- 专利标题: Machine training for native language and fluency identification
-
申请号: US15695209申请日: 2017-09-05
-
公开(公告)号: US10431203B2公开(公告)日: 2019-10-01
- 发明人: David Millen , Livy Maria Real Coelho
- 申请人: International Business Machines Corporation
- 申请人地址: US NY Armonk
- 专利权人: International Business Machines Corporation
- 当前专利权人: International Business Machines Corporation
- 当前专利权人地址: US NY Armonk
- 代理机构: Scully, Scott, Murphy & Presser, P.C.
- 代理商 Grant Johnson
- 主分类号: G10L15/06
- IPC分类号: G10L15/06 ; G06N3/08 ; G06N3/04 ; G10L15/02 ; G06F17/27 ; G10L15/16 ; G10L15/187 ; G10L15/18 ; G10L25/51 ; G10L15/26 ; G10L25/27
摘要:
Training a machine by a machine learning technique for recognizing speech utterance to determine language fluency level of a user. Native speaker recorded data and language specific dictionary of heteronyms may be retrieved. The native speaker recorded data may be parsed and the heteronyms from the native speaker recorded data may be isolated. Linguistic features from the native speaker recorded data including at least linguistic features associated with the heteronyms may be extracted, and a language dependent machine learning model is generated based on the linguistic features.