Invention Grant
- Patent Title: Improving custom keyword spotting system accuracy with text-to-speech-based data augmentation
-
Application No.: US17626629Application Date: 2020-06-12
-
Publication No.: US12159627B2Publication Date: 2024-12-03
- Inventor: Yao Tian , Yuija Xiao , Edward Lin , Lei He , Hui Zhu
- Applicant: Microsoft Technology Licensing, LLC
- Applicant Address: US WA Redmond
- Assignee: Microsoft Technology Licensing, LLC
- Current Assignee: Microsoft Technology Licensing, LLC
- Current Assignee Address: US WA Redmond
- Agency: Schwegman Lundberg & Woessner, P.A.
- Priority: CN201910783303.8 20190823
- International Application: PCT/US2020/037339 WO 20200612
- International Announcement: WO2021/040842 WO 20210304
- Main IPC: G10L15/16
- IPC: G10L15/16 ; G06F40/166 ; G06F40/279 ; G06F40/30 ; G10L13/02 ; G10L15/18 ; G10L15/22 ; G10L15/08
Abstract:
The present disclosure provides methods and apparatus for optimizing a keyword spotting system. A set of utterance texts including a given keyword may be generated. A set of speech signals corresponding to the set of utterance texts may be synthesized. An acoustic model in the keyword spotting system may be optimized with at least a part of speech signals in the set of speech signals and utterance texts in the set of utterance texts corresponding to the at least a part of speech signals.
Public/Granted literature
- US20220262352A1 Improving custom keyword spotting system accuracy with text-to-speech-based data augmentation Public/Granted day:2022-08-18
Information query
