Individualização do Perfil de Consumo Musical usando Aprendizagem de Métricas/
Mendes, Angelo
Individualização do Perfil de Consumo Musical usando Aprendizagem de Métricas/ Seminário de Computação Gráfica: Angelo Mendes. - Rio de Janeiro: IMPA, 2020. - video online
Abstract: This presentation consists of showing the study developed in the paper A Music Classification Model based on Metric Learning Applied to MP3 Audio Files and the results obtained with the evolution of the study. This paper proposes a novel music classification model based on metric learning, whose main objective is to learn a personalized metric for each customer. The metric learning process considers the learning of a set of parameterized distances employing a structured prediction approach from a set of MP3 audio files containing several music genres according to the customers preference. To extract the acoustic information from audio files, we used the Mel-Frequency Cepstral Coefficient (MFCC) and made a dimensionality reduction using Principal Components Analysis (PCA). We attest to the model validity performing a set of experiments and comparing the results with Soft Margin Linear Support Vector Machine (SVM) .
Matematica.
Individualização do Perfil de Consumo Musical usando Aprendizagem de Métricas/ Seminário de Computação Gráfica: Angelo Mendes. - Rio de Janeiro: IMPA, 2020. - video online
Abstract: This presentation consists of showing the study developed in the paper A Music Classification Model based on Metric Learning Applied to MP3 Audio Files and the results obtained with the evolution of the study. This paper proposes a novel music classification model based on metric learning, whose main objective is to learn a personalized metric for each customer. The metric learning process considers the learning of a set of parameterized distances employing a structured prediction approach from a set of MP3 audio files containing several music genres according to the customers preference. To extract the acoustic information from audio files, we used the Mel-Frequency Cepstral Coefficient (MFCC) and made a dimensionality reduction using Principal Components Analysis (PCA). We attest to the model validity performing a set of experiments and comparing the results with Soft Margin Linear Support Vector Machine (SVM) .
Matematica.