VOICE PROCESSING DEVICE, METHOD, AND RECORDING MEDIUM
A voice processing device includes a calculation unit and a determination processing unit. The calculation unit calculates a first feature being a feature of an input voice signal. When a similarity between the first feature and a second feature out of one or more registered features having been registered is equal to or larger than a first threshold, the determination processing unit makes determination that the input voice signal is a voice of a first registered person out of registered persons. The first registered person corresponds to the second feature. When the similarity is equal to or larger than the first threshold and smaller than a second threshold, the determination processing unit adds the first feature to the registered features or updates the registered features with the first feature.
1 . A voice processing device comprising:
a memory in which a computer program is stored; and
a hardware processor coupled to the memory and configured to perform processing by executing the computer program, the processing including:
calculating a first feature being a feature of an input voice signal;
when a similarity between the first feature and a second feature out of one or more registered features having been registered is equal to or larger than a first threshold, making determination that the input voice signal is a voice of a first registered person out of registered persons, the first registered person corresponding to the second feature; and,
when the similarity is equal to or larger than the first threshold and smaller than a second threshold, adding the first feature to the registered features or updating the registered features with the first feature.
2 . The voice processing device according to claim 1 , wherein, in the processing, the hardware processor performs the updating of the registered features with the first feature in response to determining that the similarity is equal to or larger than the first threshold and smaller than the second threshold due to a change in voice quality of the first registered person.
3 . The voice processing device according to claim 1 , wherein the first threshold and the second threshold are each variable in setting.
4 . The voice processing device according to claim 1 , wherein, in the processing, the hardware processor
calculates a feature for each predetermined segment of the voice signal, and
performs the adding of the first feature to the registered features or the updating of the registered features with the first feature in response to determining, as to the predetermined segments, that the similarity between the feature calculated for each predetermined segment and the registered feature is equal to or larger than the first threshold and smaller than the second threshold.
5 . The voice processing device according to claim 1 , further comprising:
a speaker configured to reproduce a sound; and
a cancellation mechanism configured to cancel, from the input voice signal, a signal of the sound reproduced by the speaker.
6 . The voice processing device according to claim 1 , further comprising a user interface used for selecting a type of a mode,
wherein, in the processing, the hardware processor registers the first feature in association with a mode selected by the user interface.
7 . The voice processing device according to claim 1 , further comprising a storage device in which registered features corresponding to multiple modes are stored,
wherein, in the processing, the hardware processor
automatically determines a mode among the multiple modes, and
makes the determination that the input voice signal is a voice of the first registered person corresponding to the second feature when a similarity between the first feature and the second feature is equal to or larger than the first threshold, the second feature being a feature out of one or more registered features corresponding to the determined mode.
8 . The voice processing device according to claim 7 , wherein
the processing further includes performing facial recognition of a speaking person, and,
in the processing, the hardware processor registers the first feature in association with the determined mode when the speaking person is recognized as the registered person as a result of the facial recognition and no feature corresponding to the determined mode has been registered in the storage device.
9 . A method implemented by a computer, the method comprising:
calculating a first feature being a feature of an input voice signal;
when a similarity between the first feature and a second feature out of one or more registered features having been registered is equal to or larger than a first threshold, making determination that the input voice signal is a voice of a first registered person out of registered persons, the first registered person corresponding to the second feature; and,
when the similarity is equal to or larger than the first threshold and smaller than a second threshold, adding the first feature to the registered features or updating the registered features with the first feature.
10 . A non-transitory computer-readable recording medium on which programmed instructions are recorded, the instructions causing a computer to execute processing, the processing comprising:
calculating a first feature being a feature of an input voice signal;
when a similarity between the first feature and a second feature out of one or more registered features having been registered is equal to or larger than a first threshold, making determination that the input voice signal is a voice of a first registered person out of registered persons, the first registered person corresponding to the second feature; and,
when the similarity is equal to or larger than the first threshold and smaller than a second threshold, adding the first feature to the registered features or updating the registered features with the first feature.