SYSTEM AND METHOD FOR APPLYING A CONVOLUTIONAL NEURAL NETWORK TO SPEECH RECOGNITION
Patent №
US 9,734,824
Granted
2017-08-15
Filed 2015
Owner
THE GOVERNING COUNCIL OF THE UNIVERSITY OF TORONTO
+1 more
AI components
4
ml · nlp · speech · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
14720891
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.
AI classification
Speech1.00
Machine learning1.00
Natural language1.00
AI hardware0.92
Vision0.02
Evolutionary computation0.00
Planning0.00
Knowledge representation0.00
Ownership
THE GOVERNING COUNCIL OF THE UNIVERSITY OF TORONTO
assignment · 367510165
FLUENT.AI INC.
assignment · 446410570
From the same owner
QUANTIZATION FOR NEURAL NETWORK COMPUTATIONUS 12,566,939 · 2026SYSTEM AND METHOD FOR OFF-CHIP DATA COMPRESSION AND DECOMPRESSION FOR MACHINE LEARNING NETWORKSUS 12,555,044 · 2026METHOD AND SYSTEM FOR EFFICIENT QUANTUM OPTICAL DESIGN USING NON-LINEAR MAPPINGSUS 12,511,571 · 2025ONLINE CLASS-INCREMENTAL CONTINUAL LEARNING WITH ADVERSARIAL SHAPLEY VALUEUS 12,406,483 · 2025DEEP-LEARNING FOR DISTRIBUTED CHANNEL FEEDBACK AND PRECODINGUS 12,284,654 · 2025MONOLITHIC QUBIT INTEGRATED CIRCUITSUS 12,211,928 · 2025METHOD AND SYSTEM FOR TRAFFIC SIGNAL CONTROL WITH A LEARNED MODELUS 12,190,722 · 2025SYSTEM AND METHOD FOR USING SPARSITY TO ACCELERATE DEEP LEARNING NETWORKSUS 12,182,621 · 2024