System and method for improving speech recognition accuracy using textual context

摘要: Disclosed herein are systems, methods, and computer-readable storage media for improving speech recognition accuracy using textual context. The method includes retrieving a recorded utterance, capturing text from device display associated with the spoken dialog viewed by one party to identifying words in captured that relevant utterance. further adding identified dynamic language model, recognizing utterance model. can be dialog. A time stamp assigned each word. include and/or removing model based on their respective stamps. screen scraper capture contain customer service data.