Identifying and displaying call participants using voice sample

• US 9,812,131 B2
• Filed: 11/09/2015
• Issued: 11/07/2017
• Est. Priority Date: 11/09/2015
• Status: Active Grant

• Current Assignee: Lenovo Global Technologies International Ltd. (Lenovo Group Ltd.)
• Original Assignee: Lenovo Enterprise Solutions (Singapore) Pte., Ltd. (Lenovo Group Ltd.)
• Inventors: Parker, Emil Paul, Grice, Jonathan Keener, McAlpin, John Thomas
• Primary Examiner(s): Han, Qi
• Application Number:
  US14/936,497
• Publication Number:
  US 20170133018A1
• Time in Patent Office: 729 Days
• Field of Search: 704250, 704246, 704273, 704270
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/08 Use of distortion metrics or a particular distance between probe pattern and reference templates
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: G10L 25/72 for transmitting results of analysis
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 2203/6045 Identity confirmation
• CPC Class Codes: H04M 3/568 audio processing specific to telephonic conferencing, e.g. spatial distribution, mixing of participants echo suppression in two-way loud-speaking telephone systems H04M9/02; sound field processing per se H04S7/30

Abstract

A computer program product, according to one embodiment, includes a computer readable storage medium having program instructions embodied therewith, the program instructions readable and/or executable by a computer to cause the computer to: receive one or more voice signals from one or more participants of a call, correlate each of the one or more received voice signals with speaker profiles in a database, output speaker identification information from the correlated speaker profiles, and send the speaker identification information at least one of the participants of the call. Other systems, methods, and computer program products are described in additional embodiments.

Claims

1. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions being executable by a computer to cause the computer to:

receive one or more voice signals from one or more participants of a telephonic call;

correlate each of the one or more received voice signals with speaker profiles in a database;

output speaker identification information from the correlated speaker profiles;

send the speaker identification information to at least one of the participants of the call; and

discard the received one or more voice signals in response to the speaker identification information from each of the correlated speaker profiles being output,

wherein the speaker identification information is sent to the one or more physical locations while the speaker is creating a voice signal

wherein the speaker identification information is sent for output in a mode selected from a group consisting of;

visually presented on a display screen at each of one or more physical locations and audibly projected by an electrical speaker at each of the one or more physical locations, wherein the mode is selected based on a selection received from each of the one or more physical locations.

2. The computer program product of claim 1, wherein the program instructions are executable by the computer to cause the computer to:

generate a document in response to the call ending, the document being based on the speaker identification information, wherein the document includes a name of each speaker identified by the correlating; and

send the document to each of the speakers identified by the correlating,

wherein the document is sent to each of the speakers via email,

wherein the correlating includes distinguishing between more than one voice signal received from a same physical location.

3. The computer program product of claim 1, wherein the program instructions are executable by the computer to cause the computer to:

send a request for speaker identification information to a supplemental database corresponding to a source of an unidentified voice signal;

redirect the request for speaker identification information to a source location of the unidentified voice signal in response to the request failing to produce speaker identification information from the supplemental database;

receive speaker identification information from the source of the unidentified voice signal;

use the speaker identification information received from the source of the unidentified voice signal to create a new speaker profile in the database; and

integrate the new speaker profile with the supplemental database.

4. The computer program product of claim 3, wherein the program instructions are executable by the computer to cause the computer to:

record a voice sample from the unidentified voice signal;

add the recorded voice sample to the new speaker profile; and

use the new speaker profile to correlate subsequently received voice signals.

5. The computer program product of claim 1, wherein the program instructions are executable by the computer to cause the computer to:

collect one or more voice samples from one or more speakers;

use the one or more voice samples to create a speaker profile for each of the one or more speakers in the database;

populate the speaker profiles with speaker identification information corresponding to each of the one or more speakers; and

collect one or more voice samples from one or more potential speakers, wherein collecting the one or more voice samples from the one or more potential speakers includes;

sending a second request to each of the one or more potential speakers, the second request being to call a specified phone number,

receiving a phone call at the specified phone number from at least one of the one or more potential speakers in response to the second request sent to each of the one or more potential speakers,

establishing a telephonic connection with the at least one of the one or more potential speakers in response to receiving the phone call,

sending a third request to the at least one of the one or more potential speakers via the telephonic connection, the third request being to provide an audio signal by speaking into a microphone of a phone receiver,

receiving the audio signal from the at least one of the one or more potential speakers via the telephonic connection in response to sending the third request, and

using the at least one received audio signal to create at least one of the voice samples,

wherein the third request is for prompting the at least one of the one or more potential speakers to perform at least one action selected from a group consisting of;

provide a vocal response to a series of predetermined questions included in the third request, repeat a series of phrases included in the third request, and read a series of phrases included in the second request.

6. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:

receive at least two voice signals from participants of a telephonic call;

select a first subset of speaker profiles in a database for each of the received voice signals;

select a second subset of speaker profiles in the database for each of the received voice signals;

cross-correlate each of the received voice signals with both of the first and second selected subsets of speaker profiles in the database;

output speaker identification information from the cross-correlated speaker profiles; and

send the speaker identification information to participants of the call located at two or more physical locations,

wherein the speaker identification information is sent to the two or more physical locations while the speaker is creating a voice signal

wherein the speaker identification information is sent for output in a mode selected from a group consisting of;

visually presented on a display screen at each of the two or more physical locations and audibly projected by an electrical speaker at each of the two or more physical locations, wherein the mode is selected based on a selection received from each of the physical locations.

7. The computer program product of claim 6, wherein the first and second subsets of the database are respectively selected based on geographical location information associated with each of the voice signals and a meeting invite list.

8. The computer program product of claim 6, wherein additional subsets of speaker profiles are organized in a hierarchy which determines a correlation priority, wherein the additional subsets of speaker profiles are used according to the correlation priority to perform subsequent correlations with each of the at least two received voice signals in response to determining that the cross-correlation has failed to output speaker identification information for each of the at least two received voice signals.

9. The computer program product of claim 6, wherein the first and second subsets of the database are respectively selected based on time zones associated with each of the voice signals and a meeting invite list.

10. The computer program product of claim 6, wherein the program instructions are executable by the computer to cause the computer to:

discard the at least two received voice signals from the participants of the call in response to the speaker identification information from each of the cross-correlated speaker profiles being output.

11. The computer program product of claim 6, wherein the program instructions are executable by the computer to cause the computer to:

send, by the computer, a request for speaker identification information to a supplemental database corresponding to a source of an unidentified voice signal;

redirect, by the computer, the request for speaker identification information to a source location of the unidentified voice signal in response to the request failing to produce speaker identification information from the supplemental database;

receive, by the computer, speaker identification information from the source of the unidentified voice signal;

use, by the computer, the speaker identification information received from the source of the unidentified voice signal to create a new speaker profile in the database; and

integrate, by the computer, the new speaker profile with the supplemental database.

12. The computer program product of claim 11, wherein the program instructions are executable by the computer to cause the computer to:

record, by the computer, a voice sample from the unidentified voice signal;

add, by the computer, the recorded voice sample to the new speaker profile; and

use, by the computer, the new speaker profile to correlate subsequently received voice signals.

13. The computer program product of claim 6, wherein the program instructions are executable by the computer to cause the computer to:

collect, by the computer, one or more voice samples from one or more potential speakers;

use, by the computer, the one or more voice samples to create a speaker profile for each of the one or more potential speakers in the database; and

populate, by the computer, the speaker profiles with potential speaker identification information corresponding to each of the one or more potential speakers,

wherein collecting the one or more voice samples from the one or more potential speakers includes;

sending a second request to each of the one or more potential speakers, the second request being to call a specified phone number,

receiving a phone call at the specified phone number from at least one of the one or more potential speakers in response to the second request sent to each of the one or more potential speakers,

establishing a telephonic connection with the at least one of the one or more potential speakers in response to receiving the phone call,

sending a third request to the at least one of the one or more potential speakers via the telephonic connection, the third request being to provide an audio signal by speaking into a microphone of a phone receiver,

receiving the audio signal from the at least one of the one or more potential speakers via the telephonic connection in response to sending the third request, and

using the at least one received audio signal to create at least one of the voice samples,

wherein the third request is for prompting the at least one of the one or more potential speakers to perform at least one action selected from a group consisting of;

provide a vocal response to a series of predetermined questions included in the third request, repeat a series of phrases included in the third request, and read a series of phrases included in the second request.

14. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions being executable by a computer to cause the computer to:

receive one or more voice signals from one or more participants of a telephonic call;

correlate each of the one or more received voice signals with speaker profiles in a database;

output speaker identification information from the correlated speaker profiles;

send the speaker identification information to at least one of the participants of the call;

discard the received one or more voice signals in response to the speaker identification information from each of the correlated speaker profiles being output;

send a request for speaker identification information to a supplemental database corresponding to a source of an unidentified voice signal;

redirect the request for speaker identification information to a source location of the unidentified voice signal in response to the request failing to produce speaker identification information from the supplemental database;

receive speaker identification information from the source of the unidentified voice signal;

use the speaker identification information received from the source of the unidentified voice signal to create a new speaker profile in the database; and

integrate the new speaker profile with the supplemental database.

15. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:

receive at least two voice signals from participants of a telephonic call;

select a first subset of speaker profiles in a database for each of the received voice signals;

select a second subset of speaker profiles in the database for each of the received voice signals;

cross-correlate each of the received voice signals with both of the first and second selected subsets of speaker profiles in the database;

output speaker identification information from the cross-correlated speaker profiles; and

send the speaker identification information to participants of the call located at two or more physical locations,

wherein additional subsets of speaker profiles are organized in a hierarchy which determines a correlation priority,

wherein the additional subsets of speaker profiles are used according to the correlation priority to perform subsequent correlations with each of the at least two received voice signals in response to determining that the cross-correlation has failed to output speaker identification information for each of the at least two received voice signals.

16. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:

receive at least two voice signals from participants of a telephonic call;

select a first subset of speaker profiles in a database for each of the received voice signals;

select a second subset of speaker profiles in the database for each of the received voice signals;

cross-correlate each of the received voice signals with both of the first and second selected subsets of speaker profiles in the database;

output speaker identification information from the cross-correlated speaker profiles; and

send the speaker identification information to participants of the call located at two or more physical locations;

send, by the computer, a request for speaker identification information to a supplemental database corresponding to a source of an unidentified voice signal;

redirect, by the computer, the request for speaker identification information to a source location of the unidentified voice signal in response to the request failing to produce speaker identification information from the supplemental database;

receive, by the computer, speaker identification information from the source of the unidentified voice signal;

use, by the computer, the speaker identification information received from the source of the unidentified voice signal to create a new speaker profile in the database; and

integrate, by the computer, the new speaker profile with the supplemental database.

17. A method, comprising:

receiving one or more voice signals from one or more participants of a telephonic call;

correlating each of the one or more received voice signals with speaker profiles in a database;

outputting speaker identification information from the correlated speaker profiles;

sending the speaker identification information to at least one of the participants of the call; and

discarding the received one or more voice signals in response to the speaker identification information from each of the correlated speaker profiles being output,

wherein the speaker identification information is sent to the one or more physical locations while the speaker is creating a voice signal

wherein the speaker identification information is sent for output in a mode selected from a group consisting of;

visually presented on a display screen at each of one or more physical locations and audibly projected by an electrical speaker at each of the one or more physical locations, wherein the mode is selected based on a selection received from each of the one or more physical locations.