Physical activity based music recommendation and selection system

点击翻译按钮获取中文摘要

Inventu Research, Inc is a Victoria based company that specializes on the development of innovative products**promoting fitness in the workplace. The goal of this project is to improve the user experience of the developed**Inventu Research hardware by customizing music to their preferences and fitness goals. Two main objectives**will be pursued. The first is to explore how to automatically estimate tempo and beat information from music**tracks and utilize the extracted information in combination with data obtained by sensors on the fitness**equipment to personalize music playback. The second objective is to explore music recommendation using**timbral similarity in addition to rhythmic information. A variety of techniques that have been proposed in the**field of Music Information Retrieval will be utilized. The main innovation is the integration with fitness data**obtained by Inventu Research Inc. For the purposes of the experiments the Free Music Archive, a large**resources of music that is licensed for creative commons, will be utilized. The research group of Dr.Tzanetakis**has a strong international presence in Music Information Retrieval and Machine Learning. which are research**areas that will contribute ideas, concepts, and algorithms to the project. Two PhD students with complementary**experience in machine learning, music information retrieval, and emotion recognition, and audio signal**processing will be funded through the project and work with the designers and engineers at Inventu Research,**Inc.