Systems and methods for configuring an automatic translation of sign language in a video conference

A video conference system configured to perform automatic translation of sign language, the video conference system comprising

• a first endpoint communicatively coupled to a second endpoint, the first endpoint including a first processor and a first memory storing instructions that, when executed by the first processor of the first endpoint, cause the first processor to perform steps including:
• receiving, at the first endpoint of the video conference system, a request from a user to preview an entirety or a portion of a textual translation of a first message expressed in sign language before the textual translation is transmitted to the second endpoint of the video conference system;
• capturing, at the first endpoint of the video conference system, a video stream of the first message expressed in sign language by the user;
• automatically translating the video stream of the first message expressed in sign language into the textual translation of the first message;
• displaying, on a display of the first endpoint of the video conference system, the entirety or the portion of the textual translation of the first message;
• and
• if feedback is received from the user to modify the textual translation of the first message, modifying the textual translation of the first message based on the feedback and transmitting a modified version of the textual translation of the first message to the second endpoint of the video conference system;
• otherwise, if no feedback is received or if approval of the textual translation of the first message is received from the user, transmitting an unmodified version of the textual translation of the first message to the second endpoint of the video conference system;
• the second endpoint including a second processor and a second memory storing instructions that, when executed by the second processor of the second endpoint, cause the second processor to perform steps including:
• receiving at least one of a playback or linguistic characteristic for synthesizing an audio translation, wherein the playback characteristic includes at least one of a gender of a simulated speaker or a playback speed, and wherein the linguistic characteristic includes at least one of an accent of the simulated speaker, a pronunciation of words by the simulated speaker, a prosody of speech from the simulated speaker, or a choice of vocabulary by the simulated speaker;
• synthesizing the audio translation from the modified or unmodified version of the textual translation of the first message in accordance with the at least one of the playback or linguistic characteristic;
• and
• transmitting the synthesized audio translation to a speaker of the second endpoint.