Method and system for voice based media search

• US 9,734,151 B2
• Filed: 10/31/2012
• Issued: 08/15/2017
• Est. Priority Date: 10/31/2012
• Status: Active Grant

• Current Assignee: TiVo Solutions Inc. (Adeia Inc.)
• Original Assignee: TiVo Solutions Inc. (Adeia Inc.)
• Inventors: Silverstein, Lu, Jandhyala, Srinivas, Patel, Mukesh K.
• Primary Examiner(s): Hudspeth, David
• Assistant Examiner(s): Nguyen, Timothy
• Application Number:
  US13/665,735
• Publication Number:
  US 20140122059A1
• Time in Patent Office: 1,749 Days
• Field of Search: 704 9, 704 7, 704235, 704E2102, 7042701, 704271, 704272
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

Voice-based input is used to operate a media device and/or to search for media content. Voice input is received by a media device via one or more audio input devices and is translated into a textual representation of the voice input. The textual representation of the voice input is used to search one or more cache mappings between input commands and one or more associated device actions and/or media content queries. One or more natural language processing techniques may be applied to the translated text and the resulting text may be transmitted as a query to a media search service. A media search service returns results comprising one or more content item listings and the results may be presented on a display to a user.

Claims

1. A method comprising:

sending voice input data received by a media device to a speech-to-text service;

receiving, by the media device, a textual representation of the voice input from the speech-to-text service;

generating a signature based on the entire textual representation of the voice input, wherein the signature is a hash value;

searching a set of data entries stored by the media device for a data entry matching the signature generated based on the entire textual representation of the voice input, each data entry of the set of stored data entries specifying a mapping between a signature and one or more media device actions;

updating the set of stored data entries by storing the mapping between the signature and the entire textual representation;

in response to locating a particular data entry among the set of stored data entries based on the generated signature, performing one or more particular media device actions associated with the particular stored data entry, the one or more particular media device actions including sending a media content query to a media search service;

receiving, by the media device, one or more content item listings based on the media content query;

causing display of at least a portion of the one or more content item listings;

wherein the method is performed on one or more computing devices.

2. The method of claim 1, further comprising:

causing display of at least a portion of the textual representation, wherein the textual representation comprises one or more words;

receiving input from a user indicating one or more modifications to the textual representation.

3. The method of claim 1, further comprising:

sending the textual representation of the voice input to a natural language processing service;

receiving, by the media device, a parsed representation of the textual representation of the voice input;

based on the parsed representation, filtering one or more words of the textual representation;

generating a signature based on the textual representation;

storing a cache entry in a cache comprising a mapping between the signature and the filtered textual representation.

4. The method of claim 1, further comprising:

receiving input from a user indicating a selection of one or more of the one or more content item listings;

in response to selection of one or more of the one or more content item listings, storing information representing the selection.

5. The method of claim 4, further comprising:

wherein the input from the user indicating the selection of one or more of the one or more content item listings comprises second voice input;

sending the second voice input to the speech-to-text service;

receiving, by the media device, a second textual representation of the second voice input;

determining, based on the second textual representation, a selection of one or more of the content item listings; and

causing an action associated with the one or more selected content item listings to be performed.

6. The method of claim 1, further comprising:

storing, in a buffer, audio data representing audio output generated by the media device, wherein the audio data comprises one or more temporal markers;

filtering the voice input data using the audio data based on the one or more temporal markers.

7. The method of claim 1, wherein the signature is the hash value generated using the entire textual representation as input to a hash function.

8. A non-transitory computer readable medium storing instructions which, when executed by one or more processors, cause performance of steps comprising:

sending voice input data received by a media device to a speech-to-text service;

receiving, by the media device, a textual representation of the voice input from the speech-to-text service;

generating a signature based on the entire textual representation of the voice input, wherein the signature is a hash value;

searching a set of data entries stored by the media device for a data entry matching the signature generated based on the entire textual representation of the voice input, each data entry of the set of stored data entries specifying a mapping between a signature and one or more media device actions;

updating the set of stored data entries by storing the mapping between the signature and the entire textual representation;

in response to locating a particular stored data entry based on the generated signature, performing one or more particular media device actions associated with the particular stored data entry, the one or more particular media device actions including sending a media content query to a media search service;

receiving, by the media device, one or more content item listings based on the media content query;

causing display of at least a portion of the one or more content item listings.

9. The non-transitory computer readable medium as recited in claim 8, further comprising:

causing display of at least a portion of the textual representation, wherein the textual representation comprises one or more words;

receiving from a user one or more modifications to the textual representation.

10. The non-transitory computer readable medium as recited in claim 8, further comprising:

sending the textual representation of the voice input to a natural language processing service;

receiving, by the media device, a parsed representation of the textual representation of the voice input;

based on the parsed representation, filtering one or more words of the textual representation;

generating a signature based on the textual representation;

storing a cache entry in a cache comprising a mapping between the signature and the filtered textual representation.

11. The non-transitory computer readable medium as recited in claim 8, further comprising:

receiving input from a user indicating a selection of one or more of the content item listings;

in response to selection of one or more of the content item listings, storing information representing the selection.

12. The non-transitory computer readable medium as recited in claim 11, further comprising:

wherein the input from the user indicating the selection of one or more of the one or more content item listings comprises second voice input;

sending the second voice input to the speech-to-text service;

receiving, by the media device, a second textual representation of the second voice input;

determining, based on the second textual representation, a selection of one or more of the content item listings; and

causing an action associated with the one or more selected content item listings to be performed.

13. The non-transitory computer readable medium as recited in claim 8, further comprising:

storing, in a buffer, audio data representing audio output generated by the media device, wherein the audio data comprises one or more temporal markers;

filtering the voice input data using the audio data based on the one or more temporal markers.

14. The non-transitory computer readable medium as recited in claim 8, wherein the signature is the hash value generated using the entire textual representation as input to a hash function.

15. An apparatus comprising:

a subsystem, implemented at least partially in hardware, that sends voice input data to a speech-to-text service;

a subsystem, implemented at least partially in hardware, that receives a textual representation of the voice input from the speech-to-text service;

a subsystem, implemented at least partially in hardware, that generates a signature based on the entire textual representation of the voice input, wherein the signature is a hash value;

a subsystem, implemented at least partially in hardware, that searches a set of data entries for a data entry matching the signature generated by performing the calculation based the entire textual representation of the voice input, each data entry of the set of stored data entries specifying a mapping between a signature and one or more media device actions;

a subsystem, implemented at least partially in hardware, that updates the set of stored data entries by storing the mapping between the signature and the entire textual representation;

a subsystem, implemented at least partially in hardware, that, in response to locating a particular stored data entry based on the generated signature, performing one or more particular media device actions associated with the particular stored data entry, the one or more particular media device actions including sending a media content query to a media search service;

a subsystem, implemented at least partially in hardware, that receives one or more content item listings based on the media content query.

16. The apparatus as recited in claim 15, further comprising:

a subsystem, implemented at least partially in hardware, that causes display of at least a portion of the textual representation, wherein the textual representation comprises one or more words;

a subsystem, implemented at least partially in hardware, that receives input from a user indicating one or more modifications to the textual representation.

17. The apparatus as recited in claim 15, further comprising:

a subsystem, implemented at least partially in hardware, that sends the textual representation of the voice input to a natural language processing service;

a subsystem, implemented at least partially in hardware, that receives, by the media device, a parsed representation of the textual representation of the voice input;

a subsystem, implemented at least partially in hardware, that, based on the parsed representation, filters one or more words of the textual representation;

a subsystem, implemented at least partially in hardware, that generates a signature associated with the textual representation;

a subsystem, implemented at least partially in hardware, that stores a cache entry in a cache comprising a mapping between the signature and the filtered textual representation.

18. The apparatus as recited in claim 15, further comprising:

a subsystem, implemented at least partially in hardware, that receives input from a user indicating a selection of one or more of the one or more content item listings;

a subsystem, implemented at least partially in hardware, that, in response to selection of one or more of the one or more content item listings, stores information representing the selection.

19. The apparatus as recited in claim 18, further comprising:

wherein the input from the user indicating the selection of one or more of the one or more content item listings comprises second voice input;

a subsystem, implemented at least partially in hardware, that sends the second voice input to the speech-to-text service;

a subsystem, implemented at least partially in hardware, that receives, by the media device, a second textual representation of the second voice input;

a subsystem, implemented at least partially in hardware, that determines, based on the second textual representation, a selection of one or more of the content item listings; and

a subsystem, implemented at least partially in hardware, that causes an action associated with the one or more selected content item listings to be performed.

20. The apparatus as recited in claim 15, further comprising:

a subsystem, implemented at least partially in hardware, that stores, in a buffer, audio data representing audio output generated by the media device, wherein the audio data comprises one or more temporal markers;

a subsystem, implemented at least partially in hardware, that filters the voice input data using the audio data based on the one or more temporal markers.

21. The apparatus as recited in claim 15, wherein the signature is the hash value generated using the entire textual representation as input to a hash function.