Neural network-based acoustic model with softening target-layer

A computer program product for training a neural network-based (NN-based) acoustic model, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

• receiving, by the processor, the neural network-based (NN-based) acoustic model, trained by a one-hot scheme and having an input layer, a set of middle layers, and an original output layer, at least each of the middle layers subsequent to a first one of the middle layers having trained parameters;
• stacking, by the processor, a new output layer on the original output layer of the NN-based acoustic model to form a new NN-based acoustic model, the new output layer having a same size as the original output layer;
• and
• retraining, by the processor, only the new output layer and the original output layer of the new NN-based acoustic model in the one-hot scheme, with the trained parameters of middle layers subsequent to at least the first one of the middle layers being fixed.

A computer processing system for training a neural network-based (NN-based) acoustic model, comprising:

• a memory for storing program code;
• and
• a processor, operatively coupled to the memory, for running the program code to
• receive the neural network-based (NN-based) acoustic model, trained by a one-hot scheme and having an input layer, a set of middle layers, and an original output layer, at least each of the middle layers subsequent to a first one of the middle layers having trained parameters;
• stack a new output layer on the original output layer of the NN-based acoustic model to form a new NN-based acoustic model, the new output layer having a same size as the original output layer;
• and
• retrain only the new output layer and the original output layer of the new NN-based acoustic model in the one-hot scheme, with the trained parameters of middle layers subsequent to at least the first one of the middle layers being fixed.