公开(公告)号：WO2016191313A1

公开(公告)日：2016-12-01

申请号：PCT/US2016/033649

申请日：2016-05-20

Applicant: GOOGLE INC.

Inventor： SUNG, Sangsoo ,  GAO, Yuli ,  MURUGESAN, Prathab

IPC: G10L15/19 ,  G10L15/30 ,  G06F17/27 ,  G06F17/30

CPC classification number: G06F17/3097 ,  G06F17/271 ,  G06F17/274 ,  G06F17/30321 ,  G06F17/30395 ,  G06F17/30401 ,  G06F17/30684 ,  G10L15/19 ,  G10L15/30 ,  G10L17/22

Abstract: An offline semantic processor of a resource-constrained voice-enabled device such as a mobile device utilizes an offline grammar model with reduced resource requirements to parse voice-based queries received by the device. The offline grammar model may be generated from a larger and more comprehensive grammar model used by an online voice-based query processor, and the generation of the offline grammar model may be based upon query usage data collected from one or more users to enable a subset of more popular voice-based queries from the online grammar model to be incorporated into the offline grammar model. In addition, such a device may collect query usage data and upload such data to an online service to enable an updated offline grammar model to be generated and downloaded back to the device and thereby enable a dynamic update of the offline grammar model to be performed.

Abstract translation: 诸如移动设备的资源受限制的语音设备的离线语义处理器利用具有减少的资源需求的离线语法模型来解析由设备接收的基于语音的查询。 离线语法模型可以由在线基于语音的查询处理器使用的较大且更全面的语法模型生成，并且离线语法模型的生成可以基于从一个或多个用户收集的查询使用数据，以使得子集 来自在线语法模型的更流行的基于语音的查询将被并入到离线语法模型中。 此外，这样的设备可以收集查询使用数据并且将这样的数据上传到在线服务以使得更新的离线语法模型被生成并被下载回设备，从而使得能够执行离线语法模型的动态更新。

公开(公告)号：WO2016191319A1

公开(公告)日：2016-12-01

申请号：PCT/US2016/033658

申请日：2016-05-20

Applicant: GOOGLE INC.

Inventor： SUNG, Sangsoo ,  GAO, Yuli ,  MURUGESAN, Prathab

IPC: G10L15/30

CPC classification number: G10L17/22 ,  G10L15/30 ,  H04L67/42

Abstract: Data associated with a selectively offline capable voice action is locally persisted in a voice-enabled electronic device whenever such an action cannot be competed locally due to the device being offline to enable the action to later be completed after online connectivity has been restored. Synchronization with an online service and/or another electronic device, and/or retrieval of context sensitive data from an online service may be performed after online connectivity has been restored to enable the voice action to thereafter be completed.

Abstract translation: 与选择性离线功能的语音动作相关联的数据，只要这种动作由于设备脱机而无法在本地进行竞争，就会本地保留在支持语音的电子设备中，以便在线路连接恢复后，使之能够完成。 可以在恢复在线连接之后执行与在线服务和/或另一电子设备的同步，和/或从在线服务检索上下文敏感数据，以使之能够完成语音动作。

公开(公告)号：WO2016191317A1

公开(公告)日：2016-12-01

申请号：PCT/US2016/033654

申请日：2016-05-20

Applicant: GOOGLE INC.

Inventor： SUNG, Sangsoo ,  GAO, Yuli ,  MURUGESAN, Prathab

IPC: G10L15/32 ,  G10L15/30 ,  G10L15/26 ,  G06F3/16 ,  G06F17/30

CPC classification number: G06F3/167 ,  G06F17/30 ,  G06F17/30663 ,  G10L15/22 ,  G10L15/26 ,  G10L15/30 ,  G10L15/32 ,  G10L2015/223 ,  H04L67/02 ,  H04L67/10 ,  H04L67/42 ,  H04M2250/74

Abstract: Online processing of a voice input directed to a voice-enabled electronic device is selectively aborted whenever it is determined that a voice input directed to the voice-enabled electronic device can be successfully processed locally by the device. Doing so may in some instances reduce the latency of responding to a voice input.

Abstract translation: 只要确定定向到支持语音的电子设备的语音输入可以被设备本地成功地处理，则有选择地中止定向到支持语音的电子设备的语音输入的在线处理。 这样做可能会在某些情况下减少响应语音输入的延迟。

公开(公告)号：WO2016191318A1

公开(公告)日：2016-12-01

申请号：PCT/US2016/033657

申请日：2016-05-20

Applicant: GOOGLE INC.

Inventor： GAO, Yuli ,  SUNG, Sangsoo ,  MURUGESAN, Prathab

IPC: G10L15/22 ,  G10L15/065 ,  G10L15/08 ,  G10L15/18

CPC classification number: G10L15/26 ,  G10L15/065 ,  G10L15/083 ,  G10L15/1822 ,  G10L15/22 ,  G10L2015/223 ,  G10L2015/228

Abstract: A voice to text model used by a voice-enabled electronic device is dynamically and in a context-sensitive manner updated to facilitate recognition of entities that potentially may be spoken by a user in a voice input directed to the voice-enabled electronic device. The dynamic update to the voice to text model may be performed, for example, based upon processing of a first portion of a voice input, e.g., based upon detection of a particular type of voice action, and may be targeted to facilitate the recognition of entities that may occur in a later portion of the same voice input, e.g., entities that are particularly relevant to one or more parameters associated with a detected type of voice action.

Abstract translation: 由启用语音的电子设备使用的语音到文本模型是动态地并且以更新的上下文敏感方式进行，以便于识别用户在定向到支持语音的电子设备的语音输入中潜在地可以说出的实体。 语音到文本模型的动态更新可以例如基于语音输入的第一部分的处理来执行，例如基于特定类型的语音动作的检测，并且可以被定位以便于识别 可能发生在相同语音输入的较后部分中的实体，例如与与检测到的语音动作类型相关联的一个或多个参数特别相关的实体。