公开(公告)号：US20190073997A1

公开(公告)日：2019-03-07

申请号：US15817379

申请日：2017-11-20

申请人： International Business Machines Corporation

发明人： David Millen ,  Livy Maria Real Coelho

IPC分类号： G10L15/06 ,  G10L15/18 ,  G10L15/187 ,  G10L15/16 ,  G06F17/27 ,  G10L15/02 ,  G06N3/04 ,  G06N3/08

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.

公开(公告)号：US10431203B2

公开(公告)日：2019-10-01

申请号：US15695209

申请日：2017-09-05

申请人： International Business Machines Corporation

发明人： David Millen ,  Livy Maria Real Coelho

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.

公开(公告)号：US20190073996A1

公开(公告)日：2019-03-07

申请号：US15695209

申请日：2017-09-05

申请人： International Business Machines Corporation

发明人： David Millen ,  Livy Maria Real Coelho

IPC分类号： G10L15/06 ,  G06N3/08 ,  G06N3/04 ,  G10L15/02 ,  G10L15/18 ,  G06F17/27 ,  G10L15/16 ,  G10L15/187

CPC分类号： G10L15/063 ,  G06F17/2715 ,  G06F17/2735 ,  G06F17/274 ,  G06N3/04 ,  G06N3/08 ,  G10L15/02 ,  G10L15/16 ,  G10L15/1822 ,  G10L15/187 ,  G10L15/26 ,  G10L25/27 ,  G10L25/51 ,  G10L2015/025

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.