US 11,768,961 B2
System and method for speaker role determination and scrubbing identifying information
Yun-Cheng Ju, Bellevue, WA (US); Ashwarya Poddar, Seattle, WA (US); Royi Ronen, Tel Aviv (IL); Oron Nir, Hertzeliya (IL); Ami Turgman, Tel Aviv (IL); Andreas Stolcke, Berkeley, CA (US); and Edan Hauon, Givatayim (IL)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Oct. 28, 2021, as Appl. No. 17/513,158.
Application 17/513,158 is a continuation of application No. 16/397,738, filed on Apr. 29, 2019, granted, now 11,182,504.
Prior Publication US 2022/0050922 A1, Feb. 17, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/62 (2013.01); G06F 40/295 (2020.01); G10L 15/26 (2006.01); G10L 17/00 (2013.01); G10L 15/22 (2006.01)
CPC G06F 21/6254 (2013.01) [G06F 40/295 (2020.01); G10L 15/26 (2013.01); G10L 17/00 (2013.01); G10L 2015/228 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
at least one processor; and
a memory that stores computer program instructions that are executable by the at least one processor, the computer program instructions including:
a speech recognizer configured to generate a text-based representation of audio data;
a context determiner configured to:
identify, from within the text-based representation, first text that includes one or more of at least one key phrase of a set of key phrases, at least one word that corresponds to a symbol character, or a predetermined length of numerical characters; and
determine a contextual correspondence between the first text and second text that is associated with identifying information, in the text-based representation, for removal therefrom, the second text comprising at least one non-numeric character therein; and
a scrubber configured to replace a segment of the audio data, corresponding to an identified portion of the second text, with different audio data.