Multi-modal input on an electronic device

• US 9,251,791 B2
• Filed: 06/09/2014
• Issued: 02/02/2016
• Est. Priority Date: 12/23/2009
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ballinger, Brandon M., Schalkwyk, Johan, Cohen, Michael H., Byrne, William J., Hafsteinsson, Gudmundur, LeBeau, Michael J.
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US14/299,837
• Publication Number:
  US 20140288929A1
• Time in Patent Office: 603 Days
• Field of Search: 704/2, 704/9, 704/8, 704/10, 704/257, 704/235, 704/260, 704/231, 704/275, 704/277, 715/533, 715/257, 715/264, 715/234, 719/321, 381/88.14
• US Class Current: 1/1
• CPC Class Codes: G06F 3/04886 by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.

Claims

1. A computer-implemented input-method editor process comprising:

receiving, at an electronic device, a request from a user of the electronic device for an application-independent input method editor having written and spoken input capabilities, wherein the application-independent input method editor is configured to receive input for a plurality of applications executable by the electronic device;

receiving a spoken input from the user using the application-independent input method editor, wherein the spoken input corresponds to an input to an application from the plurality of applications;

determining a category for the application;

providing the spoken input and data that indicates the application category to a server, wherein the server includes a speech recognition system configured to select one or more language models to generate text based on the spoken input, wherein the one or more language models are selected based on the data that indicates the application category;

receiving text from the server, wherein the text represents a transcription of the spoken input; and

providing the text as the input to the application.

2. The process of claim 1, further comprising:

presenting a list of candidates of text representing the spoken input to the user; and

receiving a selection from the user of a candidate from the list;

wherein providing the text to the application as user input comprises providing the selection of the candidate from the list to the application.

3. The process of claim 1, further comprising:

receiving a written input from the user;

determining a language of the written input; and

providing a language indicator to the server based on the determined language indicating the language of the written input.

4. The process of claim 1, further comprising:

providing a context indicator to the server such that the speech recognition system can select a language model from a plurality of language models based on the context indicator, where the context indicator specifies a context in which the spoken input is received.

5. The process of claim 4, wherein the context indicator specifies a web form in which the spoken input is received.

6. The process of claim 5 wherein the context indicator further specifies a field in the web form in which the spoken input is received.

7. The process of claim 6, wherein the context indicator further specifies metadata associated with the field in the web form.

8. The process of claim 1, further comprising:

receiving a written input from the user in a first writing system; and

presenting one or more candidates in a second writing system based on the written input in the first writing system.

9. The process of claim 8, wherein the first writing system is Pinyin and the second writing system is Hanzi.

10. The process of claim 1, further comprising:

performing intermediate processing on the received spoken input;

wherein providing the spoken input to the server comprises providing the intermediately processed spoken input to the server.

18. The process of claim 1, further comprising:

generating a correlation between the spoken input and the application category, comprising matching one or more utterances in the spoken input to one or more stored items that are associated with the application category,

wherein the one or more language models are further selected based on the correlation.

21. The process of claim 1, wherein the one or more language models are further selected based on one or more utterances in the spoken input.

11. A system comprising:

a data processing apparatus; and

a data store coupled to the data processing apparatus, in which is stored;

an application-independent input method editor configured to receive input for a plurality of applications executable by an electronic device, the application-independent input method editor operable to;

receive spoken input from a user of the electronic device in an application of the plurality of applications;

determine a category for the application;

provide the spoken input and data that indicates the application category to a server that includes a speech recognition system configured to select one or more language models to generate text based on the spoken input, wherein the one or more language models are selected based on the data that indicates the application category;

receive text from the server, wherein the text represents a transcription of the spoken input; and

provide the text as input to the application.

12. The system of claim 11, wherein the application-independent input method editor is further operable to:

receive a written input from the user;

determine a language of the written input; and

provide a language indicator to the server based on the determined language indicating the language of the written input.

13. The system of claim 11, wherein the application-independent input method editor is further operable to:

provide a context indicator to the server such that the speech recognition system can select a language model from a plurality of language models based on the context indicator, where the context indicator specifies a context in which the spoken input is received.

14. The system of claim 11, wherein the application-independent input method editor is further operable to:

perform intermediate processing on the received spoken input;

wherein providing the spoken input to the server comprises providing the intermediately processed spoken input to the server.

19. The system of claim 11, wherein the application-independent input method editor is further operable to:

generate a correlation between the spoken input and the application category, comprising matching one or more utterances in the spoken input to one or more stored items that are associated with the application category,

wherein the one or more language models are further selected based on the correlation.

22. The system of claim 11, wherein the one or more language models are further selected based on one or more utterances in the spoken input.

15. A non-transitory computer-readable storage device encoded with instructions that, when executed by a data processing apparatus, cause the data processing apparatus to perform operations comprising:

receiving spoken input from a user of an electronic device in an application among a plurality of applications that are capable of being executed on the electronic device;

determining a category for the application;

providing the spoken input and data that indicates the application category to a server that includes a speech recognition system configured to select one or more language models to generate text based on the spoken input, wherein the one or more language models are selected based on the data that indicates the application category;

receiving text from the server, wherein the text represents a transcription of the spoken input; and

providing the text as input to the application.

16. The non-transitory computer-readable storage device of claim 15, wherein the operations further comprise:

receiving a written input from the user;

determining a language of the written input; and

providing a language indicator to the server based on the determined language indicating the language of the written input.

17. The non-transitory computer-readable storage device of claim 15, wherein the operations further comprise:

providing a context indicator to the server such that the speech recognition system can select a language model from a plurality of language models based on the context indicator, where the context indicator specifies a context in which the spoken input is received.

20. The non-transitory computer-readable storage device of claim 15, wherein the operations further comprise:

generating a correlation between the spoken input and the application category, comprising matching one or more utterances in the spoken input to one or more stored items that are associated with the application category,

wherein the one or more language models are further selected based on the correlation.

23. The non-transitory computer-readable storage device of claim 15, wherein the one or more language models are further selected based on one or more utterances in the spoken input.