METHOD AND SYSTEM FOR PROVIDING SPEECH-TO-TEXT RECORDING GENERATED BASED ON INFORMATION AFTER SPEECH RECORDING

• Main Authors: CHOI JONGMIN, KIM GEONMIN, KIM HYUNJIN, KANG MYUNG HUN, JEON YUJIN, BAEK SEOL KI, JUNG NAMKYU, SONG YEON SOO, LEE CHAN KYU, KIM DEOK SU, CHOI JIN HYEON, LEE SUMEE, YI JAEHONG, JANG JUNGHOON, LEE JIN MYOUNG, SOHN DAIGEUN, JANG DONG HAN, HEO HEE SOO, SHIN JIEUN, JEONG YE LIM, KWON YOUNGKI, CHOI JONG PHIL, LEE PAUL, LIM DAI HYUN, LEE DONGYEOL, AN GIBAEK, LEE BONG JIN, HWANG GILHWAN
• Format: Patent
• Language: English; Korean
• Published: 14.10.2022
• Subjects: ACOUSTICS; CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The present disclosure relates to a method for providing a generated speech record based on the information after speech recording, performed by at least one computing device. The method for providing the speech record comprises: a step of receiving the information associated with the speech data after speech recording; a step of receiving a speech-to-text conversion request for the speech data; and a step of outputting the generated speech record, in response to the speech-to-text conversion request, based on at least one part of the speech included in the speech data and the information associated with the speech data received after the speech recording. Therefore, the present invention is capable of providing a text wherein the speech data is more accurately converted. 본 개시는 적어도 하나의 컴퓨팅 장치에 의해 수행되는, 음성 녹음 후의 정보에 기초하여 생성된 음성 기록을 제공하는 방법에 관한 것이다. 음성 기록을 제공하는 방법은, 음성 녹음 이후에 음성 데이터와 연관된 정보를 수신하는 단계, 음성 데이터에 대한 음성-텍스트 변환 요청을 수신하는 단계 및 음성-텍스트 변환 요청에 응답하여, 음성 데이터에 포함된 적어도 일부의 음성 및 음성 녹음 이후에 수신된 음성 데이터와 연관된 정보에 기초하여 생성된 음성 기록을 출력하는 단계를 포함한다.