摘要 |
Disclosed are an apparatus and a method for emotional voice synthesis. The emotional voice synthesis apparatus according to one embodiment of the present invention comprises: a word dictionary storing unit, which classifies emotional words into items including emotion class, similarity, positivity or negativity, and emotional intensity and stores the items to an emotional word dictionary; a voice DB storing unit, which classifies voices on the basis of the emotion class, similarity, positivity or negativity, and/or emotional intensity in response to the emotional words and stores the voices to a database; an emotion-inferring unit, which infers emotions matching the emotional word dictionary from each word, phrase, and/or sentence of a document including a text or an e-book; and a voice output unit, which selects and outputs a voice corresponding to the document from the database in accordance with the inferred emotion. |
申请人 |
MCS LOGIC INC.;PARK, WEI JIN;LEE, SE HWA;KIM, JONG HEE |
发明人 |
PARK, WEI JIN;LEE, SE HWA;KIM, JONG HEE |