System and methods for enabling applications of who-is-speaking (WIS) signals

• US 20070133437A1
• Filed: 12/13/2005
• Published: 06/14/2007
• Est. Priority Date: 12/13/2005
• Status: Abandoned Application

• Current Assignee: Alcatel SA (Nokia Corporation)
• Original Assignee: Alcatel SA (Nokia Corporation)
• Inventors: Wengrovitz, Michael, Gupta, Siddhartha
• Application Number:
  US11/302,860
• Publication Number:
  US 20070133437A1
• Time in Patent Office: Days
• US Class Current: 370/260
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• 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
• CPC Class Codes: H04N 7/155 involving storage of or access to video conference sessions tracking arrangements for later retrieval of a computer conference content or participants activities H04L12/1831

Abstract

A system for enabling controlled application of derived who-is-speaking indications related to activity of participants to a live multiparty communications conference or recorded outputs. The system includes a first node hosting a conference bridging switch, software or a combination thereof, having multiple conference input channels; a second node having data access to at least an output signal port of the conference bridging switch, software, or a combination thereof, and a software application distributed wholly to the first or second node, or in parts to the first and second node. The application is used to apply the who is speaking indications to output communications, data files, or data streams, forwarded to one of, a select potion of, or combination of, the conference participants, non-participant third parties, and one or more storage facilities.

Claims

1. A system for enabling controlled application of derived who-is-speaking indications related to activity of participants to a live multiparty communications conference or recorded output thereof including:

a first node hosting a conference bridging switch, software or a combination thereof, having multiple conference input channels;

a second node having data access to at least an output signal port of the conference bridging switch, software, or a combination thereof, and

a software application distributed wholly to the first or second node, or in parts to the first and second node, the application used to apply the who is speaking indications to output communications, data files, or data streams, forwarded to one of, a select potion of, or combination of, the conference participants, non-participant third parties, and one or more storage facilities.

2. The system of claim 1, wherein the first node is a dedicated conference bridging facility and the second node is one of a desktop computer, or a data server.

3. The system of claim 1, wherein the first node is a PBX switch, and the second node is a desktop computer.

4. The system of claim 1, hosted on a digital network.

5. The system of claim 1, wherein the who-is-speaking indication includes, in addition to identification information, presence information or a locator thereto, the presence information relevant to the identification information.

6. The system of claim 5, further including rich who is speaking information or a locator thereto, the rich who is speaking information wholly or partly derived from recorded activity of the identified participant over the duration of one or more conference sessions.

7. The system of claim 1, wherein the output communications are instant messages containing text of the conference content.

8. The system of claim 1, wherein the data files are text transcriptions of the conference output.

9. The system of claim 1, wherein the data streams are really simple syndication (RSS) feeds.

10. The system of claim 1, wherein the data streams are audio streams or audio/video streams.

11. An audio content transcription and annotation system for rendering annotated text transcription of live or recorded speech from a multiparty conference session enabled by a conference bridging switch, software, or a combination thereof having multiple conference input channels and for annotating the transcribed text files with who-is-speaking data including:

an input port for receiving the audio content;

a time synchronization module for recording temporal offsets of changes in a channel activity signal relevant to conference session run time;

a channel to speaker association module; and

a text annotation engine;

characterized in that the transcribed text files are annotated according to indication of signal changes over time with relevance to audible words, phrases or segments of the content found within the scope of time periods existing in between the signal changes.

12. The system of claim 11, wherein the who-is-speaking indication includes, in addition to identification information, presence information or a locator thereto, the presence information relevant to the identification information.

13. The system of claim 12, further including rich presence information or a locator thereto, the rich presence information wholly or partly derived from recorded activity of the identified participant over the duration of one or more conference sessions.

14. A method for transcribing and annotating live or recorded speech from a multiparty conference session enabled by a conference bridging switch, software, or a combination thereof having multiple conference input channels, the annotations indicative of who-is-speaking including steps for:

(a) receiving the speech files for text transcription;

(b) accessing a channel activity signal temporally associated with the speech files;

(c) inserting fields or place holders into the documents during text transcription, the fields or placeholders inserted according to time of occurrence in the document;

(d) retrieving channel-to-speaker association data for each field or placeholder; and

,(e) inserting the annotations into the appropriate fields.

15. The method of claim 14, wherein in step (e) the annotations further include presence information about the speaker, or a locator thereto, the presence information including but not limited to contact information.

16. The method of claim 15, wherein in step (e) the annotations further include rich presence information about the speaker, or a locator thereto, the rich presence information including, but not limited to statistics related to speaker activity over the duration of one or more than one conference.

17. A system for searching conference archives for information relevant to recorded content of a multiparty conference, the record temporally annotated with speaker identification and other information or locators thereto including:

a first node hosting a search engine and interface;

a second node capable of accessing the first node over a network; and

at least one repository containing the conference records in the form of transcribed text files linked or not linked to appropriate multimedia audio files or audio/video files;

characterized in that information searched may include speaker identifications using content keywords or phrasing as input, instances of repeated content spoken by a speaker using a combination of speaker identification parameters and content keywords or phrasing as input, and rich presence information including statistics using speaker identification as input.

18. The system of claim 17, wherein the searched information is returned as a list of one or more interactive results further optimized by additional interactive links to additional information relevant to the results.

19. The system of claim 18, wherein the list of results include identified speaker links and the additional information linked to for each result includes all or some of contact information, qualification information, statistical information relevant to the speaker compiled from his or her past conference activity.

20. The system of claim 17, wherein the results link to actual conference segments of transcribed text or actual multimedia files.