摘要 |
A video call service realizing method based on the voice recognition and an apparatus applied to the same are provided to load an image corresponding to the analysis execution result among pre-stored images, and transmit an image delivered during a video call to a terminal of the other party together with the loaded image. A voice recognition-based image providing device(110) converts a voice, formed from one of the first and second video terminal devices(100,300), into a corresponding character string through the voice dictation processing. By extracting a preset text from the character string, the image providing device loads the first image, matches it with the second image delivered to a video call session by being synchronized with the voice, and then transmits the matched result to the other terminal device through a video call network(200).
|