US 9,812,121 B2
Method of converting a text to a voice and outputting via a communications terminal
Dong-Myung Kim, Daejeon (KR); and Young-Soo Kwon, Daejeon (KR)
Assigned to LG CHEM, LTD., Seoul (KR)
Appl. No. 14/913,882
Filed by LG CHEM, LTD., Seoul (KR)
PCT Filed Aug. 5, 2015, PCT No. PCT/KR2015/008210
§ 371(c)(1), (2) Date Feb. 23, 2016,
PCT Pub. No. WO2016/021937, PCT Pub. Date Feb. 11, 2016.
Claims priority of application No. 10-2014-0101232 (KR), filed on Aug. 6, 2014; and application No. 10-2015-0110072 (KR), filed on Aug. 4, 2015.
Prior Publication US 2016/0210960 A1, Jul. 21, 2016
Int. Cl. G10L 13/00 (2006.01); G10L 13/02 (2013.01); G10L 13/04 (2013.01); H04W 4/18 (2009.01); G06F 17/30 (2006.01); G10L 13/08 (2013.01); H04W 4/12 (2009.01); H04L 29/08 (2006.01); H04M 1/725 (2006.01)
CPC G10L 13/043 (2013.01) [G06F 17/30743 (2013.01); G10L 13/08 (2013.01); H04L 67/04 (2013.01); H04M 1/72594 (2013.01); H04W 4/12 (2013.01); H04W 4/18 (2013.01); H04M 1/72552 (2013.01)] 32 Claims
OG exemplary drawing
 
1. A method of outputting a text to a voice through a communication network, the method of outputting a text to a voice comprising:
transmitting, by a transmitting terminal of a sender, first text data to a receiving terminal via said communications network;
converting, by the receiving terminal, text content of the first text data transmitted from the transmitting terminal to speech using text-to-speech technologies that depends on a voice database, wherein the voice database comprises the first text data and first voice data of the sender, and the first text data corresponds to the first voice data;
outputting the converted speech in voice characteristics of the sender,
updating the voice database by storing second voice data of the sender and second text data corresponding to the second voice data in the voice database, the second voice data is transmitted and received during a voice call between the transmitting terminal and the receiving terminal, and
quantitating a construction degree of the voice database constructed through the voice call between the transmitting terminal and the receiving terminal,
wherein the quantitating comprises quantitating the construction degree of the voice database for each text data sender by summing up a number of sentences, a number of words, and a number of syllables in the first and second voice data and the first and second text data stored in the voice database for each sentence, each word, and each syllable.