Invention Grant
- Patent Title: Speech recognition using domain knowledge
-
Application No.: US14048199Application Date: 2013-10-08
-
Publication No.: US09646606B2Publication Date: 2017-05-09
- Inventor: Fuchun Peng , Ben Shahshahani , Howard Scott Roy
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google Inc.
- Current Assignee: Google Inc.
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G10L15/00
- IPC: G10L15/00 ; G10L15/08 ; G10L15/18 ; G10L15/22 ; G10L15/183

Abstract:
In some implementations, data that indicates multiple candidate transcriptions for an utterance is received. For each of the candidate transcriptions, data relating to use of the candidate transcription as a search query is received, a score that is based on the received data is provided to a trained classifier, and a classifier output for the candidate transcription is received. One or more of the candidate transcriptions may be selected based on the classifier outputs.
Public/Granted literature
- US20150012271A1 SPEECH RECOGNITION USING DOMAIN KNOWLEDGE Public/Granted day:2015-01-08
Information query