REAL-TIME VOIP COMMUNICATIONS USING N-WAY SELECTIVE LANGUAGE PROCESSING

• US 20110134910A1
• Filed: 12/08/2009
• Published: 06/09/2011
• Est. Priority Date: 12/08/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Nsame, Pascal A., Hall, Ezra D.B., Ventrone, Sebastien T., Chao-Suren, Chi-Chuen, Suren, Ayidn
• Granted Patent: US 8,279,861 B2
• Time in Patent Office: Days
• US Class Current: 370/352
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: H04L 12/1827 Network arrangements for conference optimisation or adaptation
• CPC Class Codes: H04L 65/1056 Multi-site
• CPC Class Codes: H04L 65/1069 Session establishment or de-establishment
• CPC Class Codes: H04L 65/70 Media network packetisation
• CPC Class Codes: H04L 65/765 intermediate
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 3/42391 where the subscribers are hearing-impaired persons, e.g. telephone devices for the deaf
• CPC Class Codes: H04M 3/56 Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities video conference systems H04N7/15

Abstract

A computer-implemented method and system of enabling concurrent real-time multi-language communication between multiple participants using a selective broadcast protocol, the method including receiving at a first server a real-time communication from a first participant, the real-time communication being addressed to a second participant constructed in a first spoken language. A preferred spoken language of receipt of real-time communication is identified by the second participant. A determination is made whether the preferred spoken language of receipt is different than that of the first spoken language of the real-time communication. The real-time communication from the first spoken language is translated and delivered to the preferred spoken language of receipt of the second participant to create a translated real-time communication whenever the preferred spoken language is different than the first spoken language and forwarded without translation when the preferred spoken language of the second participant is the same as the preferred spoken language of the first participant.

Claims

1. A computer-implemented method of enabling real-time communication between multiple participants, the method comprising:

receiving at a first server a real-time communication from a first participant, said real-time communication being addressed to a second participant constructed in a first spoken language;

identifying, by a computing device, a preferred spoken language of receipt of real-time communication by said second participant;

determining, by said computing device, whether said preferred spoken language of receipt is different than that of said first spoken language of said real-time communication;

translating, by said computing device, said real-time communication from said first spoken language to said preferred spoken language of receipt of said second participant to create a translated real-time communication whenever said preferred spoken language is different than said first spoken language; and

delivering, by said computing device, said translated real-time communication to said second participant.

2. The method according to claim 1, further comprising:

generating, by said computing device, voice service requests for communication resources based on participant-defined profiles.

3. The method according to claim 1, further comprising:

processing, by said computing device, on-demand said voice communication between first and second participant based on participant-defined profiles.

4. The method according to claim 1, further comprising:

integrating, by said computing device, translated text, supplemental translated audio, translated document text and video data having translated audio in said communication based on participant-defined profiles.

5. The method according to claim 4, further comprising:

communicating, by said computing device, a location of voice data without actual transmission of said voice data based on participant-defined profile.

6. The method according to claim 1, further comprising:

wherein said translating comprises identifying, by said computing device, Global Positioning System (GPS) location information of respective participants in the active communication channel based on participant-defined profiles.

7. The method according to claim 1, wherein said processing of said real-time communication further comprises:

determining an optimal location at which to process said real-time communication based on said participant-defined profiles

8. A communication system comprising:

at least one sending Voice Over Internet protocol (VOIP) server;

at least one receiving VOIP server; and

at least one VOIP communication network providing communication between said sending VOIP server and said receiving VOIP server;

at least one translating module that establishes an active n-way bidirectional automatic voice translation channel between said at least one sending and said at least one receiving VOIP servers across said at least one VOIP communication network; and

a processing VOIP server at a specific location that translates at least one spoken language between participants of different spoken languages on said at least one VOIP communication network,

wherein said processing said at least one spoken language is determined to be carried out at said specific location of said processing VOIP server based on respective participant profiles of said participants of difference spoken languages.

9. The system according to claim 8, wherein said participant profiles each includes a participant spoken language profile.

10. The system according to claim 8, further comprising:

a voice service request module generates a request for available communication resources based on said participant profiles.

11. The system according to claim 8, further comprising:

a media integrator that integrates information containing text, voice, document and video data based on said participant profiles with said at least one spoken language being translated.

12. The system according to claim 8, further including a participant profile database.

13. The system according to claim 8, further comprising:

a plurality of listening VOIP servers hosting participants having different participant spoken language profiles.

14. The system according to claim 8, wherein said processing VOIP server comprises at least one of a plurality of VOIP talking servers and a plurality of VOIP listening servers.

15. A computer-implemented method, comprising:

initiating, by a computing device, a multiple-location multi-participant voice translation session;

determining, by said computing device, whether voice translation processing is required based on participant profiles of session participants in said voice translation session;

determining available translation resources at each of said multiple locations;

calculating, by said computing device, a maximum number of possible simultaneous translation processes based on said available translation resources at each of said multiple locations;

determining, by said computing device, whether a default server can meet both real-time processing and real-time routing requirements of said voice translation session; and

allocating, by said computing device, translation processing services to said available translation resources based on comparing said participant profiles of a talking participant and a listening participant.

16. The method according to claim 15, further comprising:

allocating, by said computing device, forwarding services based on said determining whether voice translation processing is required based on participant profiles.

17. The method according to claim 15, further comprising:

scheduling participant profile-based translation processing services on at least one listening server based on said determining based on comparing said participant profiles of said talking participant and said listening participant.

18. The method according to claim 15, further comprising:

integrating, by said computing device, text, voice, document and video data in said voice translation session based on participant-defined profiles.

19. The method according to claim 15, further comprising:

integrating, by said computing device, Global Positioning System (GPS) location information of participants in said voice translation session based on participant-defined profiles.

20. The method according to claim 15, wherein said participant profiles each includes a participant spoken language profile.