# US 2024/0242706 A1 · Systems and methods for multi-stage language analysis and remediation of robocalls

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

- Number: US 2024/0242706 A1
- Document ID: US20240242706A1
- Status: Published application
- Kind: A1
- Application number: 18/156,262
- Filed: 2023-01-18
- Published: 2024-07-18
- Earliest claimed: 2023-01-18
- Assignees: Verizon Patent and Licensing Inc.
- Applicants: Verizon Patent and Licensing Inc.
- Inventors: Katrina Marie Kutchko
- Web page: https://patentgrep.com/patent/US20240242706A1

## CPC

- G10L 15/005: {Language recognition}
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 25/48: specially adapted for particular use
- G10L 25/51: for comparison or discrimination
- H04M 3/436: Arrangements for screening incoming calls {, i.e. evaluating the characteristics of a call before deciding whether to answer it (based on the calling party profile H04M3/42059; based on location H04M3/42348; based on presence H04M3/42365; diversion H04M3/54)}
- H04M 2201/12: Counting circuits
- H04M 2201/18: Comparators
- H04M 2201/40: using speech recognition
- H04M 2203/2027: Live party detection
- H04M 2203/2061: Language aspects
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

A system described herein may receive audio associated with a voice call; determine an amount of speech in the audio associated with the voice call; determine, based on the amount of speech, an expected length of a transcript, associated with a particular language, of the voice call; generate or receive the transcript, associated with the particular language, of the voice call; identify a length of the transcript, associated with the particular language, of the voice call; compare the length of the transcript to the expected length of the transcript; determine, based on comparing the length of the transcript to the expected length of the transcript, whether the voice call is associated with the particular language; and output an indication of whether the voice call is associated with the particular language.

## Claims

### Claim 1

A device, comprising:
one or more processors configured to:
receive audio associated with a voice call;
determine an amount of speech in the audio associated with the voice call;
determine, based on the amount of speech, an expected length of a transcript, associated with a particular language, of the voice call;
generate or receive the transcript, associated with the particular language, of the voice call;
identify a length of the transcript, associated with the particular language, of the voice call;
compare the length of the transcript to the expected length of the transcript;
determine, based on comparing the length of the transcript to the expected length of the transcript, whether the voice call is associated with the particular language; and
output an indication of whether the voice call is associated with the particular language.

### Claim 2 (depends on 1)

The device of claim 1, wherein the expected length of the transcript and the length of the transcript each include at least a respective one of:
a quantity of characters,
a quantity of words, or
a quantity of phrases.

### Claim 3 (depends on 1)

The device of claim 1, wherein the particular language is a first language, wherein determining whether the voice call is associated with the first language includes determining that the voice call is not associated with the first language, wherein the one or more processors are further configured to:
perform, based on determining that the voice call is not associated with the first language, one or more operations to determine whether the voice call is associated with at least a second language.

### Claim 4 (depends on 3)

The device of claim 3, wherein the transcript is a first transcript, wherein determining whether the voice call is associated with the second language includes:
determining, based on the amount of speech, an expected length of a second transcript, associated with the second language, of the voice call;
generating or receiving the second transcript, associated with the second language, of the voice call;
identifying a length of the second transcript, associated with the second language, of the voice call;
comparing the length of the second transcript to the expected length of the second transcript; and
determining, based on comparing the length of the second transcript to the expected length of the second transcript, whether the voice call is associated with the second language.

### Claim 5 (depends on 1)

The device of claim 1, wherein determining whether the voice call is associated with the particular language includes determining whether the length of the transcript is within a threshold range of the expected length of the transcript.

### Claim 6 (depends on 1)

The device of claim 1, wherein the particular language is a first language, wherein determining whether the voice call is associated with the first language includes determining that the voice call is not associated with the first language, wherein the one or more processors are further configured to:
compare audio of the voice call to previously classified audio that has been identified as being associated with at least a second language; and
determine, based on comparing the audio of the voice call to the previously classified audio, whether the voice call is associated with the second language.

### Claim 7 (depends on 1)

The device of claim 1, wherein determining whether the voice call is associated with the particular language includes determining that the voice call is associated with the particular language, wherein the one or more processors are further configured to:
perform one or more robocall detection techniques associated with a caller from which the voice call was received, based on the identified particular language.

### Claim 8

A non-transitory computer-readable medium, storing a plurality of processor-executable instructions to:
receive audio associated with a voice call;
determine an amount of speech in the audio associated with the voice call;
determine, based on the amount of speech, an expected length of a transcript, associated with a particular language, of the voice call;
generate or receive the transcript, associated with the particular language, of the voice call;
identify a length of the transcript, associated with the particular language, of the voice call;
compare the length of the transcript to the expected length of the transcript;
determine, based on comparing the length of the transcript to the expected length of the transcript, whether the voice call is associated with the particular language; and
output an indication of whether the voice call is associated with the particular language.

### Claim 9 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the expected length of the transcript and the length of the transcript each include at least a respective one of:
a quantity of characters,
a quantity of words, or
a quantity of phrases.

### Claim 10 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the particular language is a first language, wherein determining whether the voice call is associated with the first language includes determining that the voice call is not associated with the first language, wherein the plurality of processor-executable instructions further include processor-executable instructions to:
perform, based on determining that the voice call is not associated with the first language, one or more operations to determine whether the voice call is associated with at least a second language.

### Claim 11 (depends on 10)

The non-transitory computer-readable medium of claim 10, wherein the transcript is a first transcript, wherein determining whether the voice call is associated with the second language includes:
determining, based on the amount of speech, an expected length of a second transcript, associated with the second language, of the voice call;
generating or receiving the second transcript, associated with the second language, of the voice call;
identifying a length of the second transcript, associated with the second language, of the voice call;
comparing the length of the second transcript to the expected length of the second transcript; and
determining, based on comparing the length of the second transcript to the expected length of the second transcript, whether the voice call is associated with the second language.

### Claim 12 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein determining whether the voice call is associated with the particular language includes determining whether the length of the transcript is within a threshold range of the expected length of the transcript.

### Claim 13 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the particular language is a first language, wherein determining whether the voice call is associated with the first language includes determining that the voice call is not associated with the first language, wherein the plurality of processor-executable instructions further include processor-executable instructions to:
compare audio of the voice call to previously classified audio that has been identified as being associated with at least a second language; and
determine, based on comparing the audio of the voice call to the previously classified audio, whether the voice call is associated with the second language.

### Claim 14 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein determining whether the voice call is associated with the particular language includes determining that the voice call is associated with the particular language, wherein the plurality of processor-executable instructions further include processor-executable instructions to:
perform one or more robocall detection techniques associated with a caller from which the voice call was received, based on the identified particular language.

### Claim 15

A method, comprising:
receiving audio associated with a voice call;
determining an amount of speech in the audio associated with the voice call;
determining, based on the amount of speech, an expected length of a transcript, associated with a particular language, of the voice call;
generating or receiving the transcript, associated with the particular language, of the voice call;
identifying a length of the transcript, associated with the particular language, of the voice call;
comparing the length of the transcript to the expected length of the transcript;
determining, based on comparing the length of the transcript to the expected length of the transcript, whether the voice call is associated with the particular language; and
outputting an indication of whether the voice call is associated with the particular language.

### Claim 16 (depends on 15)

The method of claim 15, wherein the expected length of the transcript and the length of the transcript each include at least a respective one of:
a quantity of characters,
a quantity of words, or
a quantity of phrases.

### Claim 17 (depends on 15)

The method of claim 15, wherein the particular language is a first language, wherein the transcript is a first transcript, and wherein determining whether the voice call is associated with the first language includes determining that the voice call is not associated with the first language, the method further comprising:
determining, based on the amount of speech, an expected length of a second transcript, associated with a second language, of the voice call;
generating or receiving the second transcript, associated with the second language, of the voice call;
identifying a length of the second transcript, associated with the second language, of the voice call;
comparing the length of the second transcript to the expected length of the second transcript; and
determining, based on comparing the length of the second transcript to the expected length of the second transcript, whether the voice call is associated with the second language.

### Claim 18 (depends on 15)

The method of claim 15, wherein determining whether the voice call is associated with the particular language includes determining whether the length of the transcript is within a threshold range of the expected length of the transcript.

### Claim 19 (depends on 15)

The method of claim 15, wherein the particular language is a first language, wherein determining whether the voice call is associated with the first language includes determining that the voice call is not associated with the first language, the method further comprising:
comparing audio of the voice call to previously classified audio that has been identified as being associated with at least a second language; and
determining, based on comparing the audio of the voice call to the previously classified audio, whether the voice call is associated with the second language.

### Claim 20 (depends on 15)

The method of claim 15, wherein determining whether the voice call is associated with the particular language includes determining that the voice call is associated with the particular language, the method further comprising:
performing one or more robocall detection techniques associated with a caller from which the voice call was received, based on the identified particular language.
