System and method for applying a convolutional neural network to speech recognition

US9734824B2 · kind B2 · utility

Assignees

• The Governing Council of the University of Toronto · CA
• Hui Jian · CA
• Ossama Abdelhamid · CA
• Mohamed Abdelhamid · CA

Inventors

• Gerald Bradley Penn · Toronto, CA
• Hui Jiang · Taipei, TW
• Ossama Abdelhamid Mohamed Abdelhamid · Toronto, CA
• Abdel-rahman Samir Abdel-rahman Mohamed · Toronto, CA

Key dates

• Filing date: May 25, 2015
• Grant date: Aug 15, 2017
• Expiry date: Sep 18, 2035

Classification

• Technology area (CPC G): Physics
• CPC primary: G10L25/30
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A system and method for applying a convolutional neural network (CNN) to speech recognition. The CNN may provide input to a hidden Markov model and has at least one pair of a convolution layer and a pooling layer. The CNN operates along the frequency axis. The CNN has units that operate upon one or more local frequency bands of an acoustic signal. The CNN mitigates acoustic variation.