Granted Patent B1

US 9,773,501 · App. 15/400,433 · Granted Sep 26, 2017

Inventors: Scot Lorin Brooksby (Highland, UT); Adam Montero (Midvale, UT); Merle Lamar Walker, III (Sandy, UT)

Assignee: Sorenson IP Holdings, LLC

G10L15/265H04N7/147

Abstract

Claims (54)

1. A computer-implemented method to transcribe a communication session

between devices, the method comprising:

establishing a video communication session between a first device and a second device using a communication system such that first device video and first device audio is sent from the first device to the second device and second device video and second device audio is sent from the second device to the first device;

during the video communication session:

receiving the first device audio and the second device audio at the communication system;

duplicating, by the communication system, the first device audio and the second device audio to generate duplicated first device audio and duplicated second device audio;

routing, by the communication system, the second device audio to the first device;

routing, by the communication system, the first device audio to the second device;

separately routing, by the communication system, the duplicated first device audio and the duplicated second device audio to a transcription system;

generating, in substantially real-time by the transcription system through a first process, second transcript data of the duplicated second device audio, the second transcript data including a transcription of the duplicated second device audio; and

routing the second transcript data to the first device for presentation of the transcription of the second device audio by the first device in substantially real-time and substantially synchronized with presentation of the second device audio by the first device during the video communication session; and

generating, by the transcription system through a second process separate from the first process, first transcript data of the duplicated first device audio, the first transcript data including a transcription of the duplicated first device audio, the generation of the first transcript data not occurring in substantially real-time such that the generation of the first transcript data occurs after termination of the video communication session.

2. The method of claim 1 , further comprising combining the first transcript data and the second transcript data to generate third transcript data that includes a combined transcription of the transcription of the first device audio and the transcription of the second device audio.

3. The method of claim 2 , wherein the first transcript data and the second transcript data are interweaved to create the third transcript data such that the combined transcription included in the third transcript data is substantially in chronological order.

4. The method of claim 3 , wherein:

the first transcript data includes a plurality of first data segments, each of the plurality of first data segments includes a first time stamp and one or more first words in the transcription of the first device audio,

the second transcript data includes a plurality of second data segments, each of the plurality of second data segments includes a second time stamp and one or more second words in the transcription of the second device audio, and

the first transcript data and the second transcript data are interweaved based on the first time stamps of the first data segments and the second time stamps of the second data segments.

5. The method of claim 1 , further comprising:

obtaining a request for the video communication session at the communication system from a first device; and

in response to obtaining the request, selecting the second device from a plurality of second devices to participate in the communication session.

6. The method of claim 5 , further comprising:

obtaining user data of a user associated with the first device from a server in the communication system, the user data including a medical condition of the user; and

selecting the second device from the plurality of second devices to participate in the communication session based on the medical condition of the user.

7. One or more non-transitory media configured to store instructions that in response to being executed by one or more processors cause the communication system and/or the transcription system to perform the method of claim 1 .

8. A computer-implemented method to transcribe a communication session between devices, the method comprising:

establishing a communication session between a first device and a second device such that first device audio is sent from the first device to the second device and second device audio is sent from the second device to the first device;

receiving the first device audio and the second device audio;

generating first transcript data of the first device audio, the first transcript data including a transcription of the first device audio;

generating, in substantially real-time during the communication session, second transcript data of the second device audio, the second transcript data including a transcription of the second device audio such that the second transcript data is presentable substantially synchronized with the second device audio presented during the communication session, the generation of the first transcript data not occurring in substantially real-time during the communication session such that the first transcript data is not presentable substantially synchronized with the first device audio presented during the communication session and at least a portion of the first transcript data is generated after termination of the communication session;

routing the second device audio to the first device; and

routing the first device audio to the second device.

9. The method of claim 8 , further comprising duplicating the first device audio and the second device audio to generate duplicated first device audio and duplicated second device audio, the first transcript data generated using the duplicated first device audio and the second transcript data generated using the duplicated second device audio.

10. The method of claim 8 , further comprising routing the second transcript data to the first device for presentation of the transcription of the second device audio by the first device in substantially real-time with presentation of the second device audio by the first device during the communication session.

11. The method of claim 8 , further comprising combining the first transcript data and the second transcript data to generate third transcript data that includes a combined transcription of the transcription of the first device audio and the transcription of the second device audio.

12. The method of claim 11 , wherein the first transcript data and the second transcript data are interweaved to create the third transcript data such that the combined transcription included in the third transcript data is substantially in chronological order.

13. The method of claim 8 , wherein the communication session is a video communication session.

14. One or more non-transitory media configured to store instructions that in response to being executed by one or more processors cause one or more systems to perform the method of claim 8 .

15. A computer-implemented method to transcribe a communication session between devices, the method comprising:

establishing a communication session between a first device and a second device such that the second device obtains first device audio from the first device and the first device obtains second device audio from the second device;

receiving the first device audio and the second device audio;

duplicating the first device audio and the second device audio to generate duplicated first device audio and duplicated second device audio;

routing the second device audio to the first device;

routing the first device audio to the second device;

routing the duplicated first device audio and the duplicated second device audio to a transcription system;

obtaining second transcript data of the duplicated second device audio, the second transcript data including a transcription of the duplicated second device audio;

routing the second transcript data in substantially real-time to the first device for presentation of the transcription of the second device audio by the first device in substantially real-time and substantially synchronized with presentation of the second device audio by the first device during the communication session;

obtaining first transcript data of the duplicated first device audio, the first transcript data including a transcription of the duplicated first device audio; and

routing the first transcript data to the second device after the communication session.

16. The method of claim 15 , further comprising:

obtaining a request for the communication session from a first device; and

in response to obtaining the request, selecting the second device from a plurality of second devices to participate in the communication session.

17. The method of claim 16 , wherein the first transcript data is routed to the second device for presentation of the transcription of the first device audio by the second device.

18. One or more non-transitory media configured to store instructions that in response to being executed by one or more processors cause one or more systems to perform the method of claim 15 .

Assignments (9)