US 11,893,983 B2
Adding words to a prefix tree for improving speech recognition
Masayuki Suzuki, Tokyo (JP); and Gakuto Kurata, Tokyo (JP)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jun. 23, 2021, as Appl. No. 17/304,576.
Prior Publication US 2022/0415315 A1, Dec. 29, 2022
Int. Cl. G10L 15/197 (2013.01); G10L 15/22 (2006.01); G06F 40/279 (2020.01); G10L 15/16 (2006.01); G10L 15/30 (2013.01); G10L 15/06 (2013.01); G06N 3/044 (2023.01)
CPC G10L 15/197 (2013.01) [G06F 40/279 (2020.01); G10L 15/22 (2013.01); G06N 3/044 (2023.01); G10L 15/063 (2013.01); G10L 15/16 (2013.01); G10L 15/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for improving speech recognition, the computer-implemented method comprising:
receiving, by one or more processors, a new word to add to a prefix tree;
determining, by the one or more processors, a bonus score for a first transition from a first node to a second node in the prefix tree on condition that the first transition is included in a path of at least one transition representing the new word;
determining, by the one or more processors, a hypothesis score for a hypothesis that corresponds to a speech sequence based, at least in part, on the prefix tree, wherein the hypothesis score adds the bonus score to an initial hypothesis score to determine the hypothesis score; and
responsive to a determination that the hypothesis score exceeds a threshold value, generating, by the one or more processors, an output text sequence for the speech sequence based on the hypothesis.