US Patent Application 18022901. LEARNING DEVICE, METHOD, AND PROGRAM simplified abstract
Contents
LEARNING DEVICE, METHOD, AND PROGRAM
Organization Name
Inventor(s)
Takafumi Koshinaka of Tokyo (JP)
LEARNING DEVICE, METHOD, AND PROGRAM - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18022901 Titled 'LEARNING DEVICE, METHOD, AND PROGRAM'
Simplified Explanation
The abstract describes a method of learning a speaker embedding neural network. This network is trained to minimize the difference between a speaker label and the output value it produces. The network consists of an input layer that receives voice signals and an output layer that predicts the speaker. The network also includes a calculation process that determines the accuracy of the predictions based on the input features. This accuracy is then used to calculate an average and a posterior distribution, which further improves the accuracy of the predictions.
Original Abstract Submitted
Learning means generates a speaker embedding extracting neural network by learning a weighting factor so as to minimize a loss function indicating an error between a speaker label indicating a speaker of a voice signal and an output value output from an output layer, with respect to a neural network including an input layer that receives an input of the voice signal and the output layer that outputs the output value indicating a speaker of the voice signal. The speaker embedding extracting neural network includes a network that calculates a first accuracy from a feature in units of frames and calculates an average and a second accuracy of a posterior distribution from an average and an accuracy of a prior distribution and the feature and the first accuracy.
