Provided are a method and device for recognizing a speaker by using a resonator. The method of recognizing the speaker includes receiving a plurality of electrical signals corresponding to a speech of the speaker from a plurality of resonators having different resonance bands; obtaining a difference of magnitudes of the plurality of electrical signals; and recognizing the speaker based on the difference of magnitudes of the plurality of electrical signals.

Provided are a method and device for recognizing a speaker by using a resonator. The method of recognizing the speaker includes receiving a plurality of electrical signals corresponding to a speech of the speaker from a plurality of resonators having different resonance bands; obtaining a difference of magnitudes of the plurality of electrical signals; and recognizing the speaker based on the difference of magnitudes of the plurality of electrical signals.

Disclosed herein are systems, methods, and tangible computer readable-media for detecting synthetic speaker verification. The method comprises receiving a plurality of speech samples of the same word or phrase for verification, comparing each of the plurality of speech samples to each other, denying verification if the plurality of speech samples demonstrate little variance over time or are the same, and verifying the plurality of speech samples if the plurality of speech samples demonstrates sufficient variance over time. One embodiment further adds that each of the plurality of speech samples is collected at different times or in different contexts. In other embodiments, variance is based on a pre-determined threshold or the threshold for variance is adjusted based on a need for authentication certainty. In another embodiment, if the initial comparison is inconclusive, additional speech samples are received.

Disclosed herein are systems, methods, and tangible computer readable-media for detecting synthetic speaker verification. The method comprises receiving a plurality of speech samples of the same word or phrase for verification, comparing each of the plurality of speech samples to each other, denying verification if the plurality of speech samples demonstrate little variance over time or are the same, and verifying the plurality of speech samples if the plurality of speech samples demonstrates sufficient variance over time. One embodiment further adds that each of the plurality of speech samples is collected at different times or in different contexts. In other embodiments, variance is based on a pre-determined threshold or the threshold for variance is adjusted based on a need for authentication certainty. In another embodiment, if the initial comparison is inconclusive, additional speech samples are received.

A method and system is provided for estimating clean speech parameters from noisy speech parameters. The method is performed by acquiring speech signals, estimating noise from the acquired speech signals, computing speech features from the acquired speech signals, estimating model parameters from the computed speech features and estimating clean parameters from the estimated noise and the estimated model parameters.

A method for generating voice dictionary is disclosed which makes it possible to improve the accuracy of speaker identification. A method according to an aspect of the present disclosure includes: acquiring voices of a plurality of unspecified speakers; acquiring noise in a predetermined place; superimposing the noise onto the voices of the plurality of unspecified speakers; and generating, on the basis of the features of the voices of the plurality of unspecified speakers, unspecified speaker voice dictionary that is used for generating personal voice dictionary for identifying a target speaker.

A method for generating voice dictionary is disclosed which makes it possible to improve the accuracy of speaker identification. A method according to an aspect of the present disclosure includes: acquiring voices of a plurality of unspecified speakers; acquiring noise in a predetermined place; superimposing the noise onto the voices of the plurality of unspecified speakers; and generating, on the basis of the features of the voices of the plurality of unspecified speakers, unspecified speaker voice dictionary that is used for generating personal voice dictionary for identifying a target speaker.

An electronic apparatus is disclosed. The apparatus includes a memory configured to store at least one pre-registered voiceprint and a first voiceprint cluster including the at least one pre-registered voiceprint, and a processor configured to, based on a user recognition command being received, obtain information of time at which the user recognition command is received, change the at least one pre-registered voiceprint included in the first voiceprint cluster based on the obtained information of time, generate a second voiceprint cluster based on the at least one changed voiceprint, and based on a user's utterance being received, perform user recognition with respect to the received user's utterance based on the first voiceprint cluster and the second voiceprint cluster.

Embodiments provide methods and systems for generating domain-specific text summary. Method performed by processor includes receiving request to generate text summary of textual content from user device of user and applying pre-trained language generation model over textual content for encoding textual content into word embedding vectors. Method includes predicting current word of the text summary, by iteratively performing: generating first probability distribution of first set of words using first decoder based on word embedding vectors, generating second probability distribution of second set of words using second decoder based on word embedding vectors, and ensembling first and second probability distributions using configurable weight parameter for determining current word. First probability distribution indicates selection probability of each word being selected as current word. Method includes providing custom reward score as feedback to second decoder based on custom reward model and modifying second probability distribution of words for text summary based on feedback.

Presented are a combined learning method and device using a transformed loss function and feature enhancement based on a deep neural network for speaker recognition that is robust in a noisy environment. A combined learning method using a transformed loss function and feature enhancement based on a deep neural network, according to one embodiment, can comprise the steps of: learning a feature enhancement model based on a deep neural network; learning a speaker feature vector extraction model based on the deep neural network; connecting an output layer of the feature enhancement model with an input layer of the speaker feature vector extraction model; and considering the connected feature enhancement model and speaker feature vector extraction model as one mode and performing combined learning for additional learning.