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

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.

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.

Processamento e análise de vídeos utilizando Floresta de Caminhos Ótimos

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Processamento e análise de vídeos utilizando Floresta de Caminhos Ótimos

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Towards a classification scheme for musical sounds

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

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.

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.

A Ciropedia de Xenofonte: um romance de formação na Antiguidade

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Escribir(se) fuera de los límites : (sobre En estado de memoria de Tununa Mercado)

En estado de memoria de Tununa Mercado es un texto que parece resistirse a la clasificación genérica. A pesar de que podría encuadrarse dentro del género autobiográfico, las reflexiones que ofrece la autora sobre la escritura, la memoria y el exilio abren la posibilidad de trascender los límites de la insoslayable autorreferencia. En efecto, al mismo tiempo, Tununa Mercado afirma e impugna al cogito ergo sum cartesiano, por un lado, y la capacidad representativa del lenguaje, por otro. En rigor, la autora pone en cuestión la categoría de identidad al presentar a un yo que, lejos de borrarse o anularse, se extravía en la búsqueda de un autorreconocimiento horadando las zonas oscuras de la memoria para encontrarse, paradójicamente, en un lenguaje incapaz de representarlo y en distintas figuraciones de la alteridad

Proposal for the analysis of a video game, a film, and their relationship : Silent Hill as a subject of the horror genre

Aquest treball de recerca fa un estudi comparatiu del videojoc de terror amb el seu homòleg cinematogràfic. L’objectiu és arribar a saber si els dos mitjans de comunicació usen les mateixes tècniques per transmetre les seves històries i per crear suspens. Aquesta investigació és només una part d'un estudi més ampli amb el que es pretén tenir un coneixement més aprofundit de les emocions de la gent i les reaccions que els provoca un videojoc de terror en comparació amb la visualització de l'adaptació cinematogràfica del corresponent videojoc.

Des typologies mécaniques à l'expérience esthétique : fonctions et mutations du genre dans le jeu vidéo

Cette thèse examine en profondeur la nature et l’application du concept de genre en jeu vidéo. Elle se divise en trois parties. La première fait l’inventaire des théories des genres en littérature et en études cinématographiques. Les propriétés essentielles du genre comme concept sont identifiées : il s’agit d’une catégorisation intuitive et irraisonnée, de nature discursive, qui découle d’un consensus culturel commun plutôt que de systèmes théoriques, et qui repose sur les notions de tradition, d’innovation et d’hybridité. Dans la deuxième partie, ces constats sont appliqués au cas du genre vidéoludique. Quelques typologies sont décortiquées pour montrer l’impossibilité d’une classification autoritaire. Un modèle du développement des genres est avancé, lequel s’appuie sur trois modalités : l’imitation, la réitération et l’innovation. Par l’examen de l’histoire du genre du first-person shooter, la conception traditionnelle du genre vidéoludique basée sur des mécanismes formels est remplacée par une nouvelle définition centrée sur l’expérience du joueur. La troisième partie développe l’expérience comme concept théorique et la place au centre d’une nouvelle conception du genre, la pragmatique des effets génériques. Dans cette optique, tout objet est une suite d’amorces génériques, d’effets en puissance qui peuvent se réaliser pourvu que le joueur dispose des compétences génériques nécessaires pour les reconnaître. Cette nouvelle approche est démontrée à travers une étude approfondie d’un genre vidéoludique : le survival horror. Cette étude de cas témoigne de l’applicabilité plus large de la pragmatique des effets génériques, et de la récursivité des questions de genre entre le jeu vidéo, la littérature et le cinéma.

Biologically inspired features for scene classification in video surveillance

Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper. © 2010 IEEE.

A Phylogenetic Classification of the Video-Game Industry’s Business Model Ecosystem

Part 8: Business Strategies Alignment