METHOD FOR PROVIDING FOREIGN LANGUAGE PHONICS TRAINING SERVICE BASED ON FEEDBACK FOR EACH PHONEME USING SPEECH RECOGNITION ENGINE

摘要

The present invention is related to a method for providing a foreign language phonics training service and provides a method for providing a foreign language phonics training service based on a feedback for each phoneme using a voice recognition engine. A service providing server first presents phonemes used in a training target language, provides a phonics training service with respect to a plurality of words including a corresponding phoneme for each phoneme, and adopts configurations for transmitting a moving picture on the mouth shapes for pronouncing a corresponding word and offering a feedback for each detailed phoneme. Thereby, the present invention enables a trainee to finely correct a foreign language pronunciation corresponding to each phoneme, enhances sensitivity to the sounds in the foreign language which is not well recognized to the trainee because of an influence of the sounds in the mother language as the trainee gets familiar with an oral structure when the foreign language is sounded or pronounced, enhances a foreign language listening capability by enabling the trainee to recognize a difference among the phonemes of the foreign language that is ambiguous to discriminate, arouse a trainee's interest and strengthens a motive for a pronunciation practice. Additionally, the present invention makes the service providing server store a score for each phoneme set at each step, and provides an accumulated score for each phoneme to a trainee's terminal, information on the phonemes of which pronunciation by the trainee is good and weak and information on a variation of the accumulated score for each phoneme, thereby enabling the trainee to practice more intensively pronouncing the weak phonemes and to finely correct the pronunciation and intuitively show the effects of the pronunciation practice. The present invention also includes more a phonics training step with respect to word groups which causes prolonged sounds by coupling two or more words, thereby enhancing the fluency of speaking and listening capabilities of the foreign language made by the prolonged sounds. [Reference numerals] (S100) Step of transmitting phonemes used in a training target language to a user terminal and receiving selectively one phoneme from the user terminal; (S200) Step of transmitting a plurality of words, including the phoneme selectively received in step S100, to the user terminal and transmitting a moving picture on the mouth shapes for pronouncing one among the words; (S300) Step of recording a user voice pronounced for the word transmitted as the moving picture in step S200 and receiving the user voice from the user terminal; (S400) Step of providing a total score, resulted from addition of the score on each phoneme set for the transmitted user voice, to the user terminal; (S500) Step of performing the same steps as S100 to S400 for other phonemes and words not passing the steps of S100 to S400 among the phonemes of the S100 and the words of the S200; (S600) Step of providing the accumulated score, resulted from accumulation of the score for each phoneme in the steps of S400 and S500, to the user terminal