we should consider the context and proceed to periodical plans and adjustments in the way of music insertion so as to avoid health and well-being problems to those people at work

A multimodal genre recognition prototype

In this paper, a multimodal and interactive prototype to perform music genre classification is presented. The system is oriented to multi-part files in symbolic format but it can be adapted using a transcription system to transform audio content in music scores. This prototype uses different sources of information to give a possible answer to the user. It has been developed to allow a human expert to interact with the system to improve its results. In its current implementation, it offers a limited range of interaction and multimodality. Further development aimed at full interactivity and multimodal interactions is discussed.

CONSTRUÇÕES IMAGINÁRIAS NO CONTEXTO DE UM FENÔMENO MUSICAL DE MASSA: O CASO DO CANTOR MICHEL TELÓ

Estudo sobre o processo de construção imaginária do público de gênero feminino ao consumir os produtos dos fenômenos musicais de massa, no Brasil. Tendo como base o caso do sucesso do cantor Michel Teló, representante do gênero musical sertanejo universitário, o objetivo é compreender o processo de construção imaginária que permeia a relação do público feminino (fãs) e consumo do gênero musical sertanejo universitário, a partir do discurso do cantor Michel Teló. Para tal, será tomado referencial teórico do campo dos Estudos Culturais em diálogo com estudos sobre imaginário e música de massa. A análise do discurso, de linha francesa, é a metodologia empregada em duas instâncias para se testar as reflexões construídas com a base teórica: a priori, a partir de um processo de observação participante, durante um espetáculo do artista, em que será observada a interação entre fenômeno e público, no momento de execução da sua música Ai, se eu te pego! ; e, doravante, o discurso do músico é analisado, por meio de entrevistas realizadas em programas televisivos. Um questionário aplicado a uma amostra entre o público feminino apreciador do cantor e de suas músicas contribui ainda no aprofundamento da reflexão. Resulta desta pesquisa a compreensão da proeminência do discurso ao conteúdo. Desta maneira, a importância maior se encontra na forma com que o cantor dialoga com seu público, por meio da imagem que ele constrói em torno de si.

CONSTRUÇÕES IMAGINÁRIAS NO CONTEXTO DE UM FENÔMENO MUSICAL DE MASSA: O CASO DO CANTOR MICHEL TELÓ

Estudo sobre o processo de construção imaginária do público de gênero feminino ao consumir os produtos dos fenômenos musicais de massa, no Brasil. Tendo como base o caso do sucesso do cantor Michel Teló, representante do gênero musical sertanejo universitário, o objetivo é compreender o processo de construção imaginária que permeia a relação do público feminino (fãs) e consumo do gênero musical sertanejo universitário, a partir do discurso do cantor Michel Teló. Para tal, será tomado referencial teórico do campo dos Estudos Culturais em diálogo com estudos sobre imaginário e música de massa. A análise do discurso, de linha francesa, é a metodologia empregada em duas instâncias para se testar as reflexões construídas com a base teórica: a priori, a partir de um processo de observação participante, durante um espetáculo do artista, em que será observada a interação entre “fenômeno” e público, no momento de execução da sua música “Ai, se eu te pego!”; e, doravante, o discurso do músico é analisado, por meio de entrevistas realizadas em programas televisivos. Um questionário aplicado a uma amostra entre o público feminino apreciador do cantor e de suas músicas contribui ainda no aprofundamento da reflexão. Resulta desta pesquisa a compreensão da proeminência do discurso ao conteúdo. Desta maneira, a importância maior se encontra na forma com que o cantor dialoga com seu público, por meio da imagem que ele constrói em torno de si.

Contribuições da inserção musical para a qualidade de vida no trabalho em ambiente laboral fabril

The present thesis aimed at understanding how the insertion of music in the work environment contributes to achieving Quality of Work Life. - QWL, under the perspective of biopsychosocial and organizational well-being. As to music insertion we considered the theoretical-empirical perception about how music is inserted at work and its functions on such place. The context where the study was taken was the manufacturing area of a major textile company, located in Natal, state of Rio Grande do Norte, Brazil, in which music is used during labor activities. The only study case was the research strategy adopted, with exploratory and descriptive purposes. The primary data were collected through the focus group technique, applied to the collaborator in the manufacturing sector. The semi-structured interview was done as a complementary tool, directed to the supervisor in that sector. Respecting the theoretical saturation criterion, we formed four focus groups, each one composed of eight members randomly selected, among the seventy-six collaborators in the sector. The data were analyzed qualitatively, through the content analysis technique, more specifically the category analysis. We identified twenty-eight QWL attributes. Six of them were found present in the four focus groups and in the interview. Among these ones, the attribute of Interpersonal Relationship at Work, contemplating the Psychological and Organizational dimensions, was the only one anticipated in four out of fifteen theoretical models here listed. The attribute Music at Work Environment could be inserted in the four QWL dimensions, highlighting the power and relevance of this attribute for the research participants. The way music has been inserted in the labor environment contributes to promoting well-being at work, which goes against theoretical conceptions, especially when it comes to musical genre. We identified nine functions of music at work, among which, Improving Work Conditions, Improving Interpersonal Relationship at Work and Favoring Motivation for Work had to be emphasized for being associated to three QWL attributes. In the total, we highlighted seven associations. The most affected QWL dimension through the insertion of music at work was the Psychological one, followed by the Organizational one. We conclude that music insertion provides biological, social and, above all, psychological and organizational well-being to the contributors, thus contributing to obtaining QWL at the labor environment researched. However, we should consider the context and proceed to periodical plans and adjustments in the way of music insertion so as to avoid health and well-being problems to those people at work

A flexible bio-inspired hierarchical model for analyzing musical timbre

A flexible and multipurpose bio-inspired hierarchical model for analyzing musical timbre is presented in this paper. Inspired by findings in the fields of neuroscience, computational neuroscience, and psychoacoustics, not only does the model extract spectral and temporal characteristics of a signal, but it also analyzes amplitude modulations on different timescales. It uses a cochlear filter bank to resolve the spectral components of a sound, lateral inhibition to enhance spectral resolution, and a modulation filter bank to extract the global temporal envelope and roughness of the sound from amplitude modulations. The model was evaluated in three applications. First, it was used to simulate subjective data from two roughness experiments. Second, it was used for musical instrument classification using the k-NN algorithm and a Bayesian network. Third, it was applied to find the features that characterize sounds whose timbres were labeled in an audiovisual experiment. The successful application of the proposed model in these diverse tasks revealed its potential in capturing timbral information.

Contribuições da inserção musical para a qualidade de vida no trabalho em ambiente laboral fabril

The present thesis aimed at understanding how the insertion of music in the work environment contributes to achieving Quality of Work Life. - QWL, under the perspective of biopsychosocial and organizational well-being. As to music insertion we considered the theoretical-empirical perception about how music is inserted at work and its functions on such place. The context where the study was taken was the manufacturing area of a major textile company, located in Natal, state of Rio Grande do Norte, Brazil, in which music is used during labor activities. The only study case was the research strategy adopted, with exploratory and descriptive purposes. The primary data were collected through the focus group technique, applied to the collaborator in the manufacturing sector. The semi-structured interview was done as a complementary tool, directed to the supervisor in that sector. Respecting the theoretical saturation criterion, we formed four focus groups, each one composed of eight members randomly selected, among the seventy-six collaborators in the sector. The data were analyzed qualitatively, through the content analysis technique, more specifically the category analysis. We identified twenty-eight QWL attributes. Six of them were found present in the four focus groups and in the interview. Among these ones, the attribute of Interpersonal Relationship at Work, contemplating the Psychological and Organizational dimensions, was the only one anticipated in four out of fifteen theoretical models here listed. The attribute Music at Work Environment could be inserted in the four QWL dimensions, highlighting the power and relevance of this attribute for the research participants. The way music has been inserted in the labor environment contributes to promoting well-being at work, which goes against theoretical conceptions, especially when it comes to musical genre. We identified nine functions of music at work, among which, Improving Work Conditions, Improving Interpersonal Relationship at Work and Favoring Motivation for Work had to be emphasized for being associated to three QWL attributes. In the total, we highlighted seven associations. The most affected QWL dimension through the insertion of music at work was the Psychological one, followed by the Organizational one. We conclude that music insertion provides biological, social and, above all, psychological and organizational well-being to the contributors, thus contributing to obtaining QWL at the labor environment researched. However, we should consider the context and proceed to periodical plans and adjustments in the way of music insertion so as to avoid health and well-being problems to those people at work

Sobre a interpretação das batalhas ibéricas para órgão do século XVII: uma leitura da "Batalha famoza" do manuscrito MM 43 da Biblioteca Pública Municipal do Porto

A batalha é geralmente considerada como um dos géneros mais característicos da literatura organística ibérica do Barroco. Paradoxalmente é, de todas os géneros da música de órgão peninsular, aquele acerca do qual se possuem menos dados sobre a prática interpretativa. A informação que se pode obter a partir da generalidade dos textos seiscentistas sobre música de tecla, aplica-se sobretudo à interpretação das obras contrapontísticas, deixando em aberto muitas questões relacionadas com o carácter eminentemente descritivo das batalhas. Por outro lado, é também interessante verificar que algumas das mais convincentes interpretações de batalhas que actualmente escutamos são aquelas que resultam de uma leitura menos literal do texto musical e de uma intenção clara de sublinhar o seu carácter descritivo. A informação extraída da Batalha famoza (presente no manuscrito MM 43 da Biblioteca Pública Municipal do Porto) e apresentada ao longo deste texto parece pôr em evidência o apelo que a execução das batalhas fazia a um esforço interpretativo por parte do organista, não só através da utilização de recursos específicos do órgão ibérico, mas também mediante o emprego de uma ornamentação mais livre que pusesse em evidência o carácter descritivo daquele género musical.

Análise e síntese de música através de sistemas computacionais

Este trabalho, realizado no âmbito da unidade curricular de Tese/Dissertação, procura mostrar de que forma a Computação Evolucionária se pode aplicar no mundo da Música. Este é, de resto, um tema sobejamente aliciante dentro da área da Inteligência Artificial. Começa-se por apresentar o mundo da Música com uma perspetiva cronológica da sua história, dando especial relevo ao estilo musical do Fado de Coimbra. Abordam-se também os conceitos fundamentais da teoria musical. Relativamente à Computação Evolucionária, expõem-se os elementos associados aos Algoritmos Evolucionários e apresentam-se os principais modelos, nomeadamente os Algoritmos Genéticos. Ainda no âmbito da Computação Evolucionária, foi elaborado um pequeno estudo do “estado da arte” da aplicação da Computação Evolucionária na Música. A implementação prática deste trabalho baseia-se numa aplicação – AG Fado – que compõe melodias de Fado de Coimbra, utilizando Algoritmos Genéticos. O trabalho foi dividido em duas partes principais: a primeira parte consiste na recolha de informações e posterior levantamento de dados estatísticos sobre o género musical escolhido, nomeadamente fados em tonalidade maior e fados em tonalidade menor; a segunda parte consiste no desenvolvimento da aplicação, com a conceção do respetivo algoritmo genético para composição de melodias. As melodias obtidas através da aplicação desenvolvida são bastante audíveis e boas melodicamente. No entanto, destaca-se o facto de a avaliação ser efetuada por seres humanos o que implica sensibilidades musicais distintas levando a resultados igualmente distintos.