公开(公告)号：US20220405478A1

公开(公告)日：2022-12-22

申请号：US17774460

申请日：2019-11-04

Applicant: Google LLC

Inventor： Tal Cohen ,  Tal Snir ,  Sivan Eiger ,  Zahi Akiva ,  Gadi Ben Amram ,  Ran Dahan ,  Sasha Goldshtein ,  Yossi Matias ,  Shoji Ogura

IPC: G06F40/295 ,  G10L15/197 ,  G06V20/40 ,  G06V40/10 ,  G06F3/0488 ,  G06V40/20 ,  G06F16/783

Abstract: Implementations are provided for automatically mining corpus(es) of electronic video files for video clips that contain spoken utterances that are suitable usage examples to accompany or compliment dictionary definitions. These video clips may then be associated with target n-grams in a searchable database, such as a database underlying an online dictionary. In various implementations, a set of candidate video clips in which a target n-gram is uttered in a target context may be identified from a corpus of electronic video files. For each candidate video clip of the set, pre-existing manual subtitles associated with the candidate video clip may be compared to text generated based on speech recognition processing of an audio portion of the candidate video clip. Based at least in part on the comparing, a measure of suitability as a dictionary usage example may be calculated for the candidate video clip.

公开(公告)号：US12197868B2

公开(公告)日：2025-01-14

申请号：US17774460

申请日：2019-11-04

Applicant: Google LLC

Inventor： Tal Cohen ,  Tal Snir ,  Sivan Eiger ,  Zahi Akiva ,  Gadi Ben Amram ,  Ran Dahan ,  Sasha Goldshtein ,  Yossi Matias ,  Shoji Ogura

IPC: G10L15/20 ,  G06F3/0488 ,  G06F16/783 ,  G06F40/295 ,  G06V20/40 ,  G06V40/10 ,  G06V40/20 ,  G10L15/197

Abstract: Implementations are provided for automatically mining corpus(es) of electronic video files for video clips that contain spoken utterances that are suitable usage examples to accompany or compliment dictionary definitions. These video clips may then be associated with target n-grams in a searchable database, such as a database underlying an online dictionary. In various implementations, a set of candidate video clips in which a target n-gram is uttered in a target context may be identified from a corpus of electronic video files. For each candidate video clip of the set, pre-existing manual subtitles associated with the candidate video clip may be compared to text generated based on speech recognition processing of an audio portion of the candidate video clip. Based at least in part on the comparing, a measure of suitability as a dictionary usage example may be calculated for the candidate video clip.