# US 2023/0410815 A1 · Transcription generation technique selection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0410815 A1
- Document ID: US20230410815A1
- Status: Published application
- Kind: A1
- Application number: 18/457,184
- Filed: 2023-08-28
- Published: 2023-12-21
- Earliest claimed: 2020-05-27
- Assignees: Sorenson IP Holdings, LLC
- Applicants: Sorenson IP Holdings, LLC
- Inventors: David Thomson
- Web page: https://patentgrep.com/patent/US20230410815A1

## CPC

- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G06F 18/2178: {based on feedback of a supervisor}
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
- G10L 21/10: Transforming into visible information
- G10L 15/01: Assessment or evaluation of speech recognition systems
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method to transcribe communications may include selecting a first transcription generation technique from among multiple transcription generation techniques for generating transcriptions of audio of one or more communication sessions that involve a user device and obtaining performances of the multiple transcription generation techniques with respect to generating the transcriptions of the audio. The method may also include monitoring comparisons between the performances of the multiple transcription generation techniques and obtaining input from the user with respect to the comparisons. The method may further include selecting a second transcription generation technique from among the multiple transcription generation techniques based on the input from the user.

## Claims

### Claim 1

A method to transcribe communications, the method comprising:
obtaining a performance of a first transcription generation technique with respect to generating transcriptions of audio of a first communication session associated with a user;
obtaining a performance of a second transcription generation technique with respect to generating transcriptions of the audio of the first communication session;
determining a report based on the performance of the first transcription generation technique and the performance of the second transcription generation technique;
directing the report to a first device associated with the user;
in response to the report, obtaining an indication from the first device; and
directing a transcription of a second communication session to a second device for presentation to the user, the transcription being generated by the second transcription generation technique in response to the indication from the first device.

### Claim 2 (depends on 1)

The method of claim 1, wherein the performance of the second transcription generation technique is based on one or more of the following: transcription accuracy, transcription latency, and number of transcription corrections.

### Claim 3 (depends on 2)

The method of claim 2, wherein the performance of the second transcription generation technique is based on a plurality of communications sessions that include the first communication session.

### Claim 4 (depends on 1)

The method of claim 1, wherein the report includes a recommendation for the second transcription generation technique and the indication includes a selection of the second transcription generation technique.

### Claim 5 (depends on 1)

The method of claim 1, wherein the first device and the second device are the same device.

### Claim 6 (depends on 1)

The method of claim 1, further comprising before determining the report, directing a second transcription of the first communication session that involves the second device to the second device, the second transcription generated by the first transcription generation technique.

### Claim 7 (depends on 6)

The method of claim 6, wherein the steps of directing the report and of obtaining the indication occur during the first communication session.

### Claim 8 (depends on 7)

The method of claim 7, wherein the first communication session and the second communication session are the same communication session.

### Claim 9 (depends on 1)

The method of claim 1, wherein one of the first transcription generation technique and the second transcription generation technique includes a revoicing of audio before transcription generation.

### Claim 10 (depends on 1)

At least one non-transitory computer-readable media configured to store one or more instructions that when executed by at least one processor cause or direct a system to perform the method of claim 1.

### Claim 11

A method to transcribe communications, the method comprising:
selecting a first transcription generation technique from among a plurality of transcription generation techniques for generating transcriptions of audio of one or more communication sessions that involve a user device;
obtaining performances of the plurality of transcription generation techniques with respect to generating the transcriptions of the audio;
monitoring comparisons between the performances of the plurality of transcription generation techniques;
obtaining input from the user with respect to the comparisons; and
selecting a second transcription generation technique from among the plurality of transcription generation techniques based on the input from the user.

### Claim 12 (depends on 11)

The method of claim 11, wherein the performances of the plurality of transcription generation techniques are based on one or more of the following: transcription accuracy and transcription latency.

### Claim 13 (depends on 11)

The method of claim 11, further comprising directing a report to the user based on the comparison, wherein the input is obtained in response to report.

### Claim 14 (depends on 11)

The method of claim 11, wherein the second transcription generation technique does not generate a transcription of the audio such that the performance of the second transcription generation technique is an estimated performance.

### Claim 15 (depends on 11)

The method of claim 11, wherein the selection of the first transcription generation technique is based on the performance of the first transcription generation technique.

### Claim 16 (depends on 11)

The method of claim 11, wherein monitoring comparisons between the performances of the plurality of transcription generation techniques occur with respect to a first communication session that involves the user device.

### Claim 17 (depends on 16)

The method of claim 16, wherein the second transcription generation technique is selected to generate transcriptions of audio for a second communication session that involves the user device and that occurs after the first communication session.

### Claim 18 (depends on 16)

The method of claim 16, the second transcription generation technique is selected to generate transcriptions of audio of the first communication session during the first communication session.

### Claim 19 (depends on 11)

At least one non-transitory computer-readable media configured to store one or more instructions that when executed by at least one processor cause or direct a system to perform the method of claim 11.

### Claim 20

A system comprising:
one or more processors; and
one or more non-transitory computer-readable mediums configured to store instructions that when executed by the processors cause or direct the system to perform operations, the operations comprising:
select a first transcription generation technique from among a plurality of transcription generation techniques for generating transcriptions of audio of one or more communication sessions that involve a user device;
obtain performances of the plurality of transcription generation techniques with respect to generating the transcriptions of the audio;
monitor comparisons between the performances of the plurality of transcription generation techniques;
obtain input from the user with respect to the comparisons; and
select a second transcription generation technique from among the plurality of transcription generation techniques based on the input from the user.
