US 12,148,430 B2
Method, system, and computer-readable recording medium for managing text transcript and memo for audio file
Jieun Shin, Seongnam-si (KR); Gil Hwan Hwang, Seongnam-si (KR); Ye Lim Jeong, Seongnam-si (KR); Dai-Hyun Lim, Seongnam-si (KR); SuMee Lee, Seongnam-si (KR); Hyangnam Oh, Seongnam-si (KR); Junghoon Jang, Seongnam-si (KR); Namkyu Jung, Seongnam-si (KR); Geonmin Kim, Seongnam-si (KR); Deok Su Kim, Seongnam-si (KR); Hyunjin Kim, Seongnam-si (KR); Daigeun Sohn, Seongnam-si (KR); Yeon Soo Song, Seongnam-si (KR); Dongyeol Lee, Seongnam-si (KR); Jin-myoung Lee, Seongnam-si (KR); Yujin Jeon, Seongnam-si (KR); and Jongmin Choi, Seongnam-si (KR)
Assigned to NAVER CORPORATION, Seongnam-si (KR); and LINE WORKS CORP, Tokyo (JP)
Filed by NAVER CORPORATION, Seongnam-si (KR); and LINE WORKS CORP., Tokyo (JP)
Filed on Sep. 23, 2021, as Appl. No. 17/448,616.
Claims priority of application No. 10-2020-0122847 (KR), filed on Sep. 23, 2020; application No. 10-2020-0127519 (KR), filed on Sep. 29, 2020; application No. 10-2020-0133224 (KR), filed on Oct. 15, 2020; and application No. 10-2020-0137324 (KR), filed on Oct. 22, 2020.
Prior Publication US 2022/0093103 A1, Mar. 24, 2022
Int. Cl. G10L 15/26 (2006.01); G06F 40/106 (2020.01); G10L 15/08 (2006.01)
CPC G10L 15/26 (2013.01) [G06F 40/106 (2020.01); G10L 15/08 (2013.01)] 17 Claims
OG exemplary drawing
 
1. An audio recording management method executed by a computer device having at least one processor configured to execute computer-readable instructions contained in a memory, the method comprising the steps of:
creating a text transcript of an audio recording by converting speech to text;
matching and managing the text transcript and a memo generated during an utterance spoken at a specific time in recording of the audio recording by a user, wherein the memo is matched to audio of the audio recording corresponding to the specific time of the utterance spoken;
providing the text transcript in connection with the memo; and
searching in the text transcript for a word with a similar pronunciation as a search word and whose similarity to the search word is a certain percent or more by comparing the word and the search word depending on what type of smaller units the word and the search word are broken down into, wherein the type of smaller units is one of phonemes, stems, and terms.