Automatic confirmation of personal notifications

• US 6,876,987 B2
• Filed: 01/30/2001
• Issued: 04/05/2005
• Est. Priority Date: 01/30/2001
• Status: Expired due to Fees

• Current Assignee: Exelis Incorporated (L3Harris Technologies, Inc.)
• Original Assignee: ITT Defense Incorporated
• Inventors: Bahler, Lawrence G., Higgins, Alan L.
• Primary Examiner(s): Knight, Anthony
• Assistant Examiner(s): Hirl, Joseph P.
• Application Number:
  US09/772,651
• Publication Number:
  US 20020103656A1
• Time in Patent Office: 1,526 Days
• Field of Search: 706/11, 706/12, 706/14
• US Class Current: 706/14
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: H04M 2203/2083 Confirmation by serviced party
• CPC Class Codes: H04M 3/533 Voice mail systems

Abstract

An automated system obtains a confirmation of receipt of a notification by the intended recipient by having the recipient speak all or part of the notification. The words spoken by the recipient are determined by a computerized system using an automatic speech recognition algorithm. The computerized system determines whether the words spoken are those of the notification, and if they are, the system accepts the confirmation from the recipient. Optionally, the system additionally applies an automatic speaker recognition algorithm to determine whether the person reciting the notification has similar voice characteristics to the intended recipient based on a previous enrollment of the intended recipient'"'"'s voice. The system can also record the recipient reciting the notification so that it can later be compared to the intended recipient'"'"'s voice if the intended recipient repudiates the confirmation.

Claims

1. A method for confirming that a predetermined recipient of an electronically transmitted word sequence has received and read the word sequence, comprising:

storing voice characteristic data of the predetermined recipient;

receiving by the predetermined recipient the word sequence from a sender of the word sequence;

presenting the word sequence to the predetermined recipient;

accepting an audio input from the predetermined recipient in response to presenting the word sequence;

determining whether the accepted audio input includes the predetermined recipient speaking the presented word sequence;

comparing the voice characteristic data to the accepted audio input to determine if the accepted audio input substantially matches the voice characteristic data; and

if the accepted audio input matches the presented word sequence and substantially matches the voice characteristic data, transmitting a confirmation to the sender of the word sequence, indicating that the predetermined recipient has received and read the presented word sequence.

2. The method of claim 1 wherein presenting the word sequence to the predetermined recipient includes presenting a graphical representation of the word sequence.

3. The method of claim 2 wherein presenting the graphical representation of the word sequence includes presenting said graphical representation on a display.

4. The method of claim 1 wherein presenting the word sequence to the predetermined recipient includes presenting an audible representation of the word sequence.

5. The method of claim 4 wherein presenting the audible representation of the word sequence includes playing a stored audio recording of the word sequence.

6. The method of claim 4 wherein presenting the audible representation of the word sequence includes applying a speech synthesis algorithm to the word sequence to form the audible representation.

7. The method of claim 4 wherein presenting the audible representation of the word sequence includes transmitting the audible representation over a telephone network and accepting the audio input includes transmitting the audio input over the telephone network.

8. The method of claim 1 wherein determining whether the accepted audio input includes the predetermined recipient speaking the word sequence includes applying a speech recognition algorithm to the accepted audio input.

9. The method of claim 8 wherein applying the speech recognition algorithm includes computing a resulting word sequence from the audio input and determining whether the audio input includes the predetermined recipient speaking the word sequence includes comparing the resulting word sequence to the word sequence received by the predetermined recipient.

10. The method of claim 8 wherein applying the speech recognition algorithm includes time-aligning the presented word sequence and the audio input.

11. The method of claim 8 wherein applying the speech recognition algorithm includes computing a match score characterizing a similarity between the presented word sequence and the audio input.

12. The method of claim 11 wherein determining whether the audio input includes the predetermined recipient speaking the presented word sequence includes comparing the match score with a threshold score.

13. The method of claim 1 wherein accepting the audio input includes accepting a plurality of segments of the audio input each associated with a different part of the presented word sequence, and wherein determining whether the accepted audio input includes the predetermined recipient speaking the presented word sequence includes determining whether each of the plurality of segments of the audio input includes the predetermined recipient speaking the associated part of the presented word sequence.

14. The method of claim 13 wherein presenting the word sequence includes presenting each of the different parts of the word sequence in turn and accepting the audio input associated with that part before presenting another of the different parts.

15. Software stored on computer readable media for causing a computer system to perform functions including:

storing voice characteristic data of a predetermined recipient;

receiving, by the predetermined recipient, a word sequence from a sender of the word sequence;

presenting the word sequence to the predetermined recipient;

accepting an audio input from the predetermined recipient in response to presenting the word sequence;

determining whether the accepted audio input includes the predetermined recipient speaking the presented word sequence;

comparing the voice characteristic data to the accepted audio input to determine if the accepted audio input substantially matches the voice characteristic data; and

if the accepted audio input matches the presented word sequence and substantially matches the voice characteristic data, transmitting a confirmation to the sender of the word sequence, indicating that the predetermined recipient has received and read the presented word sequence.

16. An automated notification confirmation system comprising:

means for storing voice characteristic data of a predetermined recipient;

means for receiving, by the predetermined recipient, a word sequence from a sender of the word sequence;

means for presenting the word sequence to the predetermined recipient;

means for accepting an audio input from the predetermined recipient in response to presenting the word sequence;

means for determining whether the accepted audio input includes the predetermined recipient speaking the presented word sequence;

means for comparing the voice characteristic data to the accepted audio input to determine if the accepted audio input substantially matches the voice characteristic data; and

means for transmitting a confirmation to the sender of the word sequence, indicating that the predetermined recipient has received and read the presented word sequence, if the accepted audio input matches the presented word sequence and substantially matches the voice characteristic data.