System And Method For Facilitating Cognitive Processing Of Simultaneous Remote Voice Conversations

• US 20090259464A1
• Filed: 04/11/2008
• Published: 10/15/2009
• Est. Priority Date: 04/11/2008
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Ducheneaut, Nicolas B., Smith, Trevor F.
• Granted Patent: US 8,265,252 B2
• Time in Patent Office: Days
• US Class Current: 704/232
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

A system and method for facilitating cognitive processing of simultaneous remote voice conversations is provided. A plurality of remote voice conversations participated in by distributed participants are provided over a shared communication channel. A main conversation between at least two of the distributed participants and one or more subconversations between at least two other of the distributed participants are identified from within the remote voice conversations. Segments of interest to one of the distributed participants are defined including a conversation excerpt having a lower attention activation threshold for the one distributed participant. Each of the subconversations is parsed into conversation excerpts. The conversation excerpts are compared to the segments of interest. One or more gaps between conversation flow in the main conversation are predicted. Segments of interest are selectively injected into the gaps of the main conversation as provided to the one distributed participant over the shared communications channel.

Claims

1. A system for facilitating cognitive processing of simultaneous remote voice conversations, comprising:

a communication module configured to receive a plurality of remote voice conversations between distributed participants provided over a shared communications channel;

a floor module to identify from within the remote voice conversations each of a main conversation between at least two of the distributed participants and one or more subconversations between at least two other of the distributed participants;

an identification module to define segments of interest to one of the distributed participants comprising a conversation excerpt having a lower attention activation threshold for the one distributed participant;

an analysis module to parse each of the subconversations into live conversation excerpts and to compare the live conversation excerpts to the segments of interest;

a gap prediction module to continually monitor the main conversation and to predict one or more gaps between conversation flow in the main conversation; and

an injection module to selectively inject the live conversation excerpts into the gaps of the main conversation as provided to the one distributed participant over the shared communications channel.

2. A system according to claim 1, wherein the one distributed participant is at least one of actively involved, in the main conversation and passively listening to the main conversation.

3. A system according to claim 1, further comprising:

a sound module to mute the subconversations as provided to the one distributed participant over the shared communications channel.

4. A system according to claim 1, wherein the segments of interest are selected from the group comprising parts of words, words, sentence fragments, sentences, and sounds.

5. A system according to claim 1, further comprising:

a playback modifier module to apply a playback modifier to the live conversation excerpts; and

a playback presentation module to modify presentation of the live conversation excerpts based on the playback modifier.

6. A system according to claim 5, wherein the playback modifier is selected from the group comprising volume, speed, pitch, and pause length.

7. A system according to claim 1, further comprising one or more of:

a selection module to select at least one of the segments of interest, and an

action module to place the subconversation from which the one segment of interest was comprised as the main conversation; and

a storage module to store the subconversations corresponding to the live conversation excerpts, and a replay module to replay the subconversations upon termination of the main conversation.

8. A method for facilitating cognitive processing of simultaneous remote voice conversations, comprising:

participating in a plurality of remote voice conversations between distributed participants provided over a shared communications channel;

identifying from within the remote voice conversations each of a main conversation between at least two of the distributed participants and one or more subconversations between at least two other of the distributed participants;

defining segments of interest to one of the distributed participants comprising a conversation excerpt having a lower attention activation threshold for the one distributed participant;

parsing each of the subconversations into live conversation excerpts and comparing the live conversation excerpts to the segments of interest;

continually monitoring the main conversation and predicting one or more gaps between conversation flow in the main conversation; and

selectively injecting the live conversation excerpts into the gaps of the main conversation as provided to the one distributed participant over the shared communications channel.

9. A method according to claim 8, wherein the one distributed participant is at least one of actively involved in the main conversation and passively listening to the main conversation.

10. A method according to claim 8, further comprising:

muting the subconversations as provided to the one distributed participant over the shared communications channel.

11. A method according to claim 8, wherein the segments of interest are selected from the group comprising parts of words, words, sentence fragments, sentences, and sounds.

12. A method according to claim 8, further comprising:

applying a playback modifier to the live conversation excerpts; and

modifying presentation of the live conversation excerpts based on the playback modifier.

13. A method according to claim 12, wherein the playback modifier is selected from the group comprising volume, speed, pitch, and pause length.

14. A method according to claim 8, further comprising one or more of:

selecting at least one of the segments of interest, and placing the subconversation from which the one segment of interest was comprised as the main conversation; and

storing the subconversations corresponding to the live conversation excerpts, and replaying the subconversations upon termination of the main conversation.

15. A system for providing conversation excerpts to a participant from simultaneous remote voice conversations, comprising:

a communication module configured to receive a plurality of remote voice conversations between distributed participants provided over a shared communications channel;

a floor module to identify from within the remote voice conversations each of a main conversation in which one of the distributed participants is actively involved and one or more subconversations between at least two other of the distributed participants;

an identification module to define segments of interest to the one of the distributed participants comprising a conversation excerpt having a lower attention activation threshold for the one distributed participant;

a sound module to mute the subconversations as provided to the one distributed participant over the shared communications channel;

an analysis module to parse each of the subconversations into live conversation excerpts and to compare the live conversation excerpts to the segments of interest;

a gap prediction module to continually monitor the main conversation and to predict, one or more gaps between conversation flow in the main conversation; and

an injection module to selectively inject the live conversation excerpts into the gaps of the main conversation as provided to the one distributed participant over the shared communications channel.

16. A system according to claim 15, wherein the identification module further comprises:

a criteria module to define a selection criteria for the one distributed participant; and

a segment selection module to identify segments of interest based on the selection criteria.

17. A system according to claim 16, wherein the selection criteria is selected from the group comprising personal details, interests, projects, terms, and term frequency.

18. A system according to claim 15, further comprising one or more of:

a selection module to select at least one of the segments of interest, and an action module to place the subconversation from which the one segment of interest was comprised as the main conversation; and

a storage module to store the subconversations corresponding to the live conversation excerpts, and a replay module to replay the subconversations upon termination of the main conversation.

19. A system according to claim 15, wherein the segments of interest are selected from the group comprising parts of words, words, sentence fragments, sentences, and sounds.

20. A method for providing conversation excerpts to a participant from simultaneous remote voice conversations, comprising:

actively participating in a plurality of remote voice conversations between distributed participants provided over a shared communications channel;

identifying from within the remote voice conversations each of a main conversation in which one of the distributed participants is actively involved and one or more subconversations between at least two other of the distributed participants;

defining segments of interest to the one of the distributed participants comprising a conversation excerpt having a lower attention activation threshold for the one distributed participant;

muting the subconversations as provided to the one distributed participant over the shared communications channel;

parsing each of the subconversations into live conversation excerpts and comparing the live conversation excerpts to the segments of interest;

continually monitoring the main conversation and predicting one or more gaps between conversation flow in the main conversation; and

selectively injecting the live conversation excerpts into the gaps of the main conversation as provided to the one distributed participant over the shared communications channel.

21. A method according to claim 20, further comprising:

defining a selection criteria for the one distributed participant; and

identifying segments of interest based on the selection criteria.

22. A method according to claim 21, wherein the selection criteria is selected from the group comprising personal details, interests, projects, terms, and term frequency.

23. A method according to claim 20, further comprising one or more of:

selecting at least one of the segments of interest, and placing the subconversation from which the one segment of interest was comprised as the main conversation; and

storing the subconversations corresponding to the live conversation excerpts, and replaying the subconversations upon termination of the main conversation.

24. A method according to claim 20, wherein the segments of interest are selected from the group comprising parts of words, words, sentence fragments, sentences, and sounds.