Invention Grant
- Patent Title: Using context information with end-to-end models for speech recognition
-
Application No.: US16827937Application Date: 2020-03-24
-
Publication No.: US11545142B2Publication Date: 2023-01-03
- Inventor: Ding Zhao , Bo Li , Ruoming Pang , Tara N. Sainath , David Rybach , Deepti Bhatia , Zelin Wu
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Honigman LLP
- Agent Brett A. Krueger; Grant Griffith
- Main IPC: G10L15/183
- IPC: G10L15/183 ; G10L15/16 ; G06N20/00 ; G06K9/62 ; G06N3/08

Abstract:
A method includes receiving audio data encoding an utterance, processing, using a speech recognition model, the audio data to generate speech recognition scores for speech elements, and determining context scores for the speech elements based on context data indicating a context for the utterance. The method also includes executing, using the speech recognition scores and the context scores, a beam search decoding process to determine one or more candidate transcriptions for the utterance. The method also includes selecting a transcription for the utterance from the one or more candidate transcriptions.
Information query