Tiago Fernandes Tavares

We explore relationships between self-efficacy, socioeconomic factors, study strategies, and academic performance based on a controlled observational study framework utilizing data from the Brazilian ENEM (Exame Nacional do Ensino Médio, or National High School Exam, a national assessment taken by students at the end of high school) exam. Our investigation reveals a substantial impact of self-efficacy on academic grades of high-achieving students across diverse disciplines. Furthermore, we investigate the influence of socioeconomic aspects, including family income, gender, and race, on academic performance, demonstrating their varying effects contingent upon the discipline and student achievement level. Moreover, we search for the most effective study strategies in different student achievement levels, providing actionable insights to enhance educational practices. This research contributes to a deeper understanding of the determinants of academic achievement and offers valuable implications for educational policy and practice aimed at fostering inclusive and effective learning environments.

Bird song identification has mainly been approached as a closed-set classification problem; that is, all samples are known to be from one of the classes known by the classifier. However, wildlife monitoring using bird songs is closer to an open-set classification setting, as the classifier is required to predict if a sample comes from an unknown origin, like an environmental sound or an unrelated animal. Furthermore, current approaches to bird song classification assume that the model can access the whole dataset and build optimal projections. This is not a realistic scenario in Brazil as the country has thousands of species, and it is unfeasible to build a dataset containing a representative diversity of samples of all of them. This work analyzes algorithms that can be used for the open-set classification of bird songs. The analyzed algorithms can fit models using data from one or from only a few species. The investigation revealed many current technical difficulties and highlighted several opportunities for future work in this field.

Many art installations rely on camera-based audiovisual interactions, and this commonly requires specialized hardware and software. Consequently, audiovisual installations are usually restricted to wealthier areas, in which the specialized equipment can be afforded and properly hosted. In countries with an evident income unbalance linked to location, the geographic restriction leads to an audience restriction. In this work, we present the development of a web-deployed composition tool for audiovisual interactions that runs on the client side and does not require installing any additional software. Simultaneously, it provides visual feedback that can aid the audience to understand the experience. Consequently, the tool can be used to compose audiovisual interactions that reach a large audience via web. We further explore the tool by composing the audiovisual installation Homino-idea. The installation is inspired by the interactions between humans and the environment, and can be either shown in art venues or used online.

O trabalho apresentado consistiu na obtenção de dados de sinais cerebrais, coletados através de eletroencefalografia, em voluntários ouvindo música. Estes preencheram um formulário para descrever a percepção provacada por cada música. Ao total, foram capturados dados de 10 voluntários, A intenção é, em trabalhos futuros, que esses dados sejam utilizados para associar emoções evocadas com os sinais elétricos cerebrais.

We propose a method that quantifies the importance, namely relevance, of audio segments for classification in weakly-labelled problems. It works by drawing information from a set of class-wise one-vs-all classifiers. By selecting the classifiers used in each specific classification problem, the relevance measure adapts to different user-defined viewpoints without requiring additional neural network training. This characteristic allows the relevance measure to highlight audio segments that quickly adapt to user-defined criteria. Such functionality can be used for computer-assisted audio analysis. Also, we propose a neural network architecture, namely RELNET, that leverages the relevance measure for weakly-labelled audio classification problems. RELNET was evaluated in the DCASE2018 dataset and achieved competitive classification results when compared to previous attention-based proposals.

In this work, we analyse the random projections of Mel-spectrograms as low-level features for music genre classification. This approach was compared to handcrafted features, features learned using an auto-encoder and features obtained from a transfer learning setting. Tests in five different well-known, publicly available datasets show that random projections leads to results comparable to learned features and outperforms features obtained via transfer learning in a shallow learning scenario. Random projections do not require using extensive specialist knowledge and, simultaneously, requires less computational power for training than other projection-based low-level features. Therefore, they can be are a viable choice for usage in shallow learning content-based music genre classification.

This is a lab report paper about the state of affairs in the computer music research group at the School of Electrical and Computer Engineering of the University of Campinas (FEEC/Unicamp). This report discusses the people involved in the group, the efforts in teaching and the current research work performed. Last, it provides some discussions on the lessons learned from the past few years and some pointers for future work.