公开(公告)号：US10692492B2

公开(公告)日：2020-06-23

申请号：US15721486

申请日：2017-09-29

申请人： Piotr Rozen ,  Tobias Bocklet ,  Jakub Nowicki ,  Munir Georges

发明人： Piotr Rozen ,  Tobias Bocklet ,  Jakub Nowicki ,  Munir Georges

IPC分类号： G10L15/22 ,  G06N5/04 ,  G10L15/18 ,  G10L15/01 ,  G06F3/14 ,  H04W76/10 ,  G10L15/30 ,  G10L15/08 ,  G10L15/183 ,  G06F3/16 ,  G10L17/00 ,  G10L25/63 ,  G10L25/60 ,  G10L15/00

摘要： Techniques are disclosed for client-side analysis of audio samples to identify one or more characteristics associated with captured audio. The client-side analysis may then allow a user device, e.g., a smart phone, laptop computer, in-car infotainment system, and so on, to provide the one or more identified characteristics as configuration data to a voice recognition service at or shortly after connection with the same. In turn, the voice recognition service may load one or more recognition components, e.g., language models and/or application modules/engines, based on the received configuration data. Thus, latency may be reduced based on the voice recognition engine having “hints” that allow components to be loaded without necessarily having to process audio samples first. The reduction of latency may reduce processing time relative to other approaches to voice recognitions systems that exclusively perform server-side context recognition/classification.

公开(公告)号：US20190228763A1

公开(公告)日：2019-07-25

申请号：US16369926

申请日：2019-03-29

申请人： Krzysztof Czarnowski ,  Munir Georges

发明人： Krzysztof Czarnowski ,  Munir Georges

IPC分类号： G10L15/16 ,  G06N3/04 ,  G06N3/08 ,  G10L15/18 ,  G10L15/22 ,  G10L15/06

摘要： Spoken language understanding techniques include training a dynamic neural network mask relative to a static neural network using only post-deployment training data such that the mask zeroes out some of the weights of the static neural network and allows some other weights to pass through and applying a dynamic neural network corresponding to the masked static neural network to input queries to identify outputs for the queries.

公开(公告)号：US20190103100A1

公开(公告)日：2019-04-04

申请号：US15721486

申请日：2017-09-29

申请人： PIOTR ROZEN ,  TOBIAS BOCKLET ,  JAKUB NOWICKI ,  MUNIR GEORGES

发明人： PIOTR ROZEN ,  TOBIAS BOCKLET ,  JAKUB NOWICKI ,  MUNIR GEORGES

IPC分类号： G10L15/22 ,  G10L15/30 ,  G10L15/08 ,  G10L15/183

摘要： Techniques are disclosed for client-side analysis of audio samples to identify one or more characteristics associated with captured audio. The client-side analysis may then allow a user device, e.g., a smart phone, laptop computer, in-car infotainment system, and so on, to provide the one or more identified characteristics as configuration data to a voice recognition service at or shortly after connection with the same. In turn, the voice recognition service may load one or more recognition components, e.g., language models and/or application modules/engines, based on the received configuration data. Thus, latency may be reduced based on the voice recognition engine having “hints” that allow components to be loaded without necessarily having to process audio samples first. The reduction of latency may reduce processing time relative to other approaches to voice recognitions systems that exclusively perform server-side context recognition/classification.