Language translation device and language translation method
A translation method may include: continuously receiving a voice recognition result for a first-language voice from a first terminal as a first-language text; continuously displaying the received voice recognition result; acquiring a second-language translation of an ended sentence included in the displayed voice recognition result; and substituting the displayed ended sentence with the acquired translation.
1. A method of a video call between a first terminal of a first user and a second terminal of a second user, the method comprising:
receiving, by the second terminal, video call data originating from the first terminal;
displaying, on a display screen of the second terminal, a video stream comprising verbal expressions of the first user in a first language based on the video call data; and
further displaying, on the display screen of the second terminal, a sequence of visual representations for the first user's verbal expressions along with the video stream, wherein displaying the sequence of visual representations comprises:
displaying, on the display screen, a first visual representation of the first user's verbal expressions in the first language, wherein the verbal expressions comprise a first sentence and at least one additional word following the first sentence, and
subsequently, in response to detecting an end of the first sentence within the verbal expressions, displaying a second visual representation on the display screen in replacement of the first visual representation, in which a translation of the first sentence in a second language substitutes the first sentence of the first visual representation such that the second visual representation displayed on the display screen comprises the translation of the first sentence in the second language and the at least one additional word in the first language following the translation.
2. The method of claim 1 ,
wherein the verbal expressions comprise a second sentence following the first sentence, and
wherein when the second sentence is complete in the verbal expressions, a third visual representation is displayed on the display screen in replacement of the second visual representation, the third visual representation comprising a translation of the second sentence in the second language that follows the translation of the first sentence in the second language.
3. The method of claim 2 , further comprising processing the verbal expressions to determine whether the verbal expressions comprise a complete sentence in the first language.
4. The method of claim 3 , wherein processing the verbal expressions is performed by at least one of the first terminal and the second terminal.
5. The method of claim 3 , wherein processing the verbal expressions is performed by a server coordinating the video call.
6. The method of claim 3 , further comprising translating the first sentence in the first language into the translation of the first sentence in the second language when the first sentence is complete.
7. A non-transitory computer-readable recording medium having recorded thereon a program for executing the method of claim 1 .