US Patent 9728184 Restructuring deep neural network acoustic models
Patent 9728184 was granted and assigned to Microsoft on August, 2017 by the United States Patent and Trademark Office.
All edits
A Deep Neural Network (DNN) model used in an Automatic Speech Recognition (ASR) system is restructured. A restructured DNN model may include fewer parameters compared to the original DNN model. The restructured DNN model may include a monophone state output layer in addition to the senone output layer of the original DNN model. Singular value decomposition (SVD) can be applied to one or more weight matrices of the DNN model to reduce the size of the DNN Model. The output layer of the DNN model may be restructured to include monophone states in addition to the senones (tied triphone states) which are included in the original DNN model. When the monophone states are included in the restructured DNN model, the posteriors of monophone states are used to select a small part of senones to be evaluated.
US Patent 09728184 Restructuring deep neural network acoustic models US Patent 9728184 Restructuring deep neural network acoustic models
US Patent 09728184 Restructuring deep neural network acoustic models
Find more entities like US Patent 9728184 Restructuring deep neural network acoustic models
