Speech recognition system and method for converting voice mail messages to electronic mail messages

• US 6,507,643 B1
• Filed: 03/16/2000
• Issued: 01/14/2003
• Est. Priority Date: 03/16/2000
• Status: Expired due to Term

• Current Assignee: Breveon, Inc.
• Original Assignee: Breveon, Inc.
• Inventors: Groner, Gabriel F.
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): Foster, Roland G.
• Application Number:
  US09/526,807
• Time in Patent Office: 1,034 Days
• Field of Search: 379/88.01, 379/88.04, 379/88.11, 379/88.12, 379/88.13, 379/88.14, 379/88.16, 379/88.17, 379/88.22, 379/88.23, 379/88.25, 704/231, 704/275, 709/206
• US Class Current: 379/88.14
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04L 51/066 Format adaptation, e.g. format conversion or compression
• CPC Class Codes: H04L 51/48 Message addressing, e.g. address format or anonymous messages, aliases
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/5307 for recording messages comprising any combination of audio and non-audio components

Abstract

The present invention relates generally to speech recognition systems as applied to voice and electronic message mailing. More particularly the invention is a system and method for converting speech to a text message suitable for sending as an e-mail message and for viewing on a text display device. After an audio message from a caller is received, a text message file is generated and sent to the intended recipient'"'"'s e-mail address, which has been stored prior to the receipt of the audio message. If the caller is identified, a caller-specific voice file may be used to facilitate speech recognition for generation of the text message file. Also, if the caller specifies a subject for the message, a specialized vocabulary file may be used to facilitate the generation of the text message file.

Claims

1. A method of receiving and processing voice messages, comprising:

receiving an audio message from a caller for a recipient identified by a telephone number used by the caller to place a call;

verifying whether the audio message is from a caller that is a predetermined known caller;

retrieving a stored e-mail address associated with the recipient, wherein the e-mail address associated with the recipient was stored prior to receipt of the audio message;

generating a text message from the audio message from the caller; and

sending to the recipient, at the recipient'"'"'s e-mail address, an electronic mail message, including at least a portion of the text message, and a verification notice that indicates that the electronic mail message is from the predetermined known caller.

2. A method of receiving and processing voice messages, comprising:

receiving an audio message from a caller for a recipient identified by a telephone number used by the caller to place a call;

retrieving a stored e-mail address associated with the recipient, wherein the e-mail address associated with the recipient was stored prior to receipt of the audio message;

generating a text message file from the audio message from the caller;

editing the text message file prior to sending the text message file to the recipient, wherein the editing includes converting the text message file to speech for audio review by the caller and enabling the caller to replace user selected portions of the text message file; and

sending an electronic mail message, including at least a portion of the text message file, to the recipient at the e-mail address associated with the recipient;

wherein the editing includes verbally specifying new words to be converted to text and inserted into the text message file.

3. A method of sending messages, comprising:

receiving an audio message from a caller for a recipient;

prompting the caller for an audio subject of the message;

generating a text subject from the audio subject;

determining an e-mail address for the recipient;

identifying a specialized vocabulary file identifying a specialized vocabulary file that corresponds to the text subject;

generating a text message file in accordance with the specialized vocabulary file; and

sending an electronic mail message including the text subject and at least a portion of the text message file to the recipient at the recipient'"'"'s e-mail address.

4. A message system comprising a dialog manager, a voice verification procedure and a speech recognition procedure wherein:

the dialog manager is configured to;

receive an audio message from a caller for a recipient identified by a telephone number used by the caller to place a call, and

retrieve a stored e-mail address associated with the recipient, wherein the e-mail address associated with the recipient was stored prior to receipt of the audio message;

the voice verification procedure is configured to verify whether the audio message is from a caller who is a predetermined known caller;

the speech recognition procedure is configured to generate a text message from the audio message from the caller; and

the dialog manager is configured to send to the recipient at the recipient'"'"'s e-mail address at least a portion of the text message and a verification notice that indicates that the text message is from the predetermined known caller.

5. A message system comprising a dialog manager, a speech recognition procedure and an editor wherein:

the dialog manager is configured to;

receive an audio message from a caller for a recipient identified by a telephone number used by the caller to place a call, and

retrieve a stored e-mail address associated with the recipient, wherein the e-mail address associated with the recipient was stored prior to receipt of the audio message;

the speech recognition procedure is configured to generate a text message file from the audio message from the caller;

the editor is configured to allow the caller to edit the text message file prior to sending the text message file to the recipient, wherein the editing includes converting the text message file to speech for audio review by the caller, enabling the caller to verbally specify new words to be converted to text and inserted into the text message file, and enabling the caller to replace user selected portions of the text message file; and

the dialog manager is configured to send the text message file to the recipient at the recipient'"'"'s e-mail address.

6. A message system comprising a dialog manager, a gister procedure, and a speech recognition procedure wherein:

the dialog manager is configured to;

receive an audio message from a caller for a recipient identified by a telephone number used by the caller to place a call,

retrieve a stored e-mail address associated with the recipient, wherein the e-mail address associated with the recipient was stored prior to receipt of the audio message, and

prompt the caller for an audio subject of the message;

the gister procedure is configured to generate a text subject from the audio subject and to identify a specialized vocabulary file that corresponds to the text subject; and

the speech recognition procedure is configured to generate a text message file from the audio message from the caller in accordance with the specialized vocabulary file.

7. A computer program product for use in conjunction with a computer system, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism comprising a dialog manager, a voice verification procedure and a speech recognition procedure wherein:

the dialog manager is configured to;

receive an audio message from a caller for a recipient identified by a telephone number used by the caller to place a call, and

retrieve a stored e-mail address associated with the recipient, wherein the e-mail address associated with the recipient was stored prior to receipt of the audio message;

the voice verification procedure is configured to verify whether the audio message is from a caller who is a predetermined known caller;

the speech recognition procedure is configured to generate a text message from the audio message from the caller; and

the dialog manager is configured to send to the recipient at the recipient'"'"'s e-mail address at least a portion of the text message and a verification notice that indicates that the text message is from the predetermined known caller.

8. A computer program product for use in conjunction with a computer system, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism comprising a dialog manager, a speech recognition procedure and an editor wherein:

the dialog manager is configured to;

receive an audio message from a caller for a recipient identified by a telephone number used by the caller to place a call, and

retrieve a stored e-mail address associated with the recipient, wherein the e-mail address associated with the recipient was stored prior to receipt of the audio message;

the speech recognition procedure is configured to generate a text message file from the audio message from the caller;

the editor is configured to allow the caller to edit the text message file prior to sending the text message file to the recipient, wherein the editing includes converting the text message file to speech for audio review by the caller, enabling the caller to verbally specify new words to be converted to text and inserted into the text message file, and enabling the caller to replace user selected portions of the text message file; and

the dialog manager is configured to send the text message file to the recipient at the recipient'"'"'s e-mail address.

9. A computer program product for use in conjunction with a computer system, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism comprising a dialog manager, a gister procedure, and a speech recognition procedure wherein:

the dialog manager is configured to;

receive an audio message from a caller for a recipient identified by a telephone number used by the caller to place a call,

retrieve a stored e-mail address associated with the recipient, wherein the e-mail address associated with the recipient was stored prior to receipt of the audio message, and

prompt the caller for an audio subject of the message;

the gister procedure is configured to generate a text subject from the audio subject and to identify a specialized vocabulary file that corresponds to the text subject; and

the speech recognition procedure is configured to generate a text message file from the audio message from the caller in accordance with the specialized vocabulary file.

10. A method of receiving and processing voice messages at a voice mail server, comprising:

storing for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on the voice mail server;

receiving an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call, wherein the subscriber is one of the plurality of subscribers;

verifying whether the audio message is from a caller that is a predetermined known caller;

retrieving the stored e-mail address associated with the subscriber;

generating a text message from the audio message from the caller; and

sending to the subscriber, at the subscriber'"'"'s e-mail address, an electronic mail message, including at least a portion of the text message, and a verification notice that indicates that the electronic mail message is from the predetermined known caller.

11. A method of receiving and processing voice messages at a voice mail server, comprising:

storing for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on the voice mail server;

receiving an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call, wherein the subscriber is one of the plurality of subscribers;

retrieving the stored e-mail address associated with the subscriber;

generating a text message file from the audio message from the caller;

editing the text message file prior to sending the text message file to the subscriber, wherein the editing includes converting the text message file to speech for audio review by the caller, enabling the caller to verbally specify new words to be converted to text and inserted into the text message file, and enabling the caller to replace user selected portions of the text message file; and

sending an electronic mail message including at least a portion of the text message file to the subscriber at the e-mail address associated with the subscriber.

12. A method receiving and processing voice messages at a voice mail server, comprising:

storing for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on the voice mail server;

receiving an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call, wherein the subscriber is one of the plurality of subscribers;

retrieving the stored e-mail address associated with the subscriber;

prompting the caller for an audio subject of the message;

generating a text subject from the audio subject; and

identifying a specialized vocabulary file that corresponds to the text subject;

generating the text message from the audio message in accordance with the specialized vocabulary file; and

sending an electronic mail message including the text subject and at least a portion of the text message to the subscriber at the e-mail address associated with the subscriber.

13. A message system comprising a voice mail server, an e-mail address data structure, a dialog manager, a voice verification procedure and a speech recognition procedure wherein:

the e-mail address data structure contains for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on the voice mail server;

the dialog manager is configured to;

receive an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call, and

retrieve a stored e-mail address associated with the subscriber, wherein the e-mail address associated with the subscriber was stored prior to receipt of the audio message;

the voice verification procedure is configured to verify whether the audio message is from a caller who is a predetermined known caller;

the speech recognition procedure is configured to generate a text message from the audio message from the caller; and

the dialog manager is configured to send to the subscriber at the subscriber'"'"'s e-mail address at least a portion of the text message and a verification notice that indicates that the text message is from the predetermined known caller.

14. A message system comprising a voice mail server, an e-mail address data structure, a dialog manager, a speech recognition procedure and an editor wherein:

the e-mail address data structure contains for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on the voice mail server;

the dialog manager is configured to;

receive an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call, and

retrieve a stored e-mail address associated with the subscriber, wherein the e-mail address associated with the subscriber was stored prior to receipt of the audio message;

the speech recognition procedure is configured to generate a text message file from the audio message from the caller;

the editor is configured to allow the caller to edit the text message file prior to sending the text message file to the subscriber, wherein the editing includes converting the text message file to speech for audio review by the caller, enabling the caller to verbally specify new words to be converted to text and inserted into the text message file, and enabling the caller to replace user selected portions of the text message file; and

the dialog manager is configured to send the text message file to the subscriber at the subscriber'"'"'s e-mail address.

15. A message system comprising a voice mail server, an e-mail address data structure, a dialog manager, a speech recognition procedure, and a gister procedure wherein:

the e-mail address data structure contains for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on the voice mail server;

the dialog manager is configured to;

receive an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call;

retrieve a stored e-mail address associated with the subscriber, wherein the e-mail address associated with the subscriber was stored prior to receipt of the audio message; and

prompt the caller for an audio subject of the message; and

the gister procedure is configured to generate a text subject from the audio subject and to identify a specialized vocabulary file that corresponds to the text subject;

the speech recognition procedure is configured to generate a text message from the audio message from the caller in accordance with the specialized vocabulary file; and

the dialog manager is configured to send an electronic mail message including the text subject and at least a portion of the text message to the subscriber at the e-mail address associated with the subscriber.

16. A computer program product for use in conjunction with a computer system, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism comprising:

a dialog manager;

a voice verification procedure;

a speech recognition procedure; and

an e-mail address data structure configured to store for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on a voice mail server;

wherein

the dialog manager is configured to;

receive an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call, and

retrieve a stored e-mail address associated with the subscriber, wherein the e-mail address associated with the subscriber was stored prior to receipt of the audio message;

the voice verification procedure is configured to verify whether the audio message is from a caller who is a predetermined known caller;

the speech recognition procedure is configured to generate a text message from the audio message from the caller; and

the dialog manager is configured to send to the subscriber at the subscriber'"'"'s e-mail address at least a portion of the text message and a verification notice that indicates that the text message is from the predetermined known caller.

17. A computer program product for use in conjunction with a computer system, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism comprising:

a dialog manager;

a speech recognition procedure;

an editor; and

an e-mail address data structure configured to store for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on a voice mail server;

wherein

the dialog manager is configured to;

receive an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call, and

retrieve a stored e-mail address associated with the subscriber, wherein the e-mail address associated with the subscriber was stored prior to receipt of the audio message;

the speech recognition procedure is configured to generate a text message file from the audio message from the caller;

the editor is configured to allow the caller to edit the text message file prior to sending the text message file to the subscriber, wherein the editing includes converting the text message file to speech for audio review by the caller, enabling the caller to verbally specify new words to be converted to text and inserted into the text message file, and enabling the caller to replace user selected portions of the text message file; and

the dialog manager is configured to send the text message file to the subscriber at the subscriber'"'"'s e-mail address.

18. A computer program product for use in conjunction with a computer system, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism comprising:

a dialog manager;

a speech recognition procedure; and

an e-mail address data structure configured to store for each subscriber of a plurality of subscribers an e-mail address associated with the subscriber, wherein the plurality of subscribers comprise a subset of all the subscribers on a voice mail server wherein;

the dialog manager is configured to;

receive an audio message from a caller for a subscriber identified by a telephone number used by the caller to place a call;

retrieve a stored e-mail address associated with the subscriber, wherein the e-mail address associated with the subscriber was stored prior to receipt of the audio message; and

prompt the caller for an audio subject of the message; and

the gister procedure is configured to generate a text subject from the audio subject and to identify a specialized vocabulary file that corresponds to the text subject;

the speech recognition procedure is configured to generate a text message from the audio message from the caller in accordance with the specialized vocabulary file; and

the dialog manager is configured to send an electronic mail message including the text subject and at least a portion of the text message to the subscriber at the e-mail address associated with the subscriber.