-
公开(公告)号：US11657804B2
公开(公告)日：2023-05-23
申请号：US17090716
申请日：2020-11-05
Applicant: Amazon Technologies, Inc.
Inventor： Rohit Prasad , Kenneth John Basye , Spyridon Matsoukas , Rajiv Ramachandran , Shiv Naga Prasad Vitaladevuni , Bjorn Hoffmeister
CPC classification number: G10L15/18 , G10L15/08 , G10L15/30 , G10L2015/088
Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
-
公开(公告)号：US10102845B1
公开(公告)日：2018-10-16
申请号：US13776594
申请日：2013-02-25
Applicant: Amazon Technologies, Inc.
Inventor： Weam Abu Zaki , Ying Shi , Rajiv Ramachandran
IPC: G10L15/00
Abstract: Features are disclosed for determining a definition or value of a nonstandard term. A user utterance may be processed into one or more candidate transcriptions. An interpretation of the utterance can be generated from the transcriptions. If the transcription includes a word, phrase, or term that is not recognized or is used in a nonstandard way, one or more data stores may be queried regarding the proper value or definition of the term. If a definition or value is not available in the data stores, the user may be prompted to provide one. The user-supplied definition can be saved for future use, and may be used as a general definition of the term for other users.
-
公开(公告)号：US20210134276A1
公开(公告)日：2021-05-06
申请号：US17090716
申请日：2020-11-05
Applicant: Amazon Technologies, Inc.
Inventor： Rohit Prasad , Kenneth John Basye , Spyridon Matsoukas , Rajiv Ramachandran , Shiv Naga Prasad Vitaladevuni , Bjorn Hoffmeister
Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
-
公开(公告)号：US10460719B1
公开(公告)日：2019-10-29
申请号：US15925397
申请日：2018-03-19
Applicant: Amazon Technologies, Inc.
Inventor： Gilles Jean Roger Belin , Charles S. Rogers, III , Robert David Owen , Jeffrey Penrod Adams , Rajiv Ramachandran , Gregory Michael Hart
Abstract: An interactive system may be implemented in part by an audio device located within a user environment, which may accept speech commands from a user and may also interact with the user by means of generated speech. In order to improve performance of the interactive system, a user may use a separate device, such as a personal computer or mobile device, to access a graphical user interface that lists details of historical speech interactions. The graphical user interface may be configured to allow the user to provide feedback and/or corrections regarding the details of specific interactions.
-
公开(公告)号：US20180012593A1
公开(公告)日：2018-01-11
申请号：US15641169
申请日：2017-07-03
Applicant: Amazon Technologies, Inc.
Inventor： Rohit Prasad , Kenneth John Basye , Spyridon Matsoukas , Rajiv Ramachandran , Shiv Naga Prasad Vitaladevuni , Bjorn Hoffmeister
IPC: G10L15/18
CPC classification number: G10L15/18 , G10L15/08 , G10L15/30 , G10L2015/088
Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
-
Patent Agency Ranking
公开(公告)号：US09565260B2
公开(公告)日：2017-02-07
申请号：US14792459
申请日：2015-07-06
Applicant: Amazon Technologies, Inc.
Inventor： Gregory B. Roth , James E. Scharf, Jr. , Rajiv Ramachandran , Anders Samuelsson , Keith A. Carlson
IPC: G06F15/173 , H04L29/08 , G06F11/25 , H04L12/911 , G06F11/30 , G06F11/34 , G06F11/14 , G06F17/40
CPC classification number: H04L67/16 , G06F11/1438 , G06F11/25 , G06F11/3006 , G06F11/3051 , G06F11/3086 , G06F11/3442 , G06F11/3457 , G06F17/40 , G06F2201/815 , G06F2201/875 , H04L47/827
Abstract: Methods and apparatus for an account state simulation service for cloud computing environments are disclosed. A system includes a plurality of service managers coordinating respective distributed network-accessible services, and a metadata manager. The metadata manager receives an account state change simulation request, indicating (a) an initial account state of a client account and (b) a collection of operations to be simulated. The metadata manager generates a response to the account change state simulation request, comprising at least one of (a) a representation of an expected end state of the client account reachable as a result of performing the collection of operations (b) an indication of an expected failure of a particular operation of the collection of operations or (c) an estimate of an expected billing amount associated with an implementation of the collection of operations.
Abstract translation: 公开了用于云计算环境的帐户状态模拟服务的方法和装置。 系统包括协调各个分布式网络可访问服务的多个服务管理器和元数据管理器。 元数据管理器接收帐户状态改变模拟请求，指示（a）客户帐户的初始帐户状态，以及（b）要模拟的操作的集合。 所述元数据管理器产生对所述帐户改变状态模拟请求的响应，所述响应包括以下中的至少一个：（a）作为执行操作收集的结果可访问的所述客户帐户的预期结束状态的表示（b） 预期收集操作的特定操作失败或（c）与执行操作集合相关联的预期计费金额的估计。
-
公开(公告)号：US12008983B1
公开(公告)日：2024-06-11
申请号：US17731968
申请日：2022-04-28
Applicant: Amazon Technologies, Inc.
Inventor： Gilles Jean Roger Belin , Charles S. Rogers, III , Robert David Owen , Jeffrey Penrod Adams , Rajiv Ramachandran , Gregory Michael Hart
CPC classification number: G10L15/00 , G10L15/22 , G10L2015/221 , G10L15/26
Abstract: An interactive system may be implemented in part by an audio device located within a user environment, which may accept speech commands from a user and may also interact with the user by means of generated speech. In order to improve performance of the interactive system, a user may use a separate device, such as a personal computer or mobile device, to access a graphical user interface that lists details of historical speech interactions. The graphical user interface may be configured to allow the user to provide feedback and/or corrections regarding the details of specific interactions.
-
公开(公告)号：US11990119B1
公开(公告)日：2024-05-21
申请号：US17195127
申请日：2021-03-08
Applicant: Amazon Technologies, Inc.
Inventor： Gilles Jean Roger Belin , Charles S. Rogers, III , Robert David Owen , Jeffrey Penrod Adams , Rajiv Ramachandran , Gregory Michael Hart
CPC classification number: G10L15/00 , G10L15/22 , G10L15/07 , G10L2015/221 , G10L15/26
Abstract: An interactive system may be implemented in part by an audio device located within a user environment, which may accept speech commands from a user and may also interact with the user by means of generated speech. In order to improve performance of the interactive system, a user may use a separate device, such as a personal computer or mobile device, to access a graphical user interface that lists details of historical speech interactions. The graphical user interface may be configured to allow the user to provide feedback and/or corrections regarding the details of specific interactions.
-
公开(公告)号：US10950220B1
公开(公告)日：2021-03-16
申请号：US16664459
申请日：2019-10-25
Applicant: Amazon Technologies, Inc.
Inventor： Gilles Jean Roger Belin , Charles S. Rogers, III , Robert David Owen , Jeffrey Penrod Adams , Rajiv Ramachandran , Gregory Michael Hart
Abstract: An interactive system may be implemented in part by an audio device located within a user environment, which may accept speech commands from a user and may also interact with the user by means of generated speech. In order to improve performance of the interactive system, a user may use a separate device, such as a personal computer or mobile device, to access a graphical user interface that lists details of historical speech interactions. The graphical user interface may be configured to allow the user to provide feedback and/or corrections regarding the details of specific interactions.
-
公开(公告)号：US10832662B2
公开(公告)日：2020-11-10
申请号：US15641169
申请日：2017-07-03
Applicant: Amazon Technologies, Inc.
Inventor： Rohit Prasad , Kenneth John Basye , Spyridon Matsoukas , Rajiv Ramachandran , Shiv Naga Prasad Vitaladevuni , Bjorn Hoffmeister
Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.018 seconds)
