Granted Patent B2

US 12,664,987 · App. 18/534,852 · Granted Jun 23, 2026

Inventors: Goutham Prasad Madhava (Monroe, CT); Elias Koutikas (Oxford, CT); Matthew Samuel Murphy (Baldwin Place, NY)

Assignee: IPC Systems, Inc.

G10L15/26H04L65/1104

Abstract

Claims (61)

1 . A system for transcribing audio calls during a trading session, the system comprising:

one or more processors; and

one or more memory devices coupled to the one or more processors and storing data instructions that, when executed by the one or more processors, cause the one or more processors to:

feed, during an audio call, a stream of audio signals transmitted by a communications device via a user-selected communications line to a transcription system; and

provide, during the audio call, communication dynamics metadata generated by the communications device to an application programming interface (API) gateway, the communications dynamics metadata being configured to be retrieved via the API gateway by the transcription system, the communication dynamics metadata indicating at least one of:

(i) an audio source of a plurality of audio sources of the communications device;

(ii) a type of the user-selected communications line;

(iii) a type of a switch on the communications device that has been activated to enable a user's voice received at the communications device to be transmitted as the stream of audio signals via the user-selected communications line;

(iv) a first time when the switch was activated and a later second time when the switch was deactivated; or

(v) a third time between the first time and the second time when the stream of audio signals began;

wherein the communications dynamics metadata is embedded in call events associated with the audio call;

wherein the call events are provided to the API gateway; and

wherein the API gateway converts the call events into one or more data storage files.

2 . The system of claim 1 , wherein the stream of audio signals and the communication dynamics metadata are configured in one or more data formats that enable the transcription system to:

transcribe the stream of audio signals into text; and

tag the text with the communication dynamics metadata.

3 . The system of claim 2 ,

wherein the stream of audio signals and the communications dynamics metadata have associated therewith a same identifier, the identifier being associated with the communications device; and

wherein the identifier is configured to be used by the transcription system to tag the text with the communications dynamics metadata.

4 . The system of claim 1 , wherein the API gateway is configured to enable a differently configured transcription system to retrieve the communication dynamics metadata from the API gateway.

5 . The system of claim 1 , further comprising a user application configured to extract the communications dynamics metadata from the one or more data storage files to provide extracted metadata.

6 . The system of claim 5 , wherein the extracted metadata is configured to be retrieved by the transcription system from the user application to tag, by the transcription system, transcribed text of the stream of audio signals with the extracted metadata.

7 . The system of claim 1 , wherein the call events include one or more communications devices joining a call, a push-to-talk switch being activated, or a push-to-talk switch being de-activated.

8 . The system of claim 1 , further comprising the transcription system.

9 . The system of claim 1 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to:

receive, via a user interface, an address for the transcription system, the receive enabling the transcription system to retrieve the communications dynamics metadata via the API gateway.

10 . A non-transitory computer-readable medium having stored thereon one or more sequences of instructions for causing one or more processors to perform:

feeding, during an audio call, a stream of audio signals transmitted by a communications device via a user-selected communications line to a transcription system; and

providing, during the audio call, communication dynamics metadata generated by the communications device to an application programming interface (API) gateway, the communications dynamics metadata being configured to be retrieved via the API gateway by the transcription system, the communication dynamics metadata indicating at least one of:

(i) an audio source of a plurality of audio sources of the communications device;

(ii) a type of the user-selected communications line;

(iii) a type of a switch on the communications device that has been activated to enable a user's voice received at the communications device to be transmitted as the stream of audio signals via the user-selected communications line;

(iv) a first time when the switch was activated and a later second time when the switch was deactivated; or

(v) a third time between the first time and the second time when the stream of audio signals began;

wherein the communications dynamics metadata is embedded in call events associated with the audio call;

wherein the call events are provided to the API gateway; and

wherein the API gateway converts the call events into one or more data storage files.

11 . The non-transitory computer readable medium of claim 10 , wherein the stream of audio signals and the communication dynamics metadata are configured in one or more data formats that enable the transcription system to:

transcribe the stream of audio signals into text; and

tag the text with the communication dynamics metadata.

12 . The non-transitory computer readable medium of claim 11 ,

wherein the stream of audio signals and the communications dynamics metadata have associated therewith a same identifier, the identifier being associated with the communications device; and

wherein the identifier is configured to be used by the transcription system to tag the text with the communications dynamics metadata.

13 . The non-transitory computer readable medium of claim 10 , wherein the API gateway is configured to enable a differently configured transcription system to retrieve the communication dynamics metadata from the API gateway.

14 . The non-transitory computer readable medium of claim 10 , wherein the one or more processors are further caused to perform:

causing a user application to extract the communications dynamics metadata from the one or more data storage files to provide extracted metadata.

15 . The non-transitory computer readable medium of claim 14 , wherein the extracted metadata is configured to be retrieved by the transcription system from the user application to tag, by the transcription system, transcribed text of the stream of audio signals with the extracted metadata.

16 . The non-transitory computer readable medium of claim 10 , wherein the call events include one or more communications devices joining a call, a push-to-talk switch being activated, or a push-to-talk switch being de-activated.

17 . The non-transitory computer readable medium of claim 10 , wherein the one or more processors are further caused to perform:

receiving, via a user interface, an address for the transcription system, the receive enabling the transcription system to retrieve the communications dynamics metadata via the API gateway.

18 . A computer implemented method, comprising:

feeding, during an audio call, a stream of audio signals transmitted by a communications device via a user-selected communications line to a transcription system; and

providing, during the audio call, communication dynamics metadata generated by the communications device to an application programming interface (API) gateway, the communications dynamics metadata being configured to be retrieved via the API gateway by the transcription system, the communication dynamics metadata indicating at least one of:

(i) an audio source of a plurality of audio sources of the communications device;

(ii) a type of the user-selected communications line;

(iii) a type of a switch on the communications device that has been activated to enable a user's voice received at the communications device to be transmitted as the stream of audio signals via the user-selected communications line;

(iv) a first time when the switch was activated and a later second time when the switch was deactivated; or

(v) a third time between the first time and the second time when the stream of audio signals began;

wherein the communications dynamics metadata is embedded in call events associated with the audio call;

wherein the call events are provided to the API gateway; and

wherein the API gateway converts the call events into one or more data storage files.

Assignments (2)

Continuity (1)

References Cited (31)