公开(公告)号：US20240428795A1

公开(公告)日：2024-12-26

申请号：US18828772

申请日：2024-09-09

Applicant: Rovi Guides, Inc.

Inventor： Ankur Aher ,  Sindhuja Chonat Sri ,  Aman Puniyani ,  Nishchit Mahajan

IPC: G10L15/22 ,  G06F16/635 ,  G06F16/638 ,  G06F16/683 ,  G10L15/08 ,  G10L25/51

Abstract: Systems and methods are described herein for disambiguating a voice search query that contains a command keyword by determining whether the user spoke a quotation from a content item and whether the user mimicked or approximated the way the quotation is spoken in the content item. The voice search query is transcribed into a string, and an audio signature of the voice search query is identified. Metadata of a quotation matching the string is retrieved from a database that includes audio signature information for the string as spoken within the content item. The audio signature of the voice search query is compared with the audio signature information in the metadata to determine whether the audio signature matches the audio signature information in the quotation metadata. If a match is detected, then a search result comprising an identifier of the content item from which the quotation comes is generated.

公开(公告)号：US12119001B2

公开(公告)日：2024-10-15

申请号：US18368214

申请日：2023-09-14

Applicant: Rovi Guides, Inc.

Inventor： Ankur Aher ,  Sindhuja Chonat Sri ,  Aman Puniyani ,  Nishchit Mahajan

IPC: G10L15/22 ,  G06F16/635 ,  G06F16/638 ,  G06F16/683 ,  G10L15/08 ,  G10L25/51

CPC classification number: G10L15/22 ,  G06F16/635 ,  G06F16/638 ,  G06F16/683 ,  G10L15/08 ,  G10L25/51 ,  G10L2015/088 ,  G10L2015/223

Abstract: Systems and methods are described herein for disambiguating a voice search query that contains a command keyword by determining whether the user spoke a quotation from a content item and whether the user mimicked or approximated the way the quotation is spoken in the content item. The voice search query is transcribed into a string, and an audio signature of the voice search query is identified. Metadata of a quotation matching the string is retrieved from a database that includes audio signature information for the string as spoken within the content item. The audio signature of the voice search query is compared with the audio signature information in the metadata to determine whether the audio signature matches the audio signature information in the quotation metadata. If a match is detected, then a search result comprising an identifier of the content item from which the quotation comes is generated.

公开(公告)号：US12118978B2

公开(公告)日：2024-10-15

申请号：US18387211

申请日：2023-11-06

Applicant: ROVI GUIDES, INC.

Inventor： Ankur Aher ,  Jeffry Copps Robert Jose

IPC: G10L13/06 ,  G10L13/00 ,  G10L13/02 ,  G10L13/033 ,  G10L13/08 ,  G10L15/00 ,  G10L15/10 ,  G10L15/16 ,  G10L15/18 ,  G10L15/22 ,  G10L15/26 ,  G10L25/63

CPC classification number: G10L13/0335 ,  G10L25/63 ,  G10L13/00 ,  G10L13/02 ,  G10L13/06 ,  G10L13/08 ,  G10L15/00 ,  G10L15/10 ,  G10L15/16 ,  G10L15/18 ,  G10L15/22 ,  G10L15/26

Abstract: The system provides a synthesized speech response to a voice input, based on the prosodic character of the voice input. The system receives the voice input and calculates at least one prosodic metric of the voice input. The at least one prosodic metric can be associated with a word, phrase, grouping thereof, or the entire voice input. The system also determines a response to the voice input, which may include the sequence of words that form the response. The system generates the synthesized speech response, by determining prosodic characteristics based on the response, and on the prosodic character of the voice input. The system outputs the synthesized speech response, which includes a more natural, relevant, or both answer to the call of the voice input. The prosodic character of the voice input and/or response may include pitch, note, duration, prominence, timbre, rate, and rhythm, for example.

公开(公告)号：US11842721B2

公开(公告)日：2023-12-12

申请号：US17882289

申请日：2022-08-05

Applicant: ROVI GUIDES, INC.

Inventor： Ankur Aher ,  Jeffry Copps Robert Jose

IPC: G10L13/033 ,  A63H11/00 ,  G06F40/58 ,  G10L13/10 ,  G10L13/07 ,  G10L13/08 ,  G10L25/30 ,  G10L25/63

CPC classification number: G10L13/0335 ,  G10L25/63

Abstract: The system provides a synthesized speech response to a voice input, based on the prosodic character of the voice input. The system receives the voice input and calculates at least one prosodic metric of the voice input. The at least one prosodic metric can be associated with a word, phrase, grouping thereof, or the entire voice input. The system also determines a response to the voice input, which may include the sequence of words that form the response. The system generates the synthesized speech response, by determining prosodic characteristics based on the response, and on the prosodic character of the voice input. The system outputs the synthesized speech response, which includes a more natural, relevant, or both answer to the call of the voice input. The prosodic character of the voice input and/or response may include pitch, note, duration, prominence, timbre, rate, and rhythm, for example.

公开(公告)号：US11790915B2

公开(公告)日：2023-10-17

申请号：US18118343

申请日：2023-03-07

Applicant: Rovi Guides, Inc.

Inventor： Ankur Aher ,  Sindhuja Chonat Sri ,  Aman Puniyani ,  Nishchit Mahajan

IPC: G10L15/22 ,  G06F16/638 ,  G06F16/683 ,  G06F16/635 ,  G10L15/08 ,  G10L25/51

CPC classification number: G10L15/22 ,  G06F16/635 ,  G06F16/638 ,  G06F16/683 ,  G10L15/08 ,  G10L25/51 ,  G10L2015/088 ,  G10L2015/223

Abstract: Systems and methods are described herein for disambiguating a voice search query that contains a command keyword by determining whether the user spoke a quotation from a content item and whether the user mimicked or approximated the way the quotation is spoken in the content item. The voice search query is transcribed into a string, and an audio signature of the voice search query is identified. Metadata of a quotation matching the string is retrieved from a database that includes audio signature information for the string as spoken within the content item. The audio signature of the voice search query is compared with the audio signature information in the metadata to determine whether the audio signature matches the audio signature information in the quotation metadata. If a match is detected, then a search result comprising an identifier of the content item from which the quotation comes is generated.

公开(公告)号：US11340085B2

公开(公告)日：2022-05-24

申请号：US16557925

申请日：2019-08-30

Applicant: Rovi Guides, Inc.

Inventor： Nishchit Mahajan ,  Ankur Aher

IPC: G01C21/34

Abstract: Systems and methods are disclosed herein for selecting alternate routes with fewer directions during vehicle navigation. The disclosed techniques herein determine directions from route data and direction timestamps for each of the directions. For each direction, a corresponding media asset from media assets in a playlist having a media asset duration that matches a direction duration is determined. The direction duration is the time difference between the direction timestamp and a subsequent direction timestamp.

公开(公告)号：US20210390954A1

公开(公告)日：2021-12-16

申请号：US17412924

申请日：2021-08-26

Applicant: Rovi Guides, Inc.

Inventor： Ankur Aher ,  Sindhuja Chonat Sri ,  Aman Puniyani ,  Nishchit Mahajan

IPC: G10L15/22 ,  G06F16/638 ,  G06F16/683 ,  G06F16/635 ,  G10L15/08 ,  G10L25/51

Abstract: Systems and methods are described herein for disambiguating a voice search query that contains a command keyword by determining whether the user spoke a quotation from a content item and whether the user mimicked or approximated the way the quotation is spoken in the content item. The voice search query is transcribed into a string, and an audio signature of the voice search query is identified. Metadata of a quotation matching the string is retrieved from a database that includes audio signature information for the string as spoken within the content item. The audio signature of the voice search query is compared with the audio signature information in the metadata to determine whether the audio signature matches the audio signature information in the quotation metadata. If a match is detected, then a search result comprising an identifier of the content item from which the quotation comes is generated.

公开(公告)号：US20210097977A1

公开(公告)日：2021-04-01

申请号：US16590243

申请日：2019-10-01

Applicant: Rovi Guides, Inc.

Inventor： Ankur Aher ,  Jeffry Copps Robert Jose

IPC: G10L15/02 ,  G10L15/22

Abstract: Systems and methods for determining hint words that improve the accuracy of automated speech recognition (ASR) systems. Hint words are determined in the context of a user issuing voice commands in connection with a voice interface system. Terms are initially taken from most frequently occurring terms in operation of a voice interface system. For example, most frequently occurring terms that arise in electronic search queries or received commands are selected. Certain of these terms are selected as hint words, and the selected hint words are then transmitted to an ASR system to assist in translation of speech to text.

公开(公告)号：US20240386201A1

公开(公告)日：2024-11-21

申请号：US18787947

申请日：2024-07-29

Applicant: Rovi Guides, Inc.

Inventor： Ankur Aher ,  Susanto Sen

IPC: G06F40/279 ,  G10L15/22 ,  H04L12/18

Abstract: Systems and methods are presented herein for providing a user with a notification or with access to live media on an audio/visual user entertainment system based on a user's conditional request for media content. The user may provide the condition of the request by speaking or by entering the condition of the request into an interactive interface. An identification application analyzes the elements of the user's request and generates a question. The application finds a live media stream with identifiers related to the elements and posts the generated question to a live chat forum associated with the live media stream. The application analyzes posts on the forum made by other users to determine if the condition of the user's request is met. When the application determines a post confirms the condition is met, the application generates a notification and provides the user access to the live media stream.

公开(公告)号：US11854529B2

公开(公告)日：2023-12-26

申请号：US17984479

申请日：2022-11-10

Applicant: Rovi Guides, Inc.

Inventor： Ankur Aher ,  Jeffry Copps Robert Jose

IPC: G10L15/02 ,  G10L15/22

CPC classification number: G10L15/02 ,  G10L15/22 ,  G10L2015/025 ,  G10L2015/223

Abstract: Systems and methods for determining hint words that improve the accuracy of automated speech recognition (ASR) systems. Hint words are determined in the context of a user issuing voice commands in connection with a voice interface system. Terms are initially taken from most frequently occurring terms in operation of a voice interface system. For example, most frequently occurring terms that arise in electronic search queries or received commands are selected. Certain of these terms are selected as hint words, and the selected hint words are then transmitted to an ASR system to assist in translation of speech to text.