# US 10,504,541 B1 · Desired signal spotting in noisy, flawed environments

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

- Number: US 10,504,541 B1
- Document ID: US10504541B1
- Status: Granted
- Kind: B1
- Application number: 16/444,890
- Filed: 2019-06-18
- Published: 2020-01-02
- Granted: 2019-12-10
- Earliest claimed: 2018-06-28
- Assignees: Invoca, Inc.
- Applicants: Invoca, Inc.
- Inventors: Sean Michael Storlie; Victor Jara Borda; Michael Kingsley McCourt, Jr.; Leland W. Kirchhoff; Colin Denison Kelley; Nicholas James Burwell
- Web page: https://patentgrep.com/patent/US10504541B1

## CPC

- G10L 25/84: for discriminating voice from noise
- G10L 15/08: Speech classification or search
- G10L 25/51: for comparison or discrimination
- H04M 3/18: with means for reducing interference {or noise}; with means for reducing effects due to line faults {with means for protecting lines}
- H04M 3/22: Arrangements for supervision, monitoring or testing
- H04M 3/51: Centralised call answering arrangements requiring operator intervention {, e.g. call or contact centers for telemarketing}
- H04M 3/54: Arrangements for diverting calls for one subscriber to another predetermined subscriber {(based on the calling party profile H04M3/42059; based on location H04M3/42348; based on presence H04M3/42365; to voice mail H04M3/53308)}
- G10L 2015/088: {Word spotting}
- 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

There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.

## Claims

### Claim 1

A method of desired signal spotting in noisy, flawed environments comprising:
identifying the desired signal to be spotted and a pool of call samples, wherein the signal is one or more spoken terms;
identifying a target confidence level;
passing the pool of call samples through a comparator to spot the desired signal, wherein the call samples are derived from respective distinct environments, wherein spotting the desired signal comprises measuring a confidence of a presence of the desired signal in each of the call samples using correlation of the desired signal to bodies of known matching samples that are machine created reference signals, and wherein the correlation includes the comparator comprises a predictive model for performing a weighting analysis comparison of the desired signal to the bodies of known matching samples that are selected by the comparator during measuring of each of the call samples;
if the confidence for a given call sample satisfies the target confidence level, flagging the given call sample as having the desired signal; and
using the flagged sample as a reference signal of the bodies of known matching samples during a subsequent spotting of the desired signal in the pool of call samples.

### Claim 2 (depends on 1)

The method of claim 1, wherein the bodies of known matching samples are artificial intelligence (AI) created reference signals created by the comparator during use of the comparator to spot the desired signal in the given call sample.

### Claim 3 (depends on 2)

The method of claim 2, wherein the pool of call samples are a collection of various stored converted call samples from one of various advertisers or marketing campaigns.

### Claim 4 (depends on 1)

The method of claim 1 wherein the bodies of known matching samples are derived from original samples selected by the comparator.

### Claim 5 (depends on 1)

The method of claim 1, wherein each call sample is a given converted sample that comprises a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form.

### Claim 6 (depends on 5)

The method of claim 5 wherein the conversion further includes anonymization.

### Claim 7 (depends on 5)

The method of claim 5 wherein:
the respective distinctive environments comprise electronic waveforms of the respective original samples;
the noisy, flawed environments comprise at least one of noise in a call signal of the pool of call samples or an erroneous sample of the bodies of known matching samples;
and
the first form is an audio electronic waveform and the second form is text.

### Claim 8 (depends on 1)

The method of claim 1 further comprising:
pooling plural call samples derived from the distinct environments with the desired signal to be spotted, the call samples comprising plural call samples; and
converting each respective original sample to a given converted sample.

### Claim 9

An apparatus for desired signal spotting in noisy, flawed environments comprising:
a first identifier unit to identify the desired signal to be spotted and a pool of call samples, wherein the signal is one or more spoken terms;
a second identifier unit to identify a target confidence level;
a synchronizer coupled to the first and second identifier units to synchronize the pool of call samples with the desired signal and the identified confidence level; and
a tester coupled to the synchronizer to pass the pool of calls samples through a comparator;
the comparator to spot the desired signal, wherein the call samples are derived from respective distinct environments, wherein spotting the desired signal comprises measuring a confidence of a presence of the desired signal in each of the call samples using correlation of the desired signal to bodies of known matching samples that are machine created reference signals, and wherein the correlation includes the comparator comprises a predictive model for performing a weighting analysis comparison of the desired signal to the bodies of known matching samples that are selected by the comparator during measuring of each of the call samples;
a flagger to flag a given call sample as having the desired signal if the confidence for the given call sample satisfies the target confidence level; and
the comparator to use the flagged sample as a reference signal of the bodies of known matching samples during a subsequent spotting of the desired signal in the pool of call samples.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the bodies of known matching samples are artificial intelligence (AI) created reference signals created by the comparator during use of the comparator to spot the desired signal in the given call sample.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein the pool of call samples are a collection of various stored converted call samples from one of various advertisers or marketing campaigns.

### Claim 12 (depends on 9)

The apparatus of claim 9 further comprising a deriver to derive the bodies of known matching samples from original samples selected by the comparator.

### Claim 13 (depends on 9)

The apparatus of claim 9 wherein each call sample is a given converted sample that comprises a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form.

### Claim 14 (depends on 13)

The apparatus of claim 13 further comprising an anonymizer to anonymize the converted sample.

### Claim 15 (depends on 13)

The apparatus of claim 13 wherein:
the respective distinctive environments comprise electronic waveforms of the respective original samples;
the noisy, flawed environments comprise at least one of noise in a call signal of the pool of call samples or an erroneous sample of the bodies of known matching samples;
and
the first form is an audio electronic waveform and the second form is text.

### Claim 16 (depends on 9)

The apparatus of claim 9 further comprising:
a pooler to pool the plural call samples derived from the distinct environments with the desired signal to be spotted, the call samples comprising plural call samples; and
a converter to convert each respective original sample to a given converted sample.

### Claim 17 (depends on 9)

The apparatus of claim 9 wherein the first and second identifier units further comprise a user input device.