Proactive completion of input fields for automated voice enablement of a web page

• US 8,543,404 B2
• Filed: 04/07/2008
• Issued: 09/24/2013
• Est. Priority Date: 04/07/2008
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Moore, Victor S., Nusbickel, Wendi L.
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US12/099,036
• Publication Number:
  US 20090254347A1
• Time in Patent Office: 1,996 Days
• Field of Search: 704/270.1, 704/266, 704/254, 704/260, 704/9, 704/275, 704/270, 704/257, 704/235, 704/231, 715/215, 715/825, 715/700, 709/217, 709/206, 379/88.17, 379/88.01, 379/67.1
• US Class Current: 704/270
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

Embodiments of the present invention provide a method and computer program product for the proactive completion of input fields for automated voice enablement of a Web page. In an embodiment of the invention, a method for proactively completing empty input fields for voice enabling a Web page can be provided. The method can include receiving speech input for an input field in a Web page and inserting a textual equivalent to the speech input into the input field in a Web page. The method further can include locating an empty input field remaining in the Web page and generating a speech grammar for the input field based upon permitted terms in a core attribute of the empty input field and prompting for speech input for the input field. Finally, the method can include posting the received speech input and the grammar to an automatic speech recognition (ASR) engine and inserting a textual equivalent to the speech input provided by the ASR engine into the empty input field.

Claims

1. A method for proactively completing empty input fields for voice enabling a Web page, the method comprising:

locating an empty input field in the Web page;

determining whether or not a speech grammar exists for the empty input field; and

if it is determined that the speech grammar does not exist for the empty input field;

generating a speech grammar for the empty input field based upon permitted terms in a core attribute of the empty input field to obtain a generated speech grammar and prompting for first speech input for the empty input field,

receiving the first speech input for the empty input field in response to the prompting,

posting the received first speech input and the generated speech grammar to an automatic speech recognition (ASR) engine, and

inserting a textual equivalent to the received first speech input into the empty input field, wherein the textual equivalent is provided by the ASR engine.

2. The method of claim 1, wherein generating the speech grammar for the empty input field comprises generating the speech grammar for the empty input field based upon permitted terms in a title attribute of the empty input field.

3. The method of claim 1, wherein generating the speech grammar for the empty input field comprises generating the speech grammar based upon permitted terms for a corresponding grammar listed in a core attribute of the empty input field and a prefix for the permitted terms.

4. The method of claim 1, wherein generating the speech grammar for the empty input field comprises generating the speech grammar based upon permitted terms for a corresponding grammar listed in a core attribute of the empty input field and a semantic indicator for the permitted terms.

5. The method of claim 1, wherein generating the speech grammar for the empty input field comprises generating the speech grammar for each empty input field in the Web page, wherein the speech grammar generated for each one of the empty input fields is based upon permitted terms in a core attribute of the one of the empty input fields.

6. The method of claim 1, wherein posting the received first speech input and the generated grammar to the ASR comprises posting the received first speech input and the generated grammar to a communicatively coupled remote representational state transfer compliant ASR engine.

7. The method of claim 1, wherein:

if it is determined that the speech grammar exists for the empty input field, the method further comprises;

loading the existing speech grammar and prompting for the first speech input for the empty input field,

receiving the first speech input for the empty input field in response to the prompting,

posting the received first speech input and the existing speech grammar to the ASR engine, and

inserting a textual equivalent to the received first speech input into the empty input field, wherein the textual equivalent is provided by the ASR engine.

8. The method of claim 1, further comprising:

receiving second speech input for an input field in the Web page and inserting a textual equivalent to the second speech input into the input field,

wherein locating the empty input field in the Web page comprises locating a remaining empty input field in the Web page in response to receiving the second speech input.

9. A computer program product comprising a computer usable medium embodying computer usable program code that when executed by a processor performs a method for proactively completing empty fields for voice enabling a Web page, the method comprising:

locating an empty input field in the Web page;

determining whether or not a speech grammar exists for the empty input field; and

if it is determined that the speech grammar does not exist for the empty input field;

generating a speech grammar for the empty input field based upon permitted terms in a core attribute of the empty input field to obtain a generated speech grammar and prompting for first speech input for the empty input field;

receiving the first speech input for the empty input field in response to the prompting,

posting the received first speech input and the speech grammar to an automatic speech recognition (ASR) engine; and

inserting a textual equivalent to the received first speech input into the empty input field, wherein the textual equivalent is provided by the ASR engine.

10. The computer program product of claim 9, wherein generating the speech grammar for the empty input field comprises generating the speech grammar based upon permitted terms in a title attribute of the empty input field.

11. The computer program product of claim 9, wherein generating the speech grammar for the empty input field comprises generating the speech grammar based upon permitted terms for a corresponding grammar listed in a core attribute of the empty input field and a prefix for the permitted terms.

12. The computer program product of claim 9, wherein generating the speech grammar for the empty input field comprises generating the speech grammar based upon permitted terms for a corresponding grammar listed in a core attribute of the empty input field and a semantic indicator for the permitted terms.

13. The computer program product of claim 9, wherein generating a speech grammar for the empty input field comprises generating a speech grammar for each empty input field in the Web page based upon terms in a core attribute of the each empty input field.

14. The computer program product of claim 9, wherein posting the received first speech input and the grammar to the ASR engine comprises posting the received first speech input and the generated grammar to a communicatively coupled remote representational state transfer (REST) compliant ASR engine.

15. The computer program product of claim 9, wherein:

if it is determined that the speech grammar exists for the empty input field, the method further comprises;

loading the existing speech grammar and prompting for the first speech input for the empty input field,

receiving the first speech input for the empty input field in response to the prompting,

posting the received first speech input and the existing speech grammar to the ASR engine, and

inserting a textual equivalent to the received first speech input into the empty input field, wherein the textual equivalent is provided by the ASR engine.

16. The computer program product of claim 9, wherein the method further comprises:

receiving second speech input for an input field in the Web page and inserting a textual equivalent to the second speech input into the input field,

wherein locating the empty input field in the Web page comprises locating a remaining empty input field in the Web page in response to receiving the second speech input.

17. A system for proactively completing empty input fields of a Web page, the system comprising:

at least one processor configured to execute a method comprising;

locating an empty input field remaining in the Web page;

determining whether or not a speech grammar exists for the empty input field;

if it is determined that the speech grammar does not exist for the empty input field;

generating the speech grammar for the empty input field based upon permitted terms in a core attribute of the empty input field;

prompting for first speech input for the empty input field;

receiving the first speech input for the empty input field in response to the prompting;

posting the first speech input and the generated speech grammar for the empty input field to an automatic speech recognition (ASR) engine; and

inserting a textual equivalent to the first speech input into the empty input field, wherein the textual equivalent is provided by the ASR engine.

18. The system of claim 17, wherein generating the speech grammar for the empty input field comprises generating the speech grammar based upon permitted terms in a title attribute of the empty input field and a prefix for the permitted terms.

19. The system of claim 17, wherein:

if it is determined that the speech grammar exists for the empty input field, the method further comprises;

loading the existing speech grammar and prompting for the first speech input for the empty input field,

receiving the first speech input for the empty input field in response to the prompting,

posting the received first speech input and the existing speech grammar to the ASR engine, and

inserting a textual equivalent to the received first speech input into the empty input field, wherein the textual equivalent is provided by the ASR engine.

20. The system of claim 17, wherein the method further comprises:

receiving second speech input for an input field in the Web page and inserting a textual equivalent to the second speech input into the input field,

wherein locating the empty input field in the Web page comprises locating a remaining empty input field in the Web page in response to receiving the second speech input.