公开(公告)号：US20250140240A1

公开(公告)日：2025-05-01

申请号：US19008048

申请日：2025-01-02

Applicant: GOOGLE LLC

Inventor： Yuan Yuan ,  Bibo Xu ,  Tianyu Wang ,  Anurag Jain

IPC: G10L15/08 ,  G06F40/279 ,  G06N20/00 ,  G06V40/19

Abstract: Techniques are described herein for detecting and/or enrolling (or commissioning) new “hot commands” that are useable to cause an automated assistant to perform responsive action(s) without having to be first explicitly invoked. In various implementations, an automated assistant may be transitioned from a limited listening state into a full speech recognition state in response to a trigger event. While in the full speech recognition state, the automated assistant may receive and perform speech recognition processing on a spoken command from a user to generate a textual command. The textual command may be determined to satisfy a frequency threshold in a corpus of textual commands. Consequently, data indicative of the textual command may be enrolled as a hot command. Subsequent utterance of another textual command that is semantically consistent with the textual command may trigger performance of a responsive action by the automated assistant, without requiring explicit invocation.

公开(公告)号：US11595514B2

公开(公告)日：2023-02-28

申请号：US17118387

申请日：2020-12-10

Applicant: Google LLC

Inventor： Vinh Quoc Ly ,  Raunaq Shah ,  Okan Kolak ,  Deniz Binay ,  Tianyu Wang

IPC: H04M3/42 ,  G10L15/30 ,  G10L17/00 ,  H04L61/4594 ,  G10L15/22 ,  G06F3/16 ,  G10L15/18 ,  H04L65/1096

Abstract: In some implementations, a determination that a first party has spoken a query for a voice-enabled virtual assistant during a voice call between the first party and a second party is made, in response to the determination that the first party has spoken the query for the voice-enabled virtual assistant during the voice call between the first party and the second party, the voice call between the first party and the second party is placed on hold, a determination that the voice-enabled virtual assistant has resolved the query is made, and in response to the determination that the voice-enabled virtual assistant has handled the query, the voice call between the first party and the second party is resumed from hold.

公开(公告)号：US20210368042A1

公开(公告)日：2021-11-25

申请号：US17393536

申请日：2021-08-04

Applicant: Google LLC

Inventor： Vinh Quoc Ly ,  Raunaq Shah ,  Okan Kolak ,  Deniz Binay ,  Tianyu Wang

IPC: H04M3/42 ,  G10L15/30 ,  G10L17/00 ,  G10L15/22 ,  H04L29/12 ,  G06F3/16 ,  G10L15/18 ,  H04L29/06

Abstract: In some implementations, an utterance that requests a voice call is received, the utterance is classified as spoken by a particular known user, the particular known user is determined to be associated with a personal voice number, and in response to determining that the particular known user is associated with a personal voice number, the voice call is initiated with the personal voice number.

公开(公告)号：US10791215B2

公开(公告)日：2020-09-29

申请号：US15980805

申请日：2018-05-16

Applicant: Google LLC

Inventor： Vinh Quoc Ly ,  Raunaq Shah ,  Okan Kolak ,  Deniz Binay ,  Tianyu Wang

IPC: H04M3/42 ,  G10L15/30 ,  G10L15/22 ,  G10L17/00 ,  H04L29/12 ,  G06F3/16 ,  G10L15/18 ,  H04L29/06

Abstract: In some implementations, an utterance that requests a voice call is received, the utterance is classified as spoken by a particular known user, the particular known user is determined to be associated with a personal voice number, and in response to determining that the particular known user is associated with a personal voice number, the voice call is initiated with the personal voice number.

公开(公告)号：US20180338038A1

公开(公告)日：2018-11-22

申请号：US15980822

申请日：2018-05-16

Applicant: Google LLC

Inventor： Vinh Quoc Ly ,  Raunaq Shah ,  Okan Kolak ,  Deniz Binay ,  Tianyu Wang

IPC: H04M3/42 ,  G10L17/00 ,  G10L15/22 ,  H04L29/12

CPC classification number: G10L15/30 ,  G10L15/22 ,  G10L2015/223 ,  G10L2015/227

Abstract: In some implementations, an utterance that requests a voice call is received, the utterance is classified as spoken by a particular known user, in response to classifying the utterance as spoken by the particular known user, a recipient voice number to call is determined based on contacts for the particular known user, and the voice call to the recipient voice number is initiated.

公开(公告)号：US12217740B2

公开(公告)日：2025-02-04

申请号：US18581286

申请日：2024-02-19

Applicant: GOOGLE LLC

Inventor： Yuan Yuan ,  Bibo Xu ,  Tianyu Wang ,  Anurag Jain

IPC: G10L15/08 ,  G06F40/279 ,  G06N20/00 ,  G06V40/19

Abstract: Techniques are described herein for detecting and/or enrolling (or commissioning) new “hot commands” that are useable to cause an automated assistant to perform responsive action(s) without having to be first explicitly invoked. In various implementations, an automated assistant may be transitioned from a limited listening state into a full speech recognition state in response to a trigger event. While in the full speech recognition state, the automated assistant may receive and perform speech recognition processing on a spoken command from a user to generate a textual command. The textual command may be determined to satisfy a frequency threshold in a corpus of textual commands. Consequently, data indicative of the textual command may be enrolled as a hot command. Subsequent utterance of another textual command that is semantically consistent with the textual command may trigger performance of a responsive action by the automated assistant, without requiring explicit invocation.

公开(公告)号：US11979518B2

公开(公告)日：2024-05-07

申请号：US18115441

申请日：2023-02-28

Applicant: GOOGLE LLC

Inventor： Vinh Quoc Ly ,  Raunaq Shah ,  Okan Kolak ,  Deniz Binay ,  Tianyu Wang

IPC: H04M3/00 ,  G06F3/16 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30 ,  G10L17/00 ,  H04L61/4594 ,  H04L65/1096 ,  H04M3/42

CPC classification number: H04M3/42008 ,  G06F3/167 ,  G10L15/1822 ,  G10L15/22 ,  G10L15/30 ,  G10L17/00 ,  H04L61/4594 ,  H04L65/1096 ,  H04M3/42059 ,  G10L2015/223 ,  G10L2015/225 ,  G10L2015/227

Abstract: In some implementations, an utterance that requests a voice call is received, the utterance is classified as spoken by a particular known user, the particular known user is determined to be associated with a personal voice number, and in response to determining that the particular known user is associated with a personal voice number, the voice call is initiated with the personal voice number.

公开(公告)号：US11948556B2

公开(公告)日：2024-04-02

申请号：US16973384

申请日：2019-12-11

Applicant: Google LLC

Inventor： Yuan Yuan ,  Bibo Xu ,  Tianyu Wang ,  Anurag Jain

IPC: G10L15/08 ,  G06F40/279 ,  G06N20/00 ,  G06V40/19

CPC classification number: G10L15/08 ,  G06F40/279 ,  G06N20/00 ,  G06V40/19 ,  G10L2015/088

Abstract: Techniques are described herein for detecting and/or enrolling (or commissioning) new “hot commands” that are useable to cause an automated assistant to perform responsive action(s) without having to be first explicitly invoked. In various implementations, an automated assistant may be transitioned from a limited listening state into a full speech recognition state in response to a trigger event. While in the full speech recognition state, the automated assistant may receive and perform speech recognition processing on a spoken command from a user to generate a textual command. The textual command may be determined to satisfy a frequency threshold in a corpus of textual commands Consequently, data indicative of the textual command may be enrolled as a hot command. Subsequent utterance of another textual command that is semantically consistent with the textual command may trigger performance of a responsive action by the automated assistant, without requiring explicit invocation.

公开(公告)号：US11758042B2

公开(公告)日：2023-09-12

申请号：US17252434

申请日：2018-07-17

Applicant: Google LLC

Inventor： Ahmet Onur Tekdas ,  Raunaq Shah ,  Deniz Binay ,  Tianyu Wang ,  Okan Kolak

IPC: H04M3/42 ,  G10L15/22 ,  G10L13/027

CPC classification number: H04M3/42042 ,  G10L13/027 ,  G10L15/22 ,  H04M3/4211 ,  H04M2201/39

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for indicating callers for incoming voice calls to a shared device among multiple users. The methods, systems, and apparatus include actions receiving an incoming voice call, determining a calling number and a called number from the incoming voice call, identifying a user account that corresponds to the called number, determining a contact name for the calling number based on contact entries for the user account, and providing the audible contact name for output to the device speaker.

公开(公告)号：US10911594B2

公开(公告)日：2021-02-02

申请号：US15980836

申请日：2018-05-16

Applicant: Google LLC

Inventor： Vinh Quoc Ly ,  Raunaq Shah ,  Okan Kolak ,  Deniz Binay ,  Tianyu Wang

IPC: H04M3/42 ,  G10L15/30 ,  G10L17/00 ,  G10L15/22 ,  G06F3/16 ,  G10L15/18 ,  H04L29/12 ,  H04L29/06

Abstract: In some implementations, a determination that a first party has spoken a query for a voice-enabled virtual assistant during a voice call between the first party and a second party is made, in response to the determination that the first party has spoken the query for the voice-enabled virtual assistant during the voice call between the first party and the second party, the voice call between the first party and the second party is placed on hold, a determination that the voice-enabled virtual assistant has resolved the query is made, and in response to the determination that the voice-enabled virtual assistant has handled the query, the voice call between the first party and the second party is resumed from hold.