US 12,254,874 B2
False suggestion detection for user-provided content
Dirk Padfield, Seattle, WA (US); Noah Murad, Vancouver (CA); Edward Lo, Sunnyvale, CA (US); and Bryan Huh, San Jose, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Feb. 20, 2022, as Appl. No. 17/676,170.
Prior Publication US 2023/0267926 A1, Aug. 24, 2023
Int. Cl. G10L 15/187 (2013.01); G06F 40/166 (2020.01); G10L 15/02 (2006.01); G10L 15/06 (2013.01); G10L 15/22 (2006.01)
CPC G10L 15/187 (2013.01) [G06F 40/166 (2020.01); G10L 15/02 (2013.01); G10L 15/063 (2013.01); G10L 15/22 (2013.01); G10L 2015/025 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining, from an automated speech recognition (ASR) tool, an ASR transcript of at least a portion of a media content;
receiving, from a user, a suggested word for a corrected word of the ASR transcript of the media content;
obtaining features using at least the suggested word or the corrected word, wherein the features include features relating to sound similarities between the suggested word and the corrected word and a count of how many times the suggested word was received as a correction for the corrected word from different users;
inputting the features into a machine learning (ML) model to obtain a determination regarding a validity of the suggested word;
responsive to the suggested word constituting a valid suggestion, incorporating the suggested word into the ASR transcript; and
transmitting at least a portion of the ASR transcript to a user device in conjunction with at least a portion of the media content.