Speech Localization and Recognition for Humanoid Robotics

Robots and other autonomous machines currently have limited sound awareness and speech recognition capabilities, which limits their ability to interact with humans. Applying insights from cognitive neuroscience provides novel ways to improve these interactions. The primary objective of this proposal is to implement an auditory AI for robotics that finds human talkers in the environment and recognizes what they are saying. At the end of the project we anticipate a functioning speech localization and recognition system that will allow humanoid robots to understand and communicate verbally with humans. This expands on work done in a Canada-Italy Innovation award in 2017. This system will use state-of-the-art neural network approaches in machine learning, and will be tested on the iCub cognitive robotics platform.

Faculty Supervisor:

Matthew Tata

Student:

Partner:

Istituto Italiano di Tecnologia

Discipline:

Computer science

Sector:

Education

University:

University of Lethbridge

Program: