公开(公告)号：US20170147558A1

公开(公告)日：2017-05-25

申请号：US15192055

申请日：2016-06-24

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jeong Se KIM ,  Sang Hun KIM ,  Seung YUN

IPC: G06F17/28 ,  H04M1/725 ,  G06F17/27

CPC classification number: G06F17/289 ,  G06F17/275 ,  G06F17/2854 ,  H04M1/7255

Abstract: Provided is a method for interpretation and translation accomplished by an interpretation and translation apparatus of a user through interfacing with an interpretation and translation apparatus of the other party. The method includes: automatically setting a translation target language which enables to communicate with the other party based on a message from the interpretation and translation apparatus of the other party by using a communication connection in a network; receiving input information of a use language of the user; calling a translator corresponding to the translation target language to transmit a result obtained by translating the input information into the translation target language to the interpretation and translation apparatus of the other party; and outputting received data from the interpretation and translation apparatus of the other party or outputting the result obtained by translating the received data into the use language of the user by using the translator.

公开(公告)号：US20140195226A1

公开(公告)日：2014-07-10

申请号：US13902057

申请日：2013-05-24

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung YUN ,  Sanghun KIM ,  Jeong Se KIM ,  Soo-jong LEE ,  Ki Hyun KIM

IPC: G10L15/01

CPC classification number: G10L15/01 ,  G10L2015/225

Abstract: A method of correcting errors in a speech recognition system includes a process of searching a speech recognition error-answer pair DB based on a sound model for a first candidate answer group for a speech recognition error, a process of searching a word relationship information DB for a second candidate answer group for the speech recognition error, a process of searching a user error correction information DB for a third candidate answer group for the speech recognition error, a process of searching a domain articulation pattern DB and a proper noun DB for a fourth candidate answer group for the speech recognition error, and a process of aligning candidate answers within each of the retrieved candidate answer groups and displaying the aligned candidate answers.

Abstract translation: 一种校正语音识别系统中的错误的方法包括：基于用于语音识别错误的第一候选答案组的声音模型搜索语音识别错误 - 答复对DB的过程，搜索词关系信息DB的处理 用于语音识别错误的第二候选答案组，搜索用于语音识别错误的第三候选答案组的用户错误校正信息DB的处理，搜索域关节模式DB和专用名词DB的处理，用于第四 用于语音识别错误的候选答案组，以及在每个所检索的候选答案组内对准候选答案并显示对齐的候选答案的处理。

公开(公告)号：US20170255616A1

公开(公告)日：2017-09-07

申请号：US15214215

申请日：2016-07-19

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Seung YUN ,  Ki Hyun KIM ,  Sang Hun KIM ,  Yun Young KIM ,  Jeong Se KIM ,  Min Kyu LEE ,  Soo Jong LEE ,  Young Jik LEE ,  Mu Yeol CHOI

IPC: G06F17/28 ,  G10L25/24 ,  G10L25/75 ,  G10L13/033 ,  G10L13/06

CPC classification number: G06F17/2872 ,  G06F17/289 ,  G10L13/0335 ,  G10L13/06 ,  G10L15/26 ,  G10L25/03 ,  G10L25/24 ,  G10L25/48 ,  G10L25/75

Abstract: Provided are an automatic interpretation system and method for generating a synthetic sound having characteristics similar to those of an original speaker's voice. The automatic interpretation system for generating a synthetic sound having characteristics similar to those of an original speaker's voice includes a speech recognition module configured to generate text data by performing speech recognition for an original speech signal of an original speaker and extract at least one piece of characteristic information among pitch information, vocal intensity information, speech speed information, and vocal tract characteristic information of the original speech, an automatic translation module configured to generate a synthesis-target translation by translating the text data, and a speech synthesis module configured to generate a synthetic sound of the synthesis-target translation.