Grants and Contributions:

Grant or Award spanning more than one fiscal year (2017-2018 to 2018-2019).

Describing music with natural language is not easy. The accuracy of any such description is typicallyx000D
proportional to one's level of expertise with the subject. The ability to search for music efficiently usingx000D
language is therefore typically reserved for musicians.x000D
Apollo Music Store (AMS) specializes in curating and licensing music to fulfill the needs of advertisingx000D
agencies and brands around the world. To stay at the top of its field, AMS is experimenting with new ways ofx000D
letting its users find and select relevant music efficiently. AMS aims to eliminate the need to translate musicalx000D
ideas to natural language, and instead allow users to input music tracks into the AMS search engine asx000D
examples of what they are looking for.x000D
Building on results obtained during our Engage Grant titled Content-aware Music Recommender System usingx000D
Emotion Recognition, where our algorithms reached accuracies of up to 87% on given emotions, we intend tox000D
pursue our research in designing machine-learning algorithms for the automated recommendation of music,x000D
based on the emotional and acoustic similarities to an audio example provided by the user. This projectx000D
combines the quest to understand how to model human emotions with machine learning techniques and musicx000D
theory, and thus has far reaching applications in affective computing, cognitive science and artificialx000D
intelligence research.