US 12,444,413 B2
Contextual spelling correction (CSC) for automatic speech recognition (ASR)
Xiaoqiang Wang, Beijing (CN); Yanqing Liu, Beijing (CN); Sheng Zhao, Beijing (CN); and Jinyu Li, Bellevue, WA (US)
Assigned to Microsoft Technology Licensing, LLC., Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Aug. 31, 2022, as Appl. No. 17/823,887.
Application 17/823,887 is a continuation of application No. PCT/CN2021/099993, filed on Jun. 15, 2021.
Prior Publication US 2022/0415314 A1, Dec. 29, 2022
Int. Cl. G10L 15/16 (2006.01); G10L 15/19 (2013.01)
CPC G10L 15/19 (2013.01) [G10L 15/16 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method of speech recognition, the method
comprising: receiving an audio stream;
performing an automatic speech recognition (ASR) process on the audio stream to produce an ASR hypothesis as a text sequence;
receiving an initial context list;
performing context filtering, wherein the context filtering comprises narrowing down the
initial context list into a preselected context list based on a user's preference, wherein the context filtering comprises adjusting contribution of a relevance weight and a preference weight, the relevance weight comprising an edit distance between the initial context list and the ASR hypothesis, and the preference weight indicating a frequency of usage of a particular context list item; and
based on at least the ASR hypothesis and the context list, performing spelling correction to produce an output text sequence, wherein performing the spelling correction further comprises:
inputting the text sequence into a text encoder;
inputting the preselected context list into a context encoder; and
passing an output of the text encoder and an output of the context encoder into a decoder.