# US 2024/0203418 A1 · Method and system for automatically visualizing a transcript

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

- Number: US 2024/0203418 A1
- Document ID: US20240203418A1
- Status: Published application
- Kind: A1
- Application number: 18/538,325
- Filed: 2023-12-13
- Published: 2024-06-20
- Earliest claimed: 2022-12-20
- Assignees: JPMorgan Chase Bank, N.A.
- Applicants: JPMorgan Chase Bank, N.A.
- Inventors: Anusha RALLABHANDI
- Web page: https://patentgrep.com/patent/US20240203418A1

## CPC

- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A method and a system for automatically visualizing a transcript are disclosed. The method is implemented by at least one processor. The method includes receiving a voice input from at least one entity. Further, the method includes recognizing speech from the voice input using a speech recognition technique. Further, the method includes processing the recognized speech using at least one signal processing technique to enhance the speech, where the speech is processed to remove an unwanted noise. Further, the method includes converting the processed speech into a transcript using a speech transcription technique. Thereafter, the method includes automatically visualizing the transcript into a design diagram.

## Claims

### Claim 1

A method for automatically visualizing a transcript, the method comprising:
receiving, by at least one processor, a voice input from at least one entity;
recognizing, by the at least one processor, speech from the voice input using a speech recognition technique;
processing, by the at least one processor, the recognized speech using at least one signal processing technique to enhance the speech, wherein the speech is processed to remove an unwanted noise;
converting, by the at least one processor, the processed speech into a transcript using a speech transcription technique; and
automatically visualizing, by the at least one processor, the transcript into a design diagram.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the at least one speech recognition technique comprises at least one from among an automatic speech recognition technique and a wake word detection technique.

### Claim 3 (depends on 1)

The method as claimed in claim 1, wherein the at least one speech transcription technique comprises at least one from among a natural language understanding technique and a natural language generation technique.

### Claim 4 (depends on 1)

The method as claimed in claim 1, wherein the automatically visualizing the transcript into the design diagram comprises:
encoding, by the at least one processor, the transcript using a frozen language model; and
generating, by the at least one processor, the design diagram using a frozen clip model.

### Claim 5 (depends on 1)

The method as claimed in claim 1, wherein the voice input is received via an audio input device.

### Claim 6 (depends on 1)

The method as claimed in claim 1, wherein the at least one entity is one from among a team member involved in a project, a team lead of the project, a project reviewer, a user to present the project, and a client.

### Claim 7

A computing device for automatically visualizing a transcript, the computing device comprising:
a processor;
a memory; and
a communication interface coupled to each of the processor and the memory,
wherein the processor is configured to:
receive a voice input from at least one entity;
recognize speech from the voice input using a speech recognition technique;
process the recognized speech using at least one signal processing technique to enhance the speech, wherein the speech is processed to remove an unwanted noise;
convert the processed speech into a transcript using a speech transcription technique; and
automatically visualize the transcript into a design diagram.

### Claim 8 (depends on 7)

The computing device as claimed in claim 7, wherein the speech recognition technique comprises at least one from among an automatic speech recognition technique and a wake word detection technique.

### Claim 9 (depends on 7)

The computing device as claimed in claim 7, wherein the speech transcription technique comprises at least one from among a natural language understanding technique and a natural language generation technique.

### Claim 10 (depends on 7)

The computing device as claimed in claim 7, wherein to automatically visualize the transcript into the design diagram, the processor is further configured to:
encode the transcript using a frozen language model; and
generate the design diagram using a frozen clip model.

### Claim 11 (depends on 7)

The computing device as claimed in claim 7, wherein the voice input is received via an audio input device.

### Claim 12

A non-transitory computer readable storage medium storing instructions for automatically visualizing a transcript, the storage medium comprising executable code which, when executed by a processor, causes the processor to:
receive a voice input from at least one entity;
recognize speech from the voice input using a speech recognition technique;
process the recognized speech using at least one signal processing technique to enhance the speech, wherein the speech is processed to remove an unwanted noise;
convert the processed speech into a transcript using a speech transcription technique; and
automatically visualize the transcript into a design diagram.

### Claim 13 (depends on 12)

The storage medium as claimed in claim 12, wherein the speech recognition technique comprises at least one from among an automatic speech recognition technique and a wake word detection technique.

### Claim 14 (depends on 12)

The storage medium as claimed in claim 12, wherein the speech transcription technique comprises at least one from among a natural language understanding technique and a natural language generation technique.

### Claim 15 (depends on 12)

The storage medium as claimed in claim 12, wherein to automatically visualize the transcript into the design diagram, when executed by the processor, the executable code further causes the processor to:
encode the transcript using a frozen language model; and
generate the design diagram using a frozen clip model.

### Claim 16 (depends on 12)

The storage medium as claimed in claim 12, wherein the voice input is received via an audio input device.
