Transcription generation

Patent metadata

Field	Value
Publication number	US-12340806-B2
Application number	US-202217664751-A
Country	US
Kind code	B2
Filing date	May 24, 2022
Priority date	May 24, 2022
Publication date	Jun 24, 2025
Grant date	Jun 24, 2025

Abstract

A method of transcript presentation may include generating, by a device, audio data by capturing via a microphone of the device an audible audio signal that is broadcast by the device. The audible audio signal may include words. The method may also include obtaining, at the device, transcript data. The transcript data may be generated using the audio data and may include a transcription of the words of the audible audio data. The method may also include presenting, by the device, the transcription.

First claim

I claim:

1. A device, comprising:
a speaker configured to broadcast an audible audio signal based on first audio data;
a microphone configured to generate second audio data based on the audible audio signal broadcast by the speaker;
a display configured to present transcript data; and
a processing system configured to:
obtain the first audio data during a communication session controlled by a native application running on the processing system, the native application not allowing non-native applications access to the first audio data;
direct, via the native application, the first audio data to the speaker;
direct, via a non-native application, the microphone to generate the second audio data;
obtain, via the non-native application, the second audio data from the microphone;
obtain, via the non-native application, the transcript data, the transcript data generated using the second audio data and including a transcription of the second audio data; and
direct, via the non-native application, the transcript data to the display.

2. The device of claim 1 , further comprising:
a communication unit configured to:
direct the second audio data generated by the microphone to a transcription system;
receive the transcript data from the transcription system; and
direct the transcript data to the processing system, such that the processing system obtains the transcript data from the communication unit.

3. The device of claim 2 , wherein the communication unit is further configured to receive first audio data, the first audio data resulting from the communication session that is between the device and a remote device, wherein the first audio data originates at the remote device.

4. The device of claim 1 , further comprising:
a communication unit configured to:
before the speaker broadcasts the first audio data, receive the first audio data, the first audio data resulting from the communication session that is between the device and a remote device, wherein the first audio data originates at the remote device.

5. The device of claim 1 , wherein the processing system is configured to obtain the transcript data by generating the transcript data using a speech recognition algorithm.

6. The device of claim 1 , wherein the display is configured to present the transcript data in substantially real-time with the generation of the second audio data by the microphone.

7. The device of claim 1 , wherein the microphone is further configured to generate third audio data that is not based on audible audio broadcast by the speaker.

8. The device of claim 7 , wherein the second audio data and the third audio data are included in a single audio channel and the processing system is further configured to divide the second audio data from the single audio channel, wherein the transcript data includes the transcription for the second audio data and does not include a transcription of the third audio data.

9. The device of claim 7 , wherein the transcript data includes first transcript data for the second audio data and second transcript data for the third audio data.

10. The device of claim 9 , wherein the transcript data includes data to distinguish between the first transcript data and the second transcript data.

11. A method of transcript presentation, the method comprising:
obtaining first audio data during a communication session between a device and a remote device, the communication session controlled by a native application running on the device, the native application not allowing non-native applications access to the first audio data;
directing, via the native application, the first audio data to a speaker to broadcast the first audio data as an audible audio signal;
directing, via a non-native application running on the device, a microphone to generate second audio data based on the audible audio signal broadcast by the speaker;
obtaining, via the non-native application, the second audio data from the microphone;
obtaining, at the device via the non-native application, transcript data, the transcript data generated using the second audio data and including a transcription of the second audio data; and
presenting, by the device, the transcript data.

12. The method of claim 11 , further comprising directing the second audio data to a transcription system, wherein the transcript data is obtained by the device from the transcription system.

13. The method of claim 11 , wherein obtaining the transcript data includes generating the transcript data using a speech recognizer and the second audio data.

14. The method of claim 11 , wherein the first audio data originates at the remote device.

15. The method of claim 11 , wherein the transcript data is presented in substantially real-time with the broadcasting of the audible audio signal by the device.

16. The method of claim 11 , further comprising generating, by the device, third audio data that is not based on the audible audio signal broadcast by the device.

17. The method of claim 16 , wherein the transcript data includes the transcription for the first audio data and does not include a transcription of the third audio data.

18. The method of claim 16 , wherein the transcript data includes first transcript data for the first audio data and second transcript data for the third audio data.

19. At least one non-transitory computer-readable media configured to store one or more instructions that, in response to being executed by the device, cause or direct the device to perform the method of claim 11 .

Assignees

• Sorenson Ip Holdings Llc

Inventors

• Thomson David

Classifications

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L21/0272

  Voice signal separating · CPC title

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title