Segment detecting device, segment detecting method, and model generating method
AssigneePreferred Networks, Inc.
InventorManabu NAGAO
Life of this patent
Estimating the term…
Abstract
A segment detecting device according to an embodiment includes at least one memory; and at least one processor. The at least one processor receives at least one of (i) an input signal including a first signal and a second signal or (ii) feature data representing one or a plurality of features of the input signal, estimates a level of the second signal by inputting the input signal or the feature data into a neural network, and determines a segment including the second signal in the input signal based on the level of the second signal.
Claims20
A segment detecting device comprising:
- at least one memory;
- and
- at least one processor configured to:
- receive at least one of (i) an input signal including a first signal and a second signal or (ii) feature data representing one or a plurality of features of the input signal,
- estimate a level of the second signal by inputting the input signal or the feature data into a neural network, and
- determine a segment including the second signal in the input signal based on the estimated level of the second signal.
A segment detecting device comprising:
- at least one memory;
- and
- at least one processor configured to:
- receive at least one of (i) an input signal including a first signal and a second signal or (ii) feature data representing one or a plurality of features of the input signal,
- estimate a ratio between a level of the second signal and a level of the first signal by inputting the input signal or the feature data into a neural network, and
- determine a segment including the second signal in the input signal based on the estimated ratio.
A segment detecting method comprising:
- receiving, by at least one processor, at least one of (i) an input signal including a first signal and a second signal or (ii) feature data representing one or a plurality of features of the input signal,
- estimating, by the at least one processor, a level of the second signal by inputting the input signal or the feature data into a neural network, and
- determining, by the at least one processor, a segment including the second signal in the input signal based on the estimated level of the second signal.
A model generating method comprising:
- acquiring, by at least one processor, teacher data including training data and correct answer data, the training data including at least one of (i) an input signal including a first signal and a second signal or (ii) feature data representing one or a plurality of features of the input signal, the correct answer data representing a level of the second signal;
- estimating, by the at least one processor, the level of the second signal by inputting the training data into a neural network;
- and
- training, by the at least one processor, the neural network based on the estimated level of the second signal and the correct answer data.
A model generating method comprising:
- acquiring, by the at least one processor, teacher data including training data and correct answer data, the training data including at least one of (i) an input signal including a first signal and a second signal or (ii) feature data representing one or a plurality of features of the input signal, the correct answer data representing a ratio between a level of the second signal and a level of the first signal;
- estimating, by the at least one processor, a ratio between the level of the second signal and the level of the first signal by inputting the training data into a neural network;
- and
- training, by the at least one processor, the neural network based on the estimated ratio and the correct answer data.
Dependencies are inferred from the claim text.