Verbal labels for electronic messages

• US 7,627,638 B1
• Filed: 12/20/2004
• Issued: 12/01/2009
• Est. Priority Date: 12/20/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Cohen, Michael H.
• Primary Examiner(s): Pwu; Jeffrey
• Assistant Examiner(s): Ali; Farhad
• Application Number:
  US11/019,431
• Time in Patent Office: 1,807 Days
• Field of Search: 709/204, 709/206
• US Class Current: 709/206
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: H04L 51/234 for tracking messages

Abstract

Verbal labels for electronic messages, as well as systems and methods for making and using such labels, are disclosed. A verbal label is a label containing audio data (such as a digital audio file of a user'"'"'s voice and/or a speaker template thereof) that is associated with one or more electronic messages. Verbal labels permit a user to more efficiently manipulate e-mail and other electronic messages by voice. For example, a user can add such labels verbally to an e-mail or to a group of e-mails, thereby permitting these messages to be sorted and retrieved more easily.

Claims

1. A computer-implemented method, comprising:

receiving an audio input from a user;

creating a verbal label comprising a digital audio file including audio data representing the audio input from the user and a speaker template of the digital audio file;

labeling an e-mail message using the verbal label, wherein the verbal label is used to identify the email message; and

unifying the verbal label with a preexisting text label for the user, wherein the unifying includes;

performing speech recognition on the audio input from the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the e-mail message with the matching preexisting text label for the user.

2. The method of claim 1, wherein the verbal label comprises a link to a text label associated with the plurality of electronic messages.

3. A computer-implemented method, comprising:

receiving an audio input from a user;

creating a verbal label comprising audio data representing the audio input from the user;

labeling a plurality of electronic messages using the verbal label, wherein the verbal label is used to identify the plurality of electronic messages; and

unifying the verbal label with a preexisting text label for the user, wherein the unifying includes;

performing speech recognition on the audio input from the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the plurality of electronic messages with the matching preexisting text label for the user.

4. The method of claim 3, wherein the electronic messages are e-mail messages.

5. The method of claim 3, wherein the verbal label comprises digital audio data.

6. The method of claim 3, wherein the verbal label comprises a speaker template of digital audio data representing the audio input from the user.

7. The method of claim 3, wherein the verbal label comprises digital audio data representing the audio input from the user and a speaker template of the digital audio data.

8. A computer-implemented method, comprising:

receiving a request for electronic messages associated with a specified label; and

identifying electronic messages labeled using the specified label, including electronic messages having an associated verbal label corresponding to the specified label,

wherein the verbal label comprises audio data representing audio input by a user,

wherein the verbal label is used to identify the electronic messages and wherein the verbal label is unified with a preexisting text label for the user, wherein unifying the verbal label with the preexisting text label includes;

performing speech recognition on the audio input by the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the electronic messages having the associated verbal label with the matching preexisting text label for the user.

9. The method of claim 8, wherein the request is generated by voice input.

10. The method of claim 8, wherein the request is generated by text input.

11. The method of claim 8, wherein at least one of the identified messages associated with the specified label has the same label as the specified label.

12. The method of claim 8, wherein at least one of the identified messages associated with the specified label has information in a header that corresponds to the specified label.

13. The method of claim 8, wherein at least one of the identified messages associated with the specified label has content that corresponds to the specified label.

14. The method of claim 8, wherein the identifying includes searching for messages selected from the group comprising messages having the same label as the specified label, messages having information in a header that corresponds to the specified label, and messages having content that corresponds to the specified label.

15. The method of claim 8, wherein text labels in the identified messages are an N-best match to a request input by voice, where N is a number greater than one.

16. The method of claim 8, wherein the request more closely corresponds to a speaker-template label for the identified messages than to a garbage model.

17. A memory containing a data structure, the data structure comprising:

a verbal label used to label a plurality of electronic messages, the verbal label comprising audio data that represents audio input from a user, wherein the verbal label is used to identify the plurality of electronic messages, and wherein the verbal label is unified with a preexisting text label for the user, wherein unifying the verbal label with the preexisting text label includes;

performing speech recognition on the audio input by the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the plurality of electronic messages with the matching preexisting text label for the user.

18. A system comprising at least one server, wherein said at least one server is configured to:

receive an audio input from a user;

create a verbal label comprising audio data that represents the audio input from the user;

label a plurality of electronic messages using the verbal label, wherein the verbal label is used to identify the plurality of electronic messages; and

unify the verbal label with a preexisting text label for the user, wherein the unifying includes;

performing speech recognition on the audio input from the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the plurality of electronic messages with the matching preexisting text label for the user.

19. A system comprising at least one server, wherein said at least one server is configured to:

receive a request for electronic messages associated with a specified label; and

identify electronic messages labeled using the specified label, including electronic messages labeled using an associated verbal label corresponding to the specified label, wherein the verbal label comprises audio data representing audio input by a user, wherein the verbal label is used to identify the electronic messages and wherein the verbal label is unified with a preexisting text label for the user, wherein unifying the verbal label with the preexisting text label includes;

performing speech recognition on the audio input by the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the electronic messages having the associated verbal label with the matching preexisting text label for the user.

20. A machine readable medium having stored thereon data representing sequences of instructions, which when executed by a computer, cause the computer to:

receive an audio input from a user;

create a verbal label comprising audio data that represents the audio input from the user;

label a plurality of electronic messages using the verbal label, wherein the verbal label is used to identify the plurality of electronic messages; and

unify the verbal label with a preexisting text label for the user, wherein the unifying includes;

performing speech recognition on the audio input from the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the plurality of electronic messages with the matching preexisting text label for the user.

21. A machine readable medium having stored thereon data representing sequences of instructions, which when executed by a computer, cause the computer to:

receive a request for electronic messages associated with a specified label; and

identify electronic messages labeled using the specified label, including electronic messages labeled using an associated verbal label corresponding to the specified label,

wherein the verbal label comprises audio data representing audio input by a user, wherein the verbal label is used to identify the electronic messages, and wherein the verbal label is unified with a preexisting text label for the user, wherein unifying the verbal label with the preexisting text label includes;

performing speech recognition on the audio input by the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the electronic messages having the associated verbal label with the matching preexisting text label for the user.

22. A computer-implemented method, comprising:

receiving an audio input from a user;

creating a verbal label comprising digital audio data representing the audio input received from the user;

labeling a plurality of electronic messages using the verbal label, wherein the verbal label is used to identify the plurality of electronic messages;

unifying the verbal label with a preexisting text label for the user, wherein the unifying includes;

performing speech recognition on the audio input from the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the plurality of electronic messages with the matching preexisting text label for the user; and

retrieving one or more of the plurality of electronic messages using the verbal label.

23. The computer-implemented method of claim 22, wherein the verbal label comprises a speaker template of the digital audio data representing the audio input received from the user.

24. The computer-implemented method of claim 22, wherein retrieving further comprises:

receiving a request for retrieval of electronic messages that are labeled with a specified label;

determining that the verbal label corresponds to the specified label; and

identifying the one or more electronic messages using the verbal label.

25. The computer-implemented method of claim 24, wherein the request is a voice input request, the determining further comprising:

performing speech recognition on speaker templates included in a plurality of verbal labels to identify that the verbal label corresponds to the specified label.

26. A computer-implemented method, comprising:

receiving an audio input from a user for a verbal label;

creating the verbal label comprising a digital audio file including audio data representing the audio input from the user, and a speaker template of the digital audio file;

labeling a plurality of electronic messages using the verbal label, wherein the verbal label is used to identify the plurality of electronic messages; and

unifying the verbal label with a preexisting text label for the user, wherein the unifying includes;

performing speech recognition on the audio input from the user or the audio data representing the audio input from the user,

matching the preexisting text label for the user to the audio input from the user or the audio data representing the audio input from the user, and

labeling the plurality of electronic messages with the matching preexisting text label for the user.