发明名称 |
SIGNAL PROCESSING ALGORITHM-INTEGRATED DEEP NEURAL NETWORK-BASED SPEECH RECOGNITION APPARATUS AND LEARNING METHOD THEREOF |
摘要 |
Provided are a signal processing algorithm-integrated deep neural network (DNN)-based speech recognition apparatus and a learning method thereof. A model parameter learning method in a deep neural network (DNN)-based speech recognition apparatus implementable by a computer includes converting a signal processing algorithm for extracting a feature parameter from a speech input signal of a time domain into signal processing deep neural network (DNN), fusing the signal processing DNN and a classification DNN, and learning a model parameter in a deep learning model in which the signal processing DNN and the classification DNN are fused. |
申请公布号 |
US2016078863(A1) |
申请公布日期 |
2016.03.17 |
申请号 |
US201514737907 |
申请日期 |
2015.06.12 |
申请人 |
ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE |
发明人 |
CHUNG Hoon;PARK Jeon Gue;LEE Sung Joo;LEE Yun Keun |
分类号 |
G10L15/16 |
主分类号 |
G10L15/16 |
代理机构 |
|
代理人 |
|
主权项 |
1. A model parameter learning method in a deep neural network (DNN)-based speech recognition apparatus implementable by a computer, the model parameter learning method comprising:
converting a signal processing algorithm for extracting a feature parameter from a speech input signal of a time domain into signal processing deep neural network (DNN); fusing the signal processing DNN and a classification DNN; and learning a model parameter in a deep learning model in which the signal processing DNN and the classification DNN are fused. |
地址 |
Daejeon KR |