| 发明名称 |
METHODS AND APPARATUS FOR TRAINING AN ARTIFICIAL NEURAL NETWORK FOR USE IN SPEECH RECOGNITION |
| 摘要 |
Methods and apparatus for training a multi-layer artificial neural network for use in speech recognition. The method comprises determining for a first speech pattern of the plurality of speech patterns, using a first processing pipeline, network activations for a plurality of nodes of the artificial neural network in response to providing the first speech pattern as input to the artificial neural network, determining based, at least in part, on the network activations and a selection criterion, whether the artificial neural network should be trained on the first speech pattern, and updating, using a second processing pipeline, network weights between nodes of the artificial neural network based, at least in part, on the network activations when it is determined that the artificial neural network should be trained on the first speech pattern. |
| 申请公布号 |
US2015371132(A1) |
申请公布日期 |
2015.12.24 |
| 申请号 |
US201414308054 |
申请日期 |
2014.06.18 |
| 申请人 |
Nuance Communications, Inc. |
发明人 |
Gemello Roberto;Mana Franco;Albesano Dario |
| 分类号 |
G06N3/08;G10L15/16;G06N3/04 |
主分类号 |
G06N3/08 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A method of training a multi-layer artificial neural network for use in speech recognition, wherein each of the layers in the artificial neural network includes a plurality of nodes, each of the plurality of nodes in a layer being connected to a plurality of nodes in one or more adjacent layers of the artificial neural network, wherein the connections between nodes in the artificial neural network are associated with network weights, the method comprising:
providing a plurality of speech patterns as input to the artificial neural network; determining for a first speech pattern of the plurality of speech patterns, using a first processing pipeline, network activations for the plurality of nodes of the artificial neural network in response to providing the first speech pattern as input to the artificial neural network; determining based, at least in part, on the network activations and a selection criterion, whether the artificial neural network should be trained on the first speech pattern; and updating, using a second processing pipeline, the network weights based, at least in part, on the network activations when it is determined that the artificial neural network should be trained on the first speech pattern. |
| 地址 |
Burlington MA US |
