公开(公告)号：US11501209B2

公开(公告)日：2022-11-15

申请号：US16680656

申请日：2019-11-12

Applicant: Panasonic Intellectual Property Corporation of America

Inventor： Kousuke Itakura ,  Ko Mizuno

IPC: G10L25/18 ,  G06N20/00 ,  G06V40/20

Abstract: In a behavior identification method, surrounding sound is acquired, a feature value that is specified by a spectrum pattern included in spectrum information generated from sound made by a person performing a predetermined behavior is extracted from the sound acquired, the predetermined behavior is identified by the feature value, and information indicating the predetermined behavior identified is output.

公开(公告)号：US11315550B2

公开(公告)日：2022-04-26

申请号：US16682661

申请日：2019-11-13

Applicant: Panasonic Intellectual Property Corporation of America

Inventor： Kousuke Itakura ,  Ko Mizuno ,  Misaki Doi

IPC: G10L15/14 ,  G06F17/18 ,  G10L25/51 ,  G10L25/30

Abstract: A speaker recognition device according to the present disclosure includes: an acoustic feature calculator that calculates, from utterance data indicating a voice of an obtained utterance, acoustic feature of the voice of the utterance; a statistic calculator that calculates an utterance data statistic from the calculated acoustic feature; a speaker feature extractor that extracts speaker feature of a speaker of the utterance data from the calculated utterance data statistic using a deep neural network (DNN); a similarity calculator that calculates a similarity between the extracted speaker feature and pre-stored speaker feature of at least one registered speaker; and a speaker recognizer that recognizes the speaker of the utterance data based on the calculated similarity.

公开(公告)号：US11580989B2

公开(公告)日：2023-02-14

申请号：US16996408

申请日：2020-08-18

Applicant: Panasonic Intellectual Property Corporation of America

Inventor： Misaki Doi ,  Takahiro Kamai ,  Kousuke Itakura

IPC: G10L17/04 ,  G10L17/02 ,  G10L17/18 ,  G10L21/003 ,  G10L15/16 ,  G10L15/06

Abstract: A training method of training a speaker identification model which receives voice data as an input and outputs speaker identification information for identifying a speaker of an utterance included in the voice data is provided. The training method includes: performing voice quality conversion of first voice data of a first speaker to generate second voice data of a second speaker; and performing training of the speaker identification model using, as training data, the first voice data and the second voice data.

公开(公告)号：US11222641B2

公开(公告)日：2022-01-11

申请号：US16576170

申请日：2019-09-19

Applicant: Panasonic Intellectual Property Corporation of America

Inventor： Kousuke Itakura

IPC: G10L17/06 ,  G06N3/08 ,  G10L17/04 ,  G06N3/04 ,  G10L17/18 ,  G10L17/00 ,  G10L17/20 ,  G10L17/02

Abstract: A speaker recognition device includes: a feature calculator that calculates two or more acoustic features of a voice of an utterance obtained; a similarity calculator that calculates two or more similarities, each being a similarity between one of one or more speaker-specific features of a target speaker for recognition and one of the two or more acoustic features; a combination unit that combines the two or more similarities to obtain a combined value; and a determiner that determines whether a speaker of the utterance is the target speaker based on the combined value. Here, (i) at least two of the two or more acoustic features have different properties, (ii) at least two of the two or more similarities have different properties, or (iii) at least two of the two or more acoustic features have different properties and at least two of the two or more similarities have different properties.