NEURAL NETWORK TRAINING APPARATUS AND METHOD, AND SPEECH RECOGNITION APPARATUS AND METHOD
First Claim
Patent Images
1. A neural network training apparatus comprising:
- a primary trainer configured to perform a primary training of a neural network model based on clean training data and target data corresponding to the clean training data; and
a secondary trainer configured to perform a secondary training of the neural network model on which the primary training has been performed based on noisy training data and a probability distribution of an output class for the clean training data calculated during the primary training of the neural network model.
1 Assignment
0 Petitions
Accused Products
Abstract
A neural network training apparatus includes a primary trainer configured to perform a primary training of a neural network model based on clean training data and target data corresponding to the clean training data; and a secondary trainer configured to perform a secondary training of the neural network model on which the primary training has been performed based on noisy training data and an output probability distribution of an output class for the clean training data calculated during the primary training of the neural network model.
-
Citations
27 Claims
-
1. A neural network training apparatus comprising:
-
a primary trainer configured to perform a primary training of a neural network model based on clean training data and target data corresponding to the clean training data; and a secondary trainer configured to perform a secondary training of the neural network model on which the primary training has been performed based on noisy training data and a probability distribution of an output class for the clean training data calculated during the primary training of the neural network model. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A neural network training method comprising:
-
performing a primary training of a neural network model based on clean training data and target data corresponding to the clean training data; and performing a secondary training of the neural network model on which the primary training has been performed based on noisy training data and a probability distribution of an output class for the clean training data calculated during the primary training of the neural network model. - View Dependent Claims (9, 10, 11, 12, 13, 14, 15)
-
-
16. A speech recognition apparatus comprising:
-
a feature extractor configured to extract a feature of noisy speech data; and a phoneme probability calculator configured to calculate a probability of a phoneme corresponding to the extracted feature using an acoustic model; wherein the acoustic model is an acoustic model on which a primary training has been performed based on speech training data and a phoneme sequence corresponding to the speech training data, and a secondary training has been performed based on noisy speech training data and a probability distribution of an output class for the speech training data calculated during the primary training of the acoustic model. - View Dependent Claims (17, 18, 19, 20, 21, 22, 23)
-
-
24. A neural network training apparatus comprising:
-
a primary trainer configured to perform a primary training of a neural network model based on clean training data and hard target data; and a secondary trainer configured to perform a secondary training of the neural network model on which the primary training has been performed based on noisy training data and soft target data obtained during the primary training of the neural network model. - View Dependent Claims (25, 26, 27)
-
Specification