Panasonic Intellectual Property Corporation of America

Misaki Doi

Kousuke Itakura

Takahiro Kamai

Ko Mizuno

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.

Training method of a speaker identification model based on a first language and a second language

The information processing method in the present disclosure is performed as below. At least one speech segment is detected from speech input to a speech input unit. A first feature quantity is extracted from each speech segment detected, the first feature quantity identifying a speaker whose voice is contained in the speech segment. The first feature quantity extracted is compared with each of second feature quantities stored in storage and identifying the respective voices of registered speakers who are target speakers in speaker recognition. The comparison is performed for each of consecutive speech segments, and under a predetermined condition, among the second feature quantities stored in the storage, at least one second feature quantity whose similarity with the first feature quantity is less than or equal to a threshold is deleted, thereby removing the at least one registered speaker identified by the at least one second feature quantity.

Information processing method, information processing device, and recording medium for determining registered speakers as target speakers in speaker recognition

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.

Speaker recognition device, speaker recognition method, and recording medium

A speaker recognizing method includes acquiring subject identification information that is identification information of an authentic person who the subject speaker claims to be, calculating a first feature value representing a feature value of the subject voice signal, selecting a group including pieces of the voice information associated with the subject identification information, from the first database, calculating degrees of similarity between the pieces of the voice information included in the selected group and the first feature value and a subject degree of similarity representing a degree of similarity between the voice information associated with the subject identification information, the voice information being stored in the second database, and the first feature value, calculating a rank of the subject degree of similarity in the calculated degrees of similarity, and when the rank is smaller than a given first rank, determining the subject speaker to be the authentic person.

Speaker recognizing method, speaker recognizing apparatus, recording medium recording speaker recognizing program, database making method, database making apparatus, and recording medium recording database making program

Growing community of inventors

Osaka, Japan

Misaki Doi