US 12,148,423 B2
Word-level correction of speech input
Michael J. Lebeau, New York, NY (US); William J. Byrne, Davis, CA (US); John Nicholas Jitkoff, Palo Alto, CA (US); Brandon M. Ballinger, San Franciso, CA (US); and Trausti T. Kristjansson, Mountain View, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jun. 7, 2021, as Appl. No. 17/340,729.
Application 17/340,729 is a continuation of application No. 16/854,670, filed on Apr. 21, 2020, granted, now 11,037,566, issued on Jun. 15, 2021.
Application 16/854,670 is a continuation of application No. 15/849,967, filed on Dec. 21, 2017, granted, now 10,672,394, issued on Jun. 2, 2020.
Application 15/849,967 is a continuation of application No. 15/608,110, filed on May 30, 2017, granted, now 9,881,608, issued on Jan. 30, 2018.
Application 15/608,110 is a continuation of application No. 15/350,309, filed on Nov. 14, 2016, granted, now 9,711,145, issued on Jul. 18, 2017.
Application 15/350,309 is a continuation of application No. 15/045,571, filed on Feb. 17, 2016, granted, now 9,542,932, issued on Jan. 10, 2017.
Application 15/045,571 is a continuation of application No. 14/988,201, filed on Jan. 5, 2016, granted, now 9,466,287, issued on Oct. 11, 2016.
Application 14/988,201 is a continuation of application No. 14/747,306, filed on Jun. 23, 2015, granted, now 9,263,048, issued on Feb. 16, 2016.
Application 14/747,306 is a continuation of application No. 13/947,284, filed on Jul. 22, 2013, granted, now 9,087,517, issued on Jul. 21, 2015.
Application 13/947,284 is a continuation of application No. 12/913,407, filed on Oct. 27, 2010, granted, now 8,494,852, issued on Jul. 23, 2013.
Claims priority of provisional application 61/292,440, filed on Jan. 5, 2010.
Prior Publication US 2021/0295842 A1, Sep. 23, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/00 (2013.01); G06F 3/0482 (2013.01); G06F 3/04842 (2022.01); G06F 3/04886 (2022.01); G06F 40/137 (2020.01); G06F 40/166 (2020.01); G06F 40/232 (2020.01); G06F 40/284 (2020.01); G10L 15/01 (2013.01); G10L 15/22 (2006.01); G10L 15/26 (2006.01); G10L 15/30 (2013.01)
CPC G10L 15/22 (2013.01) [G06F 3/0482 (2013.01); G06F 3/04842 (2013.01); G06F 3/04886 (2013.01); G06F 40/137 (2020.01); G06F 40/166 (2020.01); G06F 40/232 (2020.01); G06F 40/284 (2020.01); G10L 15/01 (2013.01); G10L 15/26 (2013.01); G10L 15/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method when executed on data processing hardware of a server system causes the data processing hardware to perform operations comprising:
receiving audio data corresponding to an utterance;
processing the audio data to obtain a word lattice of words recognized in the audio data, each possible word having an associated speech recognition confidence score; and
transmitting, over a network, the word lattice to a computing device in communication with the data processing hardware, the computing device configured to display, on a display screen:
a transcription of the utterance including multiple words from the word lattice; and
for a respective one of the multiple words included in the transcription of the utterance, one or more alternate words from the word lattice that occur at a same particular location in the word lattice as the respective one of the multiple words.
 
11. A server system comprising:
data processing hardware; and
memory hardware in communication with the data processing hardware and storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
receiving audio data corresponding to an utterance;
processing the audio data to obtain a word lattice of words recognized in the audio data, each possible word having an associated speech recognition confidence score; and
transmitting, over a network, the word lattice to a computing device in communication with the server system, the computing device configured to display, on a display screen:
a transcription of the utterance including multiple words from the word lattice; and
for a respective one of the multiple words included in the transcription of the utterance, one or more alternate words from the word lattice that occur at a same particular location in the word lattice as the respective one of the multiple words.