Issuing alerts on detection of contents of interest introduced during a conference

• US 8,731,935 B2
• Filed: 09/10/2009
• Issued: 05/20/2014
• Est. Priority Date: 09/10/2009
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Chavez, Timothy R., Eisinger, Jacob Daniel, King, Jennifer Elizabeth, Reichert, William R.
• Primary Examiner(s): Han, Qi
• Application Number:
  US12/556,667
• Publication Number:
  US 20110060591A1
• Time in Patent Office: 1,713 Days
• Field of Search: 704/270, 704/232, 704/252, 704/246, 704/231, 704/251
• US Class Current: 704/270
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04L 65/1083 In-session procedures
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/563 User guidance or feature selection

Abstract

A method, system, and computer program product for issuing an alert in response to detecting a content of interest in a conference. A listening logic comprising multiple conference engines monitors speakers, topics, and words spoken during a conference. A speech-to-text engine monitors the conference and records a transcription. A word emphasis engine monitors the transcription for key words. A voice identification engine monitors the live conversation and the recorded transcript, in real time, for a particular individual to begin speaking. An outline engine may create an outline of transcription. The listening device may issue an alert upon detecting a content of interest in the conference. The listening device may additionally display an outline or a selected portion of the transcript regarding a particular content of interest to inform a user of the listening device of a portion of content of the conference that may have been missed.

Claims

1. A method for issuing an alert in response to detecting a content of interest in a conference, the method comprising:

reading a plurality of monitoring preferences for a conference, including;

(a) preferences for monitoring and recording verbal utterances exchanged during the conference, and

(b) preferences for determining contents of interest of the conference, wherein each content of interest corresponds to one or more items from a group consisting of specific topics, specific persons, and specific names;

determining one or more target contents of interest of the conference;

based on the monitoring preferences, monitoring verbal utterances exchanged during the conference to;

i. determine an occurrence of one or more contents of interest, and

ii. produce a real time transcript of the verbal utterances including providing a name of a corresponding utterance speaker for each utterance; and

in response to detecting a content of interest, simultaneously;

i. displaying a selected portion of the transcript related to the detected content of interest, and

ii. issuing one or more alert notifications alerting of the occurrence of an identified content of interest of the conference.

2. The method of claim 1, wherein the alert is a visual alert, and issuing one or more the visual alerts further comprises at least one of:

providing an on-screen flash on a display,

displaying an alert window on the display, and

presenting a text notification message on the display.

3. The method of claim 2, wherein the visual alert contains information relevant to the detected content of interest and is accompanied by a simultaneous display of a portion of the transcript related to the detected content of interest including what each speaker has recently said regarding the specified content of interest.

4. The method of claim 1, wherein recording a transcript further comprises:

determining a speaker of a particular portion of the detected content; and

tagging portions of the transcript to actual words spoken by each individual speaker of the conference, in their order of occurrence.

5. The method of claim 1, further comprising creating at least one of a data graph and a data outline of the transcript, wherein the data graph is a representation of the conferences using visual shapes and text.

6. The method of claim 1, wherein the alert is an audible alert from among a specific sound sample to alert a user to detection of the content of interest, wherein the sound sample is one of a pre-recorded sound effect or recording, a voice alert, and a snippet of a portion of the conference.

7. The method of claim 1, wherein the alert is an audible alert and wherein issuing one or more alerts comprises raising an audio volume level of the conference.

8. The method of claim 1, wherein the alert is a vibration pulse alert that has a particular pattern or sequence of pulses to alert the user to specific contents of interest.

9. A listening device comprising:

a processor;

a memory coupled to the processor;

processing logic executing on the processor that causes the listening device to;

read a plurality of monitoring preferences for a conference, including;

(a) preferences for monitoring and recording verbal utterances exchanged during the conference, and

(b) preferences for determining contents of interest of the conference wherein each content of interest corresponds to one or more items from a group consisting of specific topics, specific persons, and specific names;

determine one or more target contents of interest of the conference;

monitor, via a listening device based on the monitoring preferences, verbal utterances exchanged during the conference to;

i. determine an occurrence of one or more contents of interest, and

ii. produce a real time transcript of the verbal utterances including providing a name of a corresponding utterance speaker for each utterance; and

in response to detecting a content of interest, simultaneously.;

i. display a selected portion of the transcript related to the detected content of interest, and

ii. issue one or more alert notifications alerting of the occurrence of an identified content of interest of the conference and wherein the alert is one or more of a visual alert, an audible alert, and a vibration pulse alert.

10. The listening device of claim 9, wherein the alert is a visual alert, and the processing logic that causes the device to issue one or more alerts further comprises processing logic that causes the device to perform at least one of:

provide an on-screen flash on a display;

display an alert window on the display; and

present a text message on the display.

11. The listening device of claim 9, wherein the one or more alerts is an audible alert comprises, and the processing logic that causes the device to issue the one or more alerts comprises processing logic that cause the device to perform one or more of:

(a) raise an audio volume level of the conference; and

(b) provide a specific sound sample to alert a user to detection of the content of interest, wherein the sound sample is one of a pre-recorded sound effect or recording, a voice alert, and

a snippet of a portion of the conference.

12. A computer-readable storage device having a plurality of instructions embodied therein, wherein the plurality of instructions, when executed by a processing device, allows a machine to:

read a plurality of monitoring preferences for a conference, the monitoring preferences further comprising;

i. preferences for monitoring and recording verbal utterances exchanged during the conference, and

ii. preferences for determining contents of interest of the conference, wherein each content of interest corresponds to one or more items from a group consisting of specific topics, specific persons, and specific names;

determine one or more target contents of interest of the conference;

monitor, via a listening device based on the monitoring preferences, verbal utterances exchanged during the conference to;

i. determine an occurrence of one or more contents of interest, and

ii. produce a real time transcript of the utterances including providing a name of a corresponding utterance speaker for each utterance; and

in response to detecting a content of interest, simultaneously;

display a selected portion of the transcript related to the detected content of interest, and

ii. issue one or more alert notifications alerting of the occurrence of an identified content of interest of the conference.

13. The computer-readable storage medium of claim 12, wherein the alert is a visual alert, and the instructions that cause the machine to issue the one or more alerts comprises instructions that cause the machine to perform at least one of:

provide an on-screen flash on a display;

display an alert window on the display; and

present a text message on the display.

14. The computer-readable storage medium of claim 12, wherein the alert is an audible alert, and the instructions that cause the machine to issue the one or more alerts comprises instructions that cause the machine to perform one or more of:

(a) raise an audio volume level of the conference; and

(b) provide a specific sound sample to alert a user to detection of the content of interest,

wherein the sound sample is one of a pre-recorded sound effect or recording, a voice alert, and a snippet of a portion of the conference.