US 11,676,577 B2
Speech processing
Petar Aleksic, Jersey City, NJ (US); and Benjamin Paul Hillson Haynor, New York, NY (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Sep. 9, 2021, as Appl. No. 17/447,282.
Application 17/447,282 is a continuation of application No. 16/696,111, filed on Nov. 26, 2019, granted, now 11,138,968.
Claims priority of provisional application 62/773,361, filed on Nov. 30, 2018.
Prior Publication US 2021/0398519 A1, Dec. 23, 2021
Int. Cl. G06F 40/30 (2020.01); G10L 15/00 (2013.01); G10L 15/07 (2013.01); G10L 15/24 (2013.01); G10L 15/06 (2013.01); G06F 40/45 (2020.01); G10L 15/187 (2013.01); G10L 15/197 (2013.01)
CPC G10L 15/063 (2013.01) [G06F 40/45 (2020.01); G10L 15/005 (2013.01); G10L 15/187 (2013.01); G10L 15/197 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method when executed on data processing hardware causes the data processing hardware to perform operations comprising:
receiving transcriptions of utterances in a source language that were received by computing devices operating in a particular domain;
adapting, using the received transcriptions of utterances in the source language, for use by a digital assistant system that operates in the particular domain, a speech recognizer for a target language to increase a likelihood that the speech recognizer generates transcriptions that include common words or phrases identified for the particular domain, wherein the digital assistant system does not have any access to training data in the target language;
receiving audio data corresponding to an utterance spoken by a user in the target language, the utterance directed toward the digital assistant operating in the particular domain; and
generating, using the adapted speech recognizer, a transcription of the utterance spoken by the user in the target language.