公开(公告)号：US11823659B2

公开(公告)日：2023-11-21

申请号：US16711046

申请日：2019-12-11

Applicant: Amazon Technologies, Inc.

Inventor： Julia Reinspach ,  Oleg Rokhlenko ,  Ramakanthachary Gottumukkala ,  Giovanni Clemente ,  Ankit Agrawal ,  Swayam Bhardwaj ,  Guy Michaeli ,  Vaidyanathan Puthucode Krishnamoorthy ,  Costantino Vlachos ,  Nalledath P. Vinodkrishnan ,  Shaun M. Vickers ,  Sethuraman Ramachandran ,  Charles C. Moore

IPC: G10L15/06 ,  G10L15/01 ,  G10L15/02 ,  G10L15/187 ,  G10L15/22

CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/02 ,  G10L15/187 ,  G10L15/22 ,  G10L2015/025 ,  G10L2015/0635 ,  G10L2015/223

Abstract: A request including audio data is received from a voice-enabled device. A string of phonemes present in the utterance is determined through speech recognition. At a later time, a subsequent user input corresponding to the request may be received, in which the user input is associated with one or more text keywords. The subsequent user input may be obtained in response to an active request. Alternatively, feedback may not be actively elicited, but rather collected passively. However it is obtained, the one or more keywords associated with the subsequent user input may be associated with the string of phonemes to indicate that the user is saying or mean those words when they product that string of phonemes. A user-specific speech recognition key for the user account is then updated to associate the string of phonemes with these words. A general speech recognition model can also be trained using the association.

公开(公告)号：US11544334B2

公开(公告)日：2023-01-03

申请号：US16712899

申请日：2019-12-12

Applicant: Amazon Technologies, Inc.

Inventor： Ramakanthachary Gottumukkala ,  Zachary Thomas Crowell ,  Leon Portman

IPC: G06F16/9532 ,  G06F16/9032 ,  G06N20/00 ,  G06F16/9535 ,  G06F16/9537 ,  G06F16/9538

Abstract: Techniques for natural language searches are described. In an example, a computer system receives a search associated with a computing device. Based on the search, the computer system determines first search results from a first data source and associated with a first type and second search results from a second data source and associated with a type. The computer system also determines a context associated with at least one of the computing device or a user. Based on the context, the computer system generates instructions associated with a presentation of the first search results and the second search results at a user interface of the computing device. The instructions indicate a first presentation order of the first search results and the second search results and a second presentation order of search results within the first search results. The computer system sends the instructions to the computing device.

公开(公告)号：US20210182350A1

公开(公告)日：2021-06-17

申请号：US16712899

申请日：2019-12-12

Applicant: Amazon Technologies, Inc.

Inventor： Ramakanthachary Gottumukkala ,  Zachary Thomas Crowell ,  Leon Portman

IPC: G06F16/9532 ,  G06F16/9537 ,  G06F16/9535 ,  G06F16/9538 ,  G06F16/9032 ,  G06N20/00

Abstract: Techniques for natural language searches are described. In an example, a computer system receives a search associated with a computing device. Based on the search, the computer system determines first search results from a first data source and associated with a first type and second search results from a second data source and associated with a type. The computer system also determines a context associated with at least one of the computing device or a user. Based on the context, the computer system generates instructions associated with a presentation of the first search results and the second search results at a user interface of the computing device. The instructions indicate a first presentation order of the first search results and the second search results and a second presentation order of search results within the first search results. The computer system sends the instructions to the computing device.

公开(公告)号：US11694682B1

公开(公告)日：2023-07-04

申请号：US16711043

申请日：2019-12-11

Applicant: Amazon Technologies, Inc.

Inventor： Julia Reinspach ,  Oleg Rokhlenko ,  Ramakanthachary Gottumukkala ,  Giovanni Clemente ,  Ankit Agrawal ,  Swayam Bhardwaj ,  Guy Michaeli ,  Vaidyanathan Puthucode Krishnamoorthy ,  Costantino Vlachos ,  Nalledath P. Vinodkrishnan ,  Shaun M. Vickers ,  Sethuraman Ramachandran ,  Charles C. Moore

IPC: G10L15/22 ,  G10L15/30 ,  G06F3/16 ,  G06F3/0484 ,  G06Q30/06 ,  G06F3/0481 ,  G10L15/19 ,  G10L15/18 ,  G06Q30/0601

CPC classification number: G10L15/22 ,  G06F3/0481 ,  G06F3/0484 ,  G06F3/167 ,  G06Q30/0625 ,  G10L15/1815 ,  G10L15/19 ,  G10L15/222 ,  G10L15/30 ,  G10L2015/223

Abstract: In various embodiments, a voice command is associated with a plurality of processing steps to be performed. The plurality of processing steps may include analysis of audio data using automatic speech recognition, generating and selecting a search query from the utterance text, and conducting a search of database of items using a search query. The plurality of processing steps may include additional or different steps, depending on the type of the request. In performing one or more of these processing steps, an error or ambiguity may be detected. An error or ambiguity may either halt the processing step or create more than one path of actions. A model may be used to determine if and how to request additional user input to attempt to resolve the error or ambiguity. The voice-enabled device or a second client device is then causing to output a request for the additional user input.

公开(公告)号：US20210183366A1

公开(公告)日：2021-06-17

申请号：US16711046

申请日：2019-12-11

Applicant: Amazon Technologies, Inc.

Inventor： Julia Reinspach ,  Oleg Rokhlenko ,  Ramakanthachary Gottumukkala ,  Giovanni Clemente ,  Ankit Agrawal ,  Swayam Bhardwaj ,  Guy Michaeli ,  Vaidyanathan Puthucode Krishnamoorthy ,  Costantino Vlachos ,  Nalledath P. Vinodkrishnan ,  Shaun M. Vickers ,  Sethuraman Ramachandran ,  Charles C. Moore

IPC: G10L15/06 ,  G10L15/22 ,  G10L15/02 ,  G10L15/01 ,  G10L15/187

Abstract: A request including audio data is received from a voice-enabled device. A string of phonemes present in the utterance is determined through speech recognition. At a later time, a subsequent user input corresponding to the request may be received, in which the user input is associated with one or more text keywords. The subsequent user input may be obtained in response to an active request. Alternatively, feedback may not be actively elicited, but rather collected passively. However it is obtained, the one or more keywords associated with the subsequent user input may be associated with the string of phonemes to indicate that the user is saying or mean those words when they product that string of phonemes. A user-specific speech recognition key for the user account is then updated to associate the string of phonemes with these words. A general speech recognition model can also be trained using the association.