Nippon Telegraph and Telephone Corporation

Taichi Asami

Takashi Nakamura

Ryo Masumura

Hirokazu Masataki

A model learning device comprises: an initial value setting part that uses a parameter of a learned first model including a neural network to set a parameter of a second model including a neural network having a same network structure as the first model; a first output probability distribution calculating part that calculates a first output probability distribution including a distribution of an output probability of each unit on an output layer, using learning features and the first model; a second output probability distribution calculating part that calculates a second output probability distribution including a distribution of an output probability of each unit on the output layer, using learning features and the second model; and a modified model update part that obtains a weighted sum of a second loss function calculated from correct information and from the second output probability distribution, and a cross entropy between the first output probability distribution and the second output probability distribution, and updates the parameter of the second model so as to reduce the weighted sum.

Model learning device, method and recording medium for learning neural network model

An acoustic model learning apparatus includes a first output probability distribution calculating part that calculates a first output probability distribution including a distribution of output probabilities of respective units of an output layer using a feature amount obtained from an acoustic signal for learning and a learned first acoustic model including a neural network, and the first output probability distribution calculating part obtains the first output probability distribution using a smoothing parameter made up of a real value greater than 0 as input so that the first output probability distribution approaches a uniform distribution as the smoothing parameter is greater, and calculates the first output probability distribution by obtaining logits of respective units of an output layer using the feature amount obtained from the acoustic signal for learning and the first acoustic model and setting a value of the smoothing parameter greater in the case where an output unit number with the greatest logit value is different from a correct unit number than in the case where the output unit number with the greatest logit value matches the correct unit number.

Growing community of inventors

Yokosuka, Japan

Taichi Asami