公开(公告)号：US11763814B2

公开(公告)日：2023-09-19

申请号：US17353678

申请日：2021-06-21

申请人： Logitech Europe S.A.

发明人： Arash Salarian ,  Milos Cernak ,  Pablo Mainar ,  Jean-Michael Chardon ,  Niccolò Antonello

IPC分类号： G10L15/32 ,  G10L15/22 ,  G10L15/10

CPC分类号： G10L15/22 ,  G10L15/10 ,  G10L15/32 ,  G10L2015/223

摘要： Digitized audio command is decoded to generate audio features. An in-domain confidence score is calculated for a model trained by a limited set of peripheral device commands. An out-domain confidence score is calculated for a model trained without the peripheral device commands. The best score determines whether to process the audio locally or at a remote server. In some embodiments, a likelihood ratio (LR) is calculated of the in-domain and out-domain confidence scores. Based on the likelihood ratio, a locally decoded audio command is performed, or the audio features are sent to a remote server for processing to determine the audio command.

公开(公告)号：US20220406305A1

公开(公告)日：2022-12-22

申请号：US17353678

申请日：2021-06-21

申请人： Logitech Europe S.A.

发明人： Arash Salarian ,  Milos Cernak ,  Pablo Mainar ,  Jean-Michael Chardon ,  Niccolò Antonello

IPC分类号： G10L15/22 ,  G10L15/10

摘要： Digitized audio command is decoded to generate audio features. An in-domain confidence score is calculated for a model trained by a limited set of peripheral device commands. An out-domain confidence score is calculated for a model trained without the peripheral device commands. The best score determines whether to process the audio locally or at a remote server. In some embodiments, a likelihood ratio (LR) is calculated of the in-domain and out-domain confidence scores. Based on the likelihood ratio, a locally decoded audio command is performed, or the audio features are sent to a remote server for processing to determine the audio command.