Loading patent…
AssigneeElectronics and Telecommunications Research Institute
InventorsHoon CHUNG, Jeon Gue PARK, Sung Joo LEE, Yun Keun LEE
Estimating the term…
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.
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:
A signal processing algorithm-integrated deep neural network-based speech recognition apparatus including at least one processor and a non-volatile memory storing a code executed by the at least one processor, wherein the processor converts a signal processing algorithm for extracting a feature parameter from a speech input signal of a time domain into a signal processing deep neural network (DNN), fuses the signal processing DNN and a classification DNN, and learns a model parameter in a deep learning model in which the signal processing DNN and the classification DNN are fused.
Dependencies are inferred from the claim text.