Teleconference recording management system

• US 10,582,063 B2
• Filed: 12/12/2017
• Issued: 03/03/2020
• Est. Priority Date: 12/12/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: De Angelis, Fabio, Balestrazzi, Luca, Napoleoni, Andrea, Sidoti, Stefano
• Primary Examiner(s): Wozniak, James S
• Application Number:
  US15/839,046
• Publication Number:
  US 20190182384A1
• Time in Patent Office: 812 Days
• Field of Search: 700 94, 704235, 704270, 7042701
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• 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 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/561 by multiplexing
• 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

An example operation may include one or more of receiving a plurality of local audio files from a plurality of audio devices that participated in a teleconference, where each local audio file includes a locally captured audio recording of a user of a respective audio device during the teleconference, generating combined audio playback information for the teleconference based on the plurality of local audio files received from the plurality of audio devices, the generating including detecting audio portions within the plurality of local audio files and synchronizing a playing order of the detected audio portions based on timing information included in the plurality of local audio files, and transmitting the combined audio playback information of the teleconference to at least one audio device among the plurality of audio devices.

Claims

1. A computing system, comprising:

a network interface configured to receive a plurality of local audio files from a plurality of audio devices that participated in a teleconference, each local audio file comprising an audio recording of a local participant user of a respective audio device that prevents recording of speech of non-local participant users during the teleconference, and receive audio timing information of a non-consenting audio device which participated in the teleconference but which did not share local audio; and

a processor configured to generate combined audio playback information for the teleconference based on the plurality of local audio files received from the plurality of audio devices which include detected audio portions within the plurality of local audio files and which excludes an audio segment that was not shared by the non-consenting audio device and synchronize a playing order of the detected audio portions based on the audio timing information from the non-consenting audio device which did not share local audio,

wherein the processor is further configured to control the network interface to transmit the combined audio playback information of the teleconference to at least one audio device among the plurality of audio devices.

2. The computing system of claim 1, wherein the processor is configured to queue the detected audio portions from the plurality of local audio files in chronological order based on timing information included in the plurality of local audio files and the audio timing information from the non-consenting audio device to prevent the detected audio portions from overlapping during audio playback.

3. The computing system of claim 2, wherein the processor is configured to queue a first chronologically detected audio portion from a first local audio file to begin playback, and queue a next chronologically detected audio portion to begin playback only after playing of the first chronologically detected audio portion has ended.

4. The computing system of claim 1, wherein the processor is configured to modify a timing of a playback of a second audio portion that overlaps with a playback of a first audio portion such that when played the second audio portion no longer overlaps the first audio portion.

5. The computing system of claim 1, wherein the processor is further configured to receive an authorization from a respective audio device for use of a respective local audio file prior to generating the combined audio playback information.

6. The computing system of claim 1, wherein each local audio file is generated by filtering out speech and noise of other users of the teleconference while performing the recording and keeping speech of the local participant user of the respective audio device.

7. The computing system of claim 1, wherein the processor is further configured to convert speech from the plurality of local audio files to text, merge the converted text into chronological order to generate a single combined text file, and control the network interface to transmit the combined text file along with the combined audio playback information.

8. The computing system of claim 7, wherein the processor is further configured to perform post-conversation processing on the converted text to remove words that are not of interest when generating the single combined text file.

9. The computing system of claim 1, wherein the processor is further configured to control the network interface to transmit an audio recording synchronization timestamp to each of the plurality of audio devices participating in the teleconference at a start of the teleconference, wherein the audio recording synchronization timestamp is configured to synchronize generation of the plurality of local audio files.

10. The computing system of claim 1, wherein the audio timing information from the non-consenting audio device comprises an identification of a start time and a stop time of the audio segment from the teleconference of the non-consenting audio device without sharing the audio segment.

11. The computing system of claim 10, wherein the processor is configured to shorten an overall playback time of the teleconference by skipping over the audio segment of the non-consenting audio device based on the start time and the stop time included in the audio timing information of the non-consenting audio device and queueing a next received audio segment of a consenting audio device in chronological order within the combined audio playback information.

12. A computer-implemented method comprising:

receiving a plurality of local audio files from a plurality of audio devices that participated in a teleconference, each local audio file comprising an audio recording of a local participant user of a respective audio device that prevents recording of speech of non-local participant users during the teleconference;

receiving audio timing information of a non-consenting audio device which participated in the teleconference but which did not share local audio;

generating combined audio playback information for the teleconference based on the plurality of local audio files received from the plurality of audio devices which include detected audio portions within the plurality of local audio files and which excludes an audio segment that was not shared by the non-consenting audio device by synchronizing a playing order of the detected audio portions based on the audio timing information from the non-consenting audio device which did not share local audio; and

transmitting the combined audio playback information of the teleconference to at least one audio device among the plurality of audio devices.

13. The computer-implemented method of claim 12, wherein the synchronizing comprises queuing the detected audio portions from the plurality of local audio files in chronological order based on timing information included in the plurality of local audio files and the audio timing information from the non-consenting audio device to prevent the detected audio portions from overlapping during audio playback.

14. The computer-implemented method of claim 13, wherein the queuing comprises queuing a first chronologically detected audio portion from a first local audio file to begin playback, and queuing a next chronologically detected audio portion to begin playback only after playing of the first chronologically detected audio portion has ended.

15. The computer-implemented method of claim 12, wherein the synchronizing comprises modifying a timing of a playback of a second audio portion that overlaps with a playback of a first audio portion such that when played the second audio portion no longer overlaps the first audio portion.

16. The computer-implemented method of claim 12, further comprising receiving authorization from a respective audio device for use of a respective local audio file prior to generating the combined audio playback information.

17. The computer-implemented method of claim 12, wherein each local audio file is generated by filtering out speech and noise of other users of the teleconference while performing the recording and keeping speech of the local participant user of the respective audio device.

18. The computer-implemented method of claim 12, further comprising converting speech from the plurality of local audio files to text, merging the converted text into chronological order to generate a single combined text file, and outputting the single combined text file along with the combined audio playback information.

19. The computer-implemented method of claim 18, further comprising performing post-conversation processing on the converted text to remove words that are not of interest when generating the single combined text file.

20. The computer-implemented method of claim 12, further comprising transmitting an audio recording synchronization timestamp to each of the plurality of audio devices participating in the teleconference at a start of the teleconference, wherein the audio recording synchronization timestamp is configured to synchronize generation of the plurality of local audio files.

21. A non-transitory computer readable medium having stored therein program instructions that when executed cause a computer to perform a method comprising:

receiving a plurality of local audio files from a plurality of audio devices that participated in a teleconference, each local audio file comprising an audio recording of a local participant user of a respective audio device that prevents recording of speech of non-local participant users during the teleconference;

receiving audio timing information of a non-consenting audio device which participated in the teleconference but which did not share local audio;

generating combined audio playback information for the teleconference based on the plurality of local audio files received from the plurality of audio devices which include detected audio portions within the plurality of local audio files and which excludes an audio segment that was not shared by the non-consenting audio device by synchronizing a playing order of the detected audio portions based on the audio timing information from the non-consenting audio device which did not share local audio; and

transmitting the combined audio playback information of the teleconference to at least one audio device among the plurality of audio devices.

22. The non-transitory computer readable medium of claim 21, wherein the synchronizing comprises queuing the detected audio portions from the plurality of local audio files in chronological order based on timing information included in the plurality of local audio files and the audio timing information from the non-consenting audio device to prevent the detected audio portions from overlapping during audio playback.