公开(公告)号：US20220366911A1

公开(公告)日：2022-11-17

申请号：US17337804

申请日：2021-06-03

Applicant: GOOGLE LLC

Inventor： Victor Carbune ,  Krishna Sapkota ,  Behshad Behzadi ,  Julia Proskurnia ,  Jacopo Sannazzaro Natta ,  Justin Lu ,  Magali Boizot-Roche ,  Márius Sajgalík ,  Nicolo D'Ercole ,  Zaheed Sabur ,  Luv Kothari

IPC: G10L15/26 ,  G10L15/22

Abstract: Implementations described herein relate to an application and/or automated assistant that can identify arrangement operations to perform for arranging text during speech-to-text operations—without a user having to expressly identify the arrangement operations. In some instances, a user that is dictating a document (e.g., an email, a text message, etc.) can provide a spoken utterance to an application in order to incorporate textual content. However, in some of these instances, certain corresponding arrangements are needed for the textual content in the document. The textual content that is derived from the spoken utterance can be arranged by the application based on an intent, vocalization features, and/or contextual features associated with the spoken utterance and/or a type of the application associated with the document, without the user expressly identifying the corresponding arrangements. In this way, the application can infer content arrangement operations from a spoken utterance that only specifies the textual content.

公开(公告)号：US11482217B2

公开(公告)日：2022-10-25

申请号：US16621540

申请日：2019-05-31

Applicant: Google LLC

Inventor： Michael Golikov ,  Zaheed Sabur ,  Denis Burakov ,  Behshad Behzadi ,  Sergey Nazarov ,  Daniel Cotting ,  Mario Bertschler ,  Lucas Mirelmann ,  Steve Cheng ,  Bohdan Vlasyuk ,  Jonathan Lee ,  Lucia Terrenghi ,  Adrian Zumbrunnen

IPC: G10L15/22 ,  G01D21/02 ,  G06F3/16 ,  G10L15/06 ,  G10L15/18 ,  G10L15/183 ,  G10L25/78

Abstract: Implementations can reduce the time required to obtain responses from an automated assistant by, for example, obviating the need to provide an explicit invocation to the automated assistant, such as by saying a hot-word/phrase or performing a specific user input, prior to speaking a command or query. In addition, the automated assistant can optionally receive, understand, and/or respond to the command or query without communicating with a server, thereby further reducing the time in which a response can be provided. Implementations only selectively initiate on-device speech recognition responsive to determining one or more condition(s) are satisfied. Further, in some implementations, on-device NLU, on-device fulfillment, and/or resulting execution occur only responsive to determining, based on recognized text form the on-device speech recognition, that such further processing should occur. Thus, through selective activation of on-device speech processing, and/or selective activation of on-device NLU and/or on-device fulfillment, various client device resources are conserved.

公开(公告)号：US20220253277A1

公开(公告)日：2022-08-11

申请号：US17619414

申请日：2019-12-13

Applicant: GOOGLE LLC

Inventor： Srikanth Pandiri ,  Luv Kothari ,  Behshad Behzadi ,  Zaheed Sabur ,  Domenico Carbotta ,  Akshay Kannan ,  Qi Wang ,  Gokay Baris Gultekin ,  Angana Ghosh ,  Xu Liu ,  Yang Lu ,  Steve Cheng

IPC: G06F3/16 ,  G06F3/0481 ,  G06F40/174 ,  G10L15/26 ,  G06F3/0484 ,  G06F3/04886 ,  G06F40/30 ,  G06F40/143 ,  G06F40/117 ,  G10L15/22

Abstract: Implementations set forth herein relate to an automated assistant that can selectively determine whether to incorporate a verbatim interpretation of portions spoken utterances into an entry field and/or incorporate synonymous content into the entry field. For instance, a user can be accessing an interface that provides an entry field (e.g., address field) for receiving user input. In order to provide input for entry field, the user can select the entry field and/or access a GUI keyboard to initialize an automated assistant for assisting with filling the entry field. Should the user provide a spoken utterance, the user can elect to provide a spoken utterance that embodies the intended input (e.g., an actual address) or a reference to the intended input (e.g., a name). In response to the spoken utterance, the automated assistant can fill the entry field with the intended input without necessitating further input from the user.

公开(公告)号：US11120083B1

公开(公告)日：2021-09-14

申请号：US16683856

申请日：2019-11-14

Applicant: Google LLC

Inventor： Michal Jastrzebski ,  Aurelien Boffy ,  Gokhan H. Bakir ,  Behshad Behzadi ,  Marcin M. Nowak-Przygodzki

IPC: G06F16/9032 ,  G06F16/25

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing contextual information to a user. In one aspect, a method includes receiving, from a user device, a query-independent request for contextual information relevant to an active resource displayed in an application environment on the user device, generating multiple queries from displayed content from the resource, determining a quality score for each of the multiple queries, selecting one or more of the multiple queries based on their respective quality scores, and providing, to the user device for each of the selected one or more queries, a respective user interface element for display with the active resource, wherein each user interface element includes contextual information regarding the respective query and includes the respective query.

公开(公告)号：US11048995B2

公开(公告)日：2021-06-29

申请号：US15847341

申请日：2017-12-19

Applicant: Google LLC

Inventor： Yariv Adan ,  Vladimir Vuskovic ,  Behshad Behzadi

IPC: G06N3/00 ,  G06Q10/06 ,  G10L15/22 ,  G06Q10/02 ,  G06F3/16 ,  G06F16/332 ,  G10L13/00 ,  H04M3/493

Abstract: An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; identifying, based on the utterance, a task to be performed by the computational assistant; responsive to determining, by the computational assistant, that complete performance of the task will take more than a threshold amount of time, outputting, for playback by one or more speakers operably connected to the computing device, synthesized voice data that informs a user of the computing device that complete performance of the task will not be immediate; and performing, by the computational assistant, the task.

公开(公告)号：US10387437B2

公开(公告)日：2019-08-20

申请号：US15406409

申请日：2017-01-13

Applicant: Google LLC

Inventor： Marcin M. Nowak-Przygodzki ,  Behshad Behzadi

IPC: G06F17/30 ,  G06F16/2457 ,  G06F16/14 ,  G06F16/245 ,  G06F16/242 ,  G06F16/332 ,  G06F16/9535 ,  G06F16/2453

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a search query from a user during a user session; obtaining a plurality of prior search queries by the user received during the user session; generating a plurality of candidate query rewrites, wherein the candidate query rewrites are derived from the search query and the plurality of prior search queries by the user; scoring each candidate query rewrite, wherein scoring each candidate rewrite includes determining a quality of each candidate query rewrite based on an analysis of search results responsive to the candidate query rewrite; selecting a candidate query rewrite having a score that satisfies a threshold value; and providing search results responsive to the selected candidate query rewrite.

公开(公告)号：US20190179846A1

公开(公告)日：2019-06-13

申请号：US16272469

申请日：2019-02-11

Applicant: Google LLC

Inventor： Alexander Taboriskiy ,  Emmanuel Mogenet ,  Oliver Heckmann ,  Matsvei Zhdanovich ,  Gokhan Hasan Bakir ,  Behshad Behzadi ,  Karoly Csalogany

IPC: G06F16/438 ,  G06F16/432 ,  H04N21/4722 ,  H04N21/422 ,  G06F16/48

Abstract: Methods, systems, and media for processing queries relating to presented media content are provided. In some implementations, a method comprises: receiving a request to associate with a media playback device that is presenting media content to a user of the mobile device, wherein a mobile application executing on the mobile device and a media application executing on the media playback device exchange media playback information; activating a microphone associated with the mobile device to receive ambient sounds in response to associating with the media playback device; converting the received ambient sounds to one or more text inputs; determining whether the text inputs include a trigger term that corresponds to a request to initiate a query relating to the presented media content and the query; in response to determining that the trigger term has been included in the text inputs, determining the media playback information from the media application that includes timing information corresponding to when during the presentation of the media content the query was received and media content identification information; causing a search to be performed that includes the query, the timing information, and the media content identification information; obtaining a search result that is responsive to the query; and presenting at least a portion of the search result to the query on a mobile display associated with the mobile device.

公开(公告)号：US20190132265A1

公开(公告)日：2019-05-02

申请号：US15833454

申请日：2017-12-06

Applicant: Google LLC

Inventor： Marcin Nowak-Przygodzki ,  Jan Lamecki ,  Behshad Behzadi

IPC: H04L12/58 ,  H04L12/18 ,  G10L15/22 ,  G10L15/18

Abstract: Techniques are described related to enabling automated assistants to enter into a “conference mode” in which they can “participate” in meetings between multiple human participants and perform various functions described herein. In various implementations, an automated assistant implemented at least in part on conference computing device(s) may be set to a conference mode in which the automated assistant performs speech-to-text processing on multiple distinct spoken utterances, provided by multiple meeting participants, without requiring explicit invocation prior to each utterance. The automated assistant may perform semantic processing on first text generated from the speech-to-text processing of one or more of the spoken utterances, and generate, based on the semantic processing, data that is pertinent to the first text. The data may be output to the participants at conference computing device(s). The automated assistant may later determine that the meeting has concluded, and may be set to a non-conference mode.

公开(公告)号：US20250140243A1

公开(公告)日：2025-05-01

申请号：US19011243

申请日：2025-01-06

Applicant: GOOGLE LLC

Inventor： Marcin M. Nowak-Przygodzki ,  Nathan David Howard ,  Gabor Simko ,  Andrei Giurgiu ,  Behshad Behzadi

IPC: G10L15/18 ,  G06F16/9032 ,  G10L15/07 ,  G10L15/08 ,  G10L15/22 ,  G10L25/51

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting a continued conversation are disclosed. In one aspect, a method includes the actions of receiving first audio data of a first utterance. The actions further include obtaining a first transcription of the first utterance. The actions further include receiving second audio data of a second utterance. The actions further include obtaining a second transcription of the second utterance. The actions further include determining whether the second utterance includes a query directed to a query processing system based on analysis of the second transcription and the first transcription or a response to the first query. The actions further include configuring the data routing component to provide the second transcription of the second utterance to the query processing system as a second query or bypass routing the second transcription.

公开(公告)号：US12265560B2

公开(公告)日：2025-04-01

申请号：US18141172

申请日：2023-04-28

Applicant: GOOGLE LLC

Inventor： Vladimir Vuskovic ,  Joseph Lange ,  Behshad Behzadi ,  Marcin M. Nowak-Przygodzki

IPC: G06F16/00 ,  G06F16/332 ,  G06F16/3329 ,  G06F16/3332 ,  G06F16/334 ,  G06F16/3349

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating subqueries from a query. In one aspect, a method includes obtaining a query, generating a set of two subqueries from the query, where the set includes a first subquery and a second subquery, determining a quality score for the set of two subqueries, determining whether the quality score for the set of two subqueries satisfies a quality threshold, and in response to determining that the quality score for the set of two subqueries satisfies the quality threshold, providing a first response to the first subquery that is responsive to a first operation that receives the first subquery as input and providing a second response to the second subquery that is responsive to a second operation that receives the second subquery as input.