Voice-controlled voice mail having random-order message retrieval based on played spoken identifier list

• US 5,797,124 A
• Filed: 05/30/1996
• Issued: 08/18/1998
• Est. Priority Date: 05/30/1996
• Status: Expired due to Term

• Current Assignee: Intervoice Limited Partnership
• Original Assignee: Intervoice Limited Partnership
• Inventors: Walsh, James K., Gardner, Marc A.
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Smits, Talivaldis Ivars
• Application Number:
  US08/656,519
• Time in Patent Office: 810 Days
• Field of Search: 704/270, 704/275, 379/67, 379/89
• US Class Current: 704/275
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/533 Voice mail systems

Abstract

A system and method for voice controlled message retrieval. Each message stored in a voice mail system has an associated header and return address. The system generates and stores a speech recognition template from each unique header. When a subscriber wishes to retrieve a message, the subscriber speaks the header. The subscriber'"'"'s speech is then compared with the speech recognition templates stored in the system. If a matching template is found, the system plays the message associated with the header from which the template was generated. Additionally, the subscriber can tag certain callers and cause the system to apply special treatment to messages from tagged callers. Moreover, the subscriber can reply to a caller calling from outside the system.

Claims

1. A system for storing messages from callers and for selectively retrieving the messages by a subscriber, comprising:

means for prompting each of said callers to utter a message identifier;

means for associating said message identifiers with a specific message;

means for storing the message identifiers and the associated messages;

means for playing a list of said message identifiers for said subscriber;

means for determining whether an input received from the subscriber matches a stored message identifier; and

means for playing the message associated with a matched one of the stored message identifiers.

2. The system of claim 1, further comprising:

means for providing special treatment for subsequent calls to the system from certain callers.

3. The system of claim 2, wherein the means for providing special treatment comprises:

means for notifying the subscriber when certain callers call the system.

4. The system of claim 2, wherein the means for providing special treatment further comprises:

means for prompting a subsequent caller to input a subsequent uttered message identifier;

means for comparing the subsequent message identifier with previously stored message identifiers; and

means for verifying that a matched subsequent message identifier identifies the caller.

5. The system of claim 1, further comprising:

means for saving the message identifiers after the associated messages have been deleted.

6. The system of claim 1, further comprising:

means for prompting the subscriber for the input.

7. The system of claim 1, wherein the associating means includes:

means for associating a caller'"'"'s return address with the message.

8. The system of claim 7, wherein the means for associating a return address includes means for automatically determining a communication location of the caller.

9. The system of claim 7, further comprising:

means for automatically delivering a reply from the subscriber to the caller'"'"'s return address.

10. The system of claim 7, wherein the caller'"'"'s return address is remote from the system.

11. The system of claim 1, wherein the associating means comprises means for recognizing a speech pattern of a caller.

12. The system of claim 1, wherein the identity is a name tag.

13. The system of claim 1, further comprising:

means for converting the message identifiers into speech recognition templates.

14. The system of claim 13, wherein the means for determining comprises:

means for comparing the input with the speech recognition templates.

15. The system as set forth in claim 1 wherein said determining means includes:

means for sequentially communicating a list of said message identifiers to said subscriber without communicating the associated message.

16. A method of delivering a message from a caller to a subscriber of a voice mail system, comprising the steps of:

prompting the caller to input a header utterance identifying the caller and to input a message associated therewith;

storing the header utterance;

playing the header utterance to the subscriber upon command of the subscriber;

receiving an input from the subscriber;

comparing the input with the stored header utterance; and

if the input matches the stored header utterance, playing the message identified by the header utterance to the subscriber.

17. The method of claim 16, further comprising the step of:

providing special treatment for subsequent calls to the voice mail system based upon recognition of the caller'"'"'s voice patterns.

18. The method of claim 17, wherein the providing special treatment step comprises the step of:

notifying the subscriber when the caller calls the voice mail system.

19. The method of claim 17, wherein the providing step comprises the steps of:

comparing the header utterance with previously stored header utterances to determine a matched previously stored header utterance; and

verifying that said matched previously stored header utterance identifies the caller.

20. The method of claim 16, wherein the presenting step comprises the steps of:

playing a list of header utterances to the subscriber; and

prompting the subscriber for the input.

21. The method of claim 16, further comprising the step of:

associating the message with information indicating where the caller can be reached.

22. The method of claim 21, further comprising the step of:

delivering a reply from the subscriber to the caller by automatically using the information indicating where the caller can be reached.

23. The system of claim 21, wherein the caller is remote from the voice mail system.

24. The method of claim 21, wherein the step of associating the message with information uses automatic number identification to determine a communication location of the caller.

25. The method of claim 16, further comprising the step of:

converting the header utterance into a speech recognition template; and

wherein the comparing step compares the input with the speech recognition template.

26. A method of replaying one or more messages from one or more callers, comprising the steps of:

playing a list of headers to a subscriber, each header identifying a message left by a caller on a voice mail system;

receiving a voice input from the subscriber;

comparing the voice input against the played list of headers to find a matching header; and

playing the message identified by the matching header.

27. The method of claim 26, further comprising the step of:

providing special treatment for subsequent calls from the caller who left the message identified by the matching header.

29. The method of claim 26, further comprising the step of:

generating a speech recognition template for each header in the list;

wherein the comparing step compares the voice input to the speech recognition templates.

28. The method of 27, wherein the providing special treatment step comprises the step of:

notifying the subscriber when the caller makes a subsequent call to the system.

30. A method for processing messages in a voice mail system, said method comprising the steps of:

obtaining a spoken identifier from a message-leaving party;

playing, upon request of said subscriber, a list of all spoken identifiers left by said message-leaving parties.

31. The method as set forth in claim 30 further comprising the steps of:

accepting a subscriber selection of one of said spoken identifiers; and

delivering, to said subscriber, a message related to said subscriber-selected spoken identifier.