| 摘要 |
The present invention relates to a system and a method to learn words using image data and pronunciation data of a native speaker. Provided is the system to learn words using image data and pronunciation data of a native speaker, which comprises: a storage unit whereby word data, image data of words, and pronunciation images and voice waveform data of a native speaker are stored; an input unit to select and input a word; a display unit displaying word data when the learning of the word selected by a learner starts and displaying image data related to the displayed word; an audio processing unit to receive the voice of the learner when the learner pronounces the displayed word during word learning; a voice analysis module unit and a voice waveform processing unit to analyze the voice inputted through the audio processing unit, converting the voice into a waveform, and comparing/analyzing a similarity to the waveform of the pronunciation data of a native speaker for the inputted voice; a camera unit to collect images of the shapes of the mouth during word pronunciation of the learner; an image processing unit to standardize the focuses and sizes of the images of the shapes of the mouth inputted from the camera unit; and a control unit to compare/display the images of the shapes of the mouth during word pronunciation of the learner standardized through the image processing unit and the images in word pronunciation of a native speaker stored in the storage unit, display the waveform processed through the voice analysis module unit and the voice waveform processing unit and the pronunciation waveform of a native speaker stored in the storage unit, and compare the similarities between them, followed by displaying a″good″in a similarity rate of 50% or more and a″bad″in a similarity rate of less than 50%. |
