US 12,230,276 B2
Computing systems for rapidly collecting digital witness statements and efficiently correcting transcription errors
Szymon Sikora, Cracow (PL); Jacek Doniec, Luborzyca (PL); Miroslaw Kawa, Kryspinow (PL); and Artur Ziajko, Cracow (PL)
Assigned to MOTOROLA SOLUTIONS, INC., Chicago, IL (US)
Filed by MOTOROLA SOLUTIONS, INC., Chicago, IL (US)
Filed on Apr. 6, 2022, as Appl. No. 17/658,115.
Prior Publication US 2023/0326460 A1, Oct. 12, 2023
Int. Cl. G10L 15/26 (2006.01); G06F 40/197 (2020.01); G06F 40/35 (2020.01); G10L 15/04 (2013.01); G10L 15/18 (2013.01); G10L 15/32 (2013.01); G10L 15/08 (2006.01); G10L 15/22 (2006.01)
CPC G10L 15/26 (2013.01) [G06F 40/197 (2020.01); G06F 40/35 (2020.01); G10L 15/04 (2013.01); G10L 15/1822 (2013.01); G10L 15/32 (2013.01); G10L 15/08 (2013.01); G10L 15/1815 (2013.01); G10L 2015/221 (2013.01); G10L 2015/225 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
capturing, via a microphone in communication with a computing device, an initial audio recording of an audible utterance vocalized by a user;
generating, via a voice-transcription software module, an initial digital transcription of the initial audio recording;
generating a score for a section of the initial digital transcription, wherein the score reflects a level of confidence that at least one word in the section was correctly identified by the voice-transcription software module;
detecting that the score does not satisfy a predefined condition;
rendering, on an electronic display in communication with the computing device, an initial timeline for the initial audio recording, wherein a segment of the initial timeline represents a time interval in the initial audio recording from which the section of the initial digital transcription was generated, the segment is rendered with a first fill scheme to indicate that the score does not satisfy the predefined condition, and a remainder of the initial timeline is rendered with a second fill scheme;
rendering, on the electronic display, a field that indicates textual content of the section of the initial digital transcription;
detecting that the field has been selected via an input device in communication with the computing device;
capturing, via the microphone, an additional audio recording of an additional audible utterance vocalized by the user;
generating, via the voice-transcription software module, an additional digital transcription of the additional audio recording;
rendering, on the electronic display, an additional timeline alongside the initial timeline, wherein a starting point of the additional timeline is aligned with a starting point of the segment, wherein the segment is associated with the field in that the field indicates content of the section of the initial digital transcription and the segment represents the time interval in the initial audio recording from which the section was generated; and
rendering, on the electronic display, an additional field that indicates content of the additional digital transcription.