Abstract: Provided is a lip-sync video providing apparatus for providing a video in which a voice and lip shapes are synchronized. The lip-sync video providing apparatus is configured to obtain a template video including at least one frame and depicting a target object, obtain a target voice to be used as a voice of the target object, generate a lip image corresponding to the voice for each frame of the template video by using a trained first artificial neural network, and generate lip-sync data including frame identification information of a frame in the template video, the lip image, and position information regarding the lip image in a frame in the template video.

Abstract: A method and apparatus for converting a voice of a first speaker into a voice of a second speaker by using a plurality of trained artificial neural networks are provided. The method of converting a voice feature of a voice comprises (i) generating a first audio vector corresponding to a first voice by using a first artificial neural network, (ii) generating a first text feature value corresponding to the first text by using a second artificial neural network, (iii) generating a second audio vector by removing the voice feature value of the first voice from the first audio vector by using the first text feature value and a third artificial neural network, and (iv) generating, by using the second audio vector and a voice feature value of a target voice, a second voice in which a feature of the target voice is reflected.

Abstract: A method of generating an application by using an artificial neural network model includes a data processing step of pre-processing training data, a model training step of training the artificial neural network model based on the preprocessed training data, and an application making step of receiving an input for editing one or more components included in the application and an input for setting a connection relationship between the one or more components. The one or more components include the artificial neural network model.

Abstract: A device for providing an interface for managing contact scenarios for one or more respondents may provide a first interface for inputting contact information of one or more respondents to be contacted, provide a second interface for inputting a scenario of the contact, and provide a third interface for displaying on a screen a contact simulation according to the scenario.

Abstract: A method of generating a speaker-labeled text from voice data including voices of at least two speakers includes converting the voice data into text to generate a first text, determining a speaker of each of one or more second texts obtained by dividing the first text in a predetermined unit, and providing an editing interface for displaying the one or more second texts and a speaker of each of the one or more second texts.

Abstract: A device for providing an interface for managing contact scenarios for one or more respondents may provide a first interface for inputting contact information of one or more respondents to be contacted, provide a second interface for inputting a scenario of the contact, and provide a third interface for displaying on a screen a contact simulation according to the scenario.

Abstract: Provided is a method of controlling display of a consultation session by integrating and displaying at least one consultation session managed by an individual respondent. The method includes receiving, from a server, data about the at least one consultation session to be displayed; displaying a consultation session window for each of the at least one consultation session; and displaying in a preset manner a session window of a consultation session in which details of consultation satisfy a certain condition for a consultant's intervention. The consultation session window includes a history of conversation in each of the at least one consultation session.

Abstract: A method of generating a voice for each speaker from audio content including a section in which at least two or more speakers simultaneously speak is provided. The method includes dividing the audio content into one or more single-speaker sections and one or more multi-speaker sections, determining a speaker feature value corresponding to each of the one or more single-speaker sections, generating grouping information by grouping the one or more single-speaker sections based on a similarity of the determined speaker feature value, determining a speaker feature value for each speaker by referring to the grouping information, and generating a voice of each of multiple speakers in each section from each of the one or more multi-speaker sections by using a trained artificial neural network and the speaker feature value for each individual speaker.