-
公开(公告)号：US20220215857A1
公开(公告)日：2022-07-07
申请号：US17531316
申请日：2021-11-19
Inventor： Jeong Uk BANG , Seung YUN , Sang Hun KIM , Min Kyu LEE , Joon Gyu MAENG
Abstract: Provided is a method of performing automatic interpretation based on speaker separation by a user terminal, the method including: receiving a first speech signal including at least one of a user speech of a user and a user surrounding speech around the user from an automatic interpretation service providing terminal, separating the first speech signal into speaker-specific speech signals, performing interpretation on the speaker-specific speech signals in a language selected by the user on the basis of an interpretation mode, and providing a second speech signal generated as a result of the interpretation to at least one of a counterpart terminal and the automatic interpretation service providing terminal according to the interpretation mode.
-
公开(公告)号：US20240420682A1
公开(公告)日：2024-12-19
申请号：US18585204
申请日：2024-02-23
Inventor： Seung Hi KIM , Jeong Uk BANG , Seung YUN
Abstract: The present disclosure relates to a method and device for improving the performance of an AI model that uses voice recognition results as text input. A method of training an AI model according to an embodiment of the present disclosure may include: generating first time information on a plurality of words included in a voice and transcription, using a first learning sample including the voice and the transcription; generating second time information by adding a pre-configured delay time to the first time information; generating a modified transcription based on an end time of a last word among the plurality of words and the second time information; and performing training of the AI model based on a second training sample including the voice and the modified transcription.
-
Search Results
2
records
(took 0.013 seconds)
