ELECTRONIC MAIL REPLIES WITH SPEECH RECOGNITION

• US 20060195541A1
• Filed: 05/11/2006
• Published: 08/31/2006
• Est. Priority Date: 05/29/2002
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Mau, Peter K. L., Ju, Yun-cheng
• Granted Patent: US 7,280,966 B2
• Time in Patent Office: Days
• US Class Current: 709/206
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: H04L 51/00 User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
• CPC Class Codes: H04L 51/066 Format adaptation, e.g. format conversion or compression

Abstract

A method for responding to an electronic mail message with a limited input device such as a phone includes audibly rendering the question and a set of proposed answers typically provided in the electronic mail message by the sender of the electronic mail message. A language model indicative of the proposed answers is provided to a speech recognizer. The response from the user is obtained and converted to a textual response using the speech recognizer and language model. A second electronic e-mail message is then sent back to the sender. The second electronic mail message includes the textual response.

Claims

1. A computer-implemented method, comprising:

accessing a first electronic mail message with a question portion indicative of a question and a proposed answer portion having proposed answers to the question;

converting the question portion and the proposed answer portion to speech;

broadcasting the first electronic mail message to a plurality of users;

audibly rendering the question and each of the proposed answers to the plurality of users;

obtaining a language model indicative of the proposed answer portion and providing the language model to a speech recognizer;

receiving a response from at least some of the plurality of users and converting each response to a textual response using the speech recognizer and the language model; and

rendering information indicative of each textual response and how many of the plurality of users provided a response.

2. The computer-implemented method of claim 1 wherein the language model comprises a context free grammar.

3. The computer-implemented method of claim 2 wherein obtaining the language model comprises generating the context free grammar as a function of the proposed answer portion.

4. The computer-implemented method of claim 3 wherein the step of generating the context free grammar follows the step of accessing the first electronic mail message.

5. The computer-implemented method of claim 2 wherein indicators denote the question portion and the proposed answer portion.

6. The computer-implemented method of claim 4 wherein indicators comprise tags indicating a beginning and an end of the question portion and a beginning and an end of the proposed answer portion.

7. The computer-implemented method of claim 5 wherein the tags associate the question portion with the proposed answer portion.

8. The computer-implemented method of claim 7 wherein indicators denote the portion indicative of the question and the textual response.

9. The computer-implemented method of claim 8 wherein indicators comprise tags indicating a beginning and an end of the portion indicative of the question and the textual response.

10. The computer-implemented method of claim 1 wherein the first electronic mail message includes a plurality of question portions indicative of a plurality of questions and a plurality of proposed answer portions having a plurality of proposed answers to the questions.

11. A computer readable media including instructions readable by a computer which, when implemented, cause the computer to handle information by performing steps comprising:

receiving information related to an electronic mail message having a question portion indicative of a question and a proposed answer portion with proposed answers to the question;

converting the question portion and the answer portion to a signal suitable for rendering audibly;

sending the signal to a plurality of users;

obtaining a language model indicative of the proposed answer portion;

receiving information indicative of responses from at least some of the plurality of users;

converting the responses to text as a function of the language model; and

analyzing the responses to determine a number of the responses that correspond to each of the proposed answers.

12. The computer readable media of claim 11 wherein the language model comprises a context free grammar.

13. The computer readable media of claim 12 wherein obtaining the language model comprises generating the context free grammar as a function of the proposed answer portion.

14. The computer readable media of claim 11 and further comprising determining how many of the plurality of users provided a response.

15. The computer readable media of claim 11 wherein the information related to an electronic mail message includes a plurality of question portions indicative of a plurality of questions and a plurality of proposed answer portions indicative of proposed answers to the questions.

16. A computer-implemented method, comprising:

accessing a first electronic mail message with a plurality of question portions indicative of a plurality of questions and a plurality of proposed answer portions having a plurality of proposed answers to the plurality of questions;

converting each of the plurality of question portions and each of the plurality of proposed answer portions to speech;

audibly rendering each of the plurality of questions and each of the plurality of proposed answers to a user;

obtaining a language model indicative of each of the plurality of the proposed answer portions and providing each language model to a speech recognizer;

receiving a plurality of responses from the user and converting each response to a textual response using the speech recognizer and each language model; and

sending a second electronic mail message to a sender of the first electronic mail message, the second electronic mail message including each textual response.

17. The computer-implemented method of claim 16 wherein each language model comprises a context free grammar.

18. The computer-implemented method of claim 16 and further comprising:

associating each of the plurality of responses with one of the proposed answers.

19. The computer-implemented method of claim 16 and further comprising:

broadcasting the first electronic mail message to a plurality of users; and

receiving a plurality of responses from at least some of the plurality of users.

20. The computer-implemented method of claim 19 and further comprising:

analyzing the plurality of responses from the at least some of the plurality of users to determine a number of responses associated with each of the plurality of proposed answers and how many of the plurality of users provided responses.