# US 2018/0322892 A1 · Deflation and Decomposition of Data Signals Using Reference Signals

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

- Number: US 2018/0322892 A1
- Document ID: US20180322892A1
- Status: Published application
- Kind: A1
- Application number: 16/019,873
- Filed: 2018-06-27
- Published: 2018-11-08
- Earliest claimed: 2012-06-29
- Assignees: Speech Technology & Applied Research Corporation; Richard S. Goldhor
- Applicants: Speech Technology & Applied Research Corporation
- Inventors: Richard S. Goldhor; Keith Gilbert; Joel MacAuslan
- Web page: https://patentgrep.com/patent/US20180322892A1

## CPC

- G10L 25/51: for comparison or discrimination
- G10L 21/0272: Voice signal separating
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A system processes data signals consisting of sums of independent signal terms, zero or more of which signal terms may already have been identified, in order to generate one or more additional terms. Deflated versions of the data signals are created by subtracting from the data signals any previously identified signal terms. Additional independent signal terms are computed using a set of reference signals organized into mutually independent partioning support sets. The images of each support set are computed on the data signals. Computed images on a data signal that are non-zero are identified as additional independent signal terms of that data signal.

## Claims

### Claim 1

A method for generating additional independent signal terms (ISTs) of a data signal given an initial set of ISTs of that data signal and at least one mutually independent partitioning support set of reference signals, the initial set of ISTs including zero or more ISTs, the method comprising:
(1) generating a deflated data signal by subtracting the sum of all of the ISTs in the initial set of ISTs from the data signal;
(2) generating an optimal image of each of the at least one mutually independent partitioning support sets on the deflated data signal;
(3) testing each generated optimal image so as to identify each non-zero optimal image;
(4) identifying each non-zero optimal image as an additional independent signal term of the data signal.

### Claim 2 (depends on 1)

The method of claim 1, wherein the initial set of ISTs consists of zero ISTs, and wherein the method further comprises:
(5) generating additional independent signal terms of the data signal by performing the following steps at least once:
a. creating an augmented set of ISTs by adding any previously-generated additional independent signal terms to the initial set of ISTs;
b. generating additional independent signal terms of the data signal, according to the method of CLAIM A, using the augmented set of ISTs as the initial set of ISTs.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
(5) before (1), generating at least one of the reference signals in the at least one mutually independent partitioning set of reference signals by linearly filtering signals generated by a blind source separation algorithm.

### Claim 4 (depends on 3)

The method of claim 3, wherein the additional independent signal term (ISTs) of the data signal represents a response of a sensor.

### Claim 5 (depends on 4)

The method of claim 4, wherein the sensor comprises an acoustic sensor.

### Claim 6

A system comprising at least one non-transitory computer readable medium having stored thereon computer program instructions executable by at least one computer processor to perform a method for generating additional independent signal terms (ISTs) of a data signal given an initial set of ISTs of that data signal and at least one mutually independent partitioning support set of reference signals, the initial set of ISTs including zero or more ISTs, the method comprising:
(1) generating a deflated data signal by subtracting the sum of all of the ISTs in the initial set of ISTs from the data signal;
(2) generating an optimal image of each of the at least one mutually independent partitioning support sets on the deflated data signal;
(3) testing each generated optimal image so as to identify each non-zero optimal image;
(4) identifying each non-zero optimal image as an additional independent signal term of the data signal.

### Claim 7 (depends on 6)

The system of claim 6, wherein the initial set of ISTs consists of zero ISTs, and wherein the method further comprises:
(5) generating additional independent signal terms of the data signal by performing the following steps at least once:
c. creating an augmented set of ISTs by adding any previously-generated additional independent signal terms to the initial set of ISTs;
d. generating additional independent signal terms of the data signal, according to the method of CLAIM A, using the augmented set of ISTs as the initial set of ISTs.

### Claim 8 (depends on 6)

The system of claim 6, wherein the method further comprises:
(5) before (1), generating at least one of the reference signals in the at least one mutually independent partitioning set of reference signals by linearly filtering signals generated by a blind source separation algorithm.

### Claim 9 (depends on 8)

The system of claim 8, wherein the additional independent signal term (ISTs) of the data signal represents a response of a sensor.

### Claim 10 (depends on 9)

The system of claim 9, wherein the sensor comprises an acoustic sensor.