Method and message server for routing a speech message

• US 9,538,348 B2
• Filed: 06/04/2012
• Issued: 01/03/2017
• Est. Priority Date: 06/04/2012
• Status: Active Grant

• Current Assignee: Telefonaktiebolaget LM Ericsson
• Original Assignee: Telefonaktiebolaget LM Ericsson
• Inventors: Arkko, Jari, Menp, Jouni, Mecklin, Tomas
• Primary Examiner(s): Huynh, Van D
• Application Number:
  US14/404,689
• Publication Number:
  US 20150148084A1
• Time in Patent Office: 1,674 Days
• Field of Search: 379/88.04, 379/88.11, 379/88.13, 370/356
• US Class Current: 1/1
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04L 51/066 Format adaptation, e.g. format conversion or compression
• CPC Class Codes: H04M 1/645 with speech synthesis
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2203/357 Autocues for dialog assistance
• CPC Class Codes: H04M 2203/4536 Voicemail combined with text-based messaging
• CPC Class Codes: H04M 2242/22 Automatic class or number identification arrangements
• CPC Class Codes: H04M 3/42382 Text-based messaging services in telephone networks such as PSTN/ISDN, e.g. User-to-User Signalling or Short Message Service for fixed networks
• CPC Class Codes: H04M 3/533 Voice mail systems
• CPC Class Codes: H04W 4/12 Messaging; Mailboxes; Announcements
• CPC Class Codes: H04W 4/18 Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals

Abstract

A method and message server (204) for routing a speech message, received (2:1) from a user equipment (200) of a sending user, to at least one recipient (208, 210) in a communication network. After obtaining (2:2) a text version created by speech recognition (206) of the received speech message, the at least one recipient is identified (2:3) by the message server based on the obtained text version, and the speech message is then routed (2:5) to the identified at least one recipient.

Claims

1. A method, performed in a message server, for routing a speech message to at least one recipient in a communication network, the method comprising:

receiving the speech message sent from a user equipment in audio form when a sending user has spoken the speech message into the user equipment;

obtaining a text version created by speech recognition of the received speech message;

obtaining contextual information comprising at least one contextual factor regarding the sending user;

identifying the at least one recipient based on the obtained text version; and

routing the speech message to the identified at least one recipient;

wherein the received speech message is processed based on the contextual information regarding the sending user;

wherein processing the received speech message comprises modifying the received speech message by adding information deduced by analysis of the obtained text version and the contextual information.

2. The method of claim 1, wherein the text version is modified and translated into speech in audio form before routing the speech message to the at least one recipient.

3. The method of claim 1, wherein the added information indicates any of:

the identity of the sending user, a location, and a context or characteristics of the sending user.

4. The method of claim 1, wherein the contextual information is obtained from any of:

meta data received with the speech message, user information that has been pre-configured in the message server, and user information maintained by another node or service in the communication network.

5. The method of claim 1, wherein multiple recipients are identified, depending on the current context of the sending user, and wherein the speech message is routed to each of the multiple recipients.

6. The method of claim 1, wherein the speech message is sent as a text message to the identified at least one recipient.

7. A message server configured to route a speech message to at least one recipient in a communication network, the message server comprising a processing circuit and a memory circuit containing computer program instructions for execution by the processing circuit, the computer program instructions comprising instructions for:

receiving the speech message sent from a user equipment in audio form when a sending user has spoken the speech message into the user equipment;

obtaining a text version created by speech recognition of the received speech message;

obtaining contextual information comprising at least one contextual factor regarding the sending user;

identifying the at least one recipient based on the obtained text version;

routing the speech message to the identified at least one recipient; and

processing the received speech message based on the contextual information regarding the sending user;

wherein the memory circuit further comprises programming instructions for processing the received speech message by modifying the received speech message by adding information deduced by analysis of the obtained text version and the contextual information.

8. The message server of claim 7, wherein the memory circuit further comprises programming instructions for modifying and translating the text version into speech in audio form before the speech message is routed to the at least one recipient.

9. The message server of claim 7, wherein the added information indicates any of:

the identity of the sending user, a location, and a context or characteristics of the sending user.

10. The message server of claim 7, wherein the memory circuit comprises programming instructions for obtaining the contextual information from any of:

meta data received with the speech message, user information that has been pre-configured in the message server, and user information maintained by another node or service in the communication network.

11. The message server of claim 7, wherein the memory circuit further comprises programming instructions for identifying multiple recipients, depending on the current context of the sending user, and for routing the speech message to each of the multiple recipients.

12. The message server of claim 7, wherein the memory circuit comprises programming instructions for sending the speech message as a text message to the identified at least one recipient.

13. A non-transitory computer-readable medium comprising, stored thereupon, a computer program comprising computer readable code units that, when run on a message server, cause the message server to:

receive the speech message sent from a user equipment in audio form when a sending user has spoken the speech message into the user equipment,

obtain a text version created by speech recognition of the received speech message,

obtain contextual information comprising at least one contextual factor regarding the sending user;

identify the at least one recipient based on the obtained text version, and

route the speech message to the identified at least one recipient,

wherein the received speech message is processed based on the contextual information regarding the sending user;

wherein processing the received speech message comprises modifying the received speech message by adding information deduced by analysis of the obtained text version and the contextual information.