Developing a Voice Interface for Music Searching

The search for music for a video is time-intensive. Video creators and bloggers listen to hundreds of tracks in music libraries, yet barely find the perfect one because of the difficulty of communicating their vision to the computer. Thus, the question we address in this research project is on the role of the modality, in which information is presented (e.g. voice, text, music, video), on the interpretation of this information. In particular, the project focused on the exploration of the music searching for video and comparison of two communication contexts: computer-mediated communication between human users and human-agent communication. The research project will involve preparing and conducting user studies, data analysis, and writing the research paper. The preparation of the user study might involve the design and implementation of a conversational agent prototype for capturing the context and idea of the user using modern artificial intelligence and deep learning techniques.

Faculty Supervisor:

Anastasia Kuzminykh

Student:

Partner:

National Technical University of Ukraine

Discipline:

Computer science

Sector:

Artificial Intelligence; Information and Communications Technology; Entertainment and Media

University:

University of Toronto

Program: