Invention Application
- Patent Title: Multi-Task Learning for End-To-End Automated Speech Recognition Confidence and Deletion Estimation
-
Application No.: US17643826Application Date: 2021-12-11
-
Publication No.: US20220310080A1Publication Date: 2022-09-29
- Inventor: David Qiu , Yanzhang He , Yu Zhang , Qiujia Li , Liangliang Cao , Ian McGraw
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Main IPC: G10L15/197
- IPC: G10L15/197 ; G10L15/06 ; G10L15/22 ; G10L15/02 ; G10L15/16 ; G10L15/30 ; G10L15/32 ; G10L15/04 ; G06N3/08

Abstract:
A method including receiving a speech recognition result corresponding to a transcription of an utterance spoken by a user. For each sub-word unit in a sequence of hypothesized sub-word units of the speech recognition result, using a confidence estimation module to: obtain a respective confidence embedding associated with the corresponding output step when the corresponding sub-word unit was output from the first speech recognizer; generate a confidence feature vector; generate an acoustic context vector; and generate a respective confidence output score for the corresponding sub-word unit based on the confidence feature vector and the acoustic feature vector received as input by the output layer of the confidence estimation module. The method also includes determining, based on the respective confidence output score generated for each sub-word unit in the sequence of hypothesized sub-word units, an utterance-level confidence score for the transcription of the utterance.
Information query