-
公开(公告)号：US11158307B1
公开(公告)日：2021-10-26
申请号：US16363814
申请日：2019-03-25
Applicant: Amazon Technologies, Inc.
Inventor： Alireza Roshan Ghias , Sean William Jewell , Chenlei Guo
Abstract: A system for handling errors during automatic speech recognition by processing a potentially defective utterance to determine an alternative, potentially successful utterance. The system processes the N-best ASR hypotheses corresponding to the defective utterance using a trained model to generate a word-level feature vector. The word-level feature vector is processed using a sequence-to-sequence architecture to determine the alternate utterance.
Search Results
1
records
(took 0.01 seconds)
筛选
AND
AND
过滤
NOT
NOT
Scan to Join
