# US 2025/0095663 A1 · System and methods for generating realistic waveforms

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

- Number: US 2025/0095663 A1
- Document ID: US20250095663A1
- Status: Published application
- Kind: A1
- Application number: 18/967,109
- Filed: 2024-12-03
- Published: 2025-03-20
- Earliest claimed: 2021-05-10
- Assignees: WellSaid Labs, Inc.
- Applicants: WellSaid Labs Inc.
- Inventors: Michael PETROCHUK
- Web page: https://patentgrep.com/patent/US20250095663A1

## CPC

- G06N 3/045: Combinations of networks
- G10L 19/02: using spectral analysis, e.g. transform vocoders or subband vocoders
- G06N 3/047: Probabilistic or stochastic networks
- G10L 15/16: using artificial neural networks
- G10L 25/30: using neural networks
- G06N 3/08: Learning methods
- G10L 13/00: Speech synthesis; Text to speech systems
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Systems, apparatuses, and methods directed to training a Generator that is part of a Generative Adversarial Network (GAN) to generate “realistic” examples of a distribution. In some embodiments, this includes training the Generator model to receive a tensor as an input and generate a distribution which is then converted to the frequency domain and used to determine a loss term. Similarly, an actual distribution is also converted to the frequency domain and used to determine a loss term. The loss terms, generated distribution, and actual distribution are provided to a Discriminator which generates loss terms used as part of a backpropagation or feedback mechanism to modify the operation of the Generator and/or Discriminator.

## Claims

### Claim 1

A method of training a generative adversarial network including a Generator and a Discriminator, comprising performing a training cycle by:
inputting a first tensor including a set of elements to the Generator, each tensor element being a value and the set of elements representing a distribution of values;
operating the Generator to output a tensor representing a generated distribution of values;
processing the output tensor to convert the generated distribution of values to the frequency domain;
determining one or more error terms from the converted generated distribution;
obtaining a second tensor including a set of elements, each tensor element being a value and the set of elements representing an actual distribution of values;
converting the actual distribution of values to the frequency domain;
determining one or more error terms from the converted actual distribution;
inputting the converted generated distribution and the converted actual distribution to the Discriminator;
operating the Discriminator to determine an adversarial loss term, the adversarial loss term including a Generator loss term and a Discriminator loss term; and
using the Generator loss term, the error term from the converted generated distribution and the error term from the converted actual distribution to modify the Generator and using the Discriminator loss term to modify the Discriminator.

### Claim 2 (depends on 1)

The method of claim 1, wherein converting the generated distribution of values to the frequency domain and converting the actual distribution of values to the frequency domain further comprises using a Fourier Transform.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining one or more error terms from the converted generated distribution and determining one or more error terms from the converted actual distribution further comprise determining an Lp loss.

### Claim 4 (depends on 1)

The method of claim 1, wherein the set of elements included in the first tensor is derived from a waveform or signal.

### Claim 5 (depends on 4)

The method of claim 4, wherein the waveform corresponds to audio content.

### Claim 6 (depends on 1)

The method of claim 1, wherein the set of elements included in the first tensor is derived from an image.

### Claim 7 (depends on 1)

The method of claim 1, wherein the set of elements included in the second tensor is derived from a waveform or signal.

### Claim 8 (depends on 1)

The method of claim 1, wherein the set of elements included in the second tensor is derived from an image.

### Claim 9 (depends on 1)

The method of claim 1, wherein the Generator includes a set of layers, with each layer containing a plurality of nodes, with a plurality of connections between a set of nodes in a first layer and a set of nodes in a second layer adjacent to the first layer, and with a set of weights with each weight in the set of weights associated with one of the plurality of connections, and the method further comprises repeating the training cycle until weights between layers of the Generator and weights between layers of the Discriminator become stable.

### Claim 10 (depends on 1)

The method of claim 1, further comprising using the Generator as an inference engine to generate realistic examples of a tensor input to the Generator.

### Claim 11

A system for training a generative adversarial network including a Generator and a Discriminator by performing one or more training cycles, comprising:
one or more electronic processors operable to execute a set of computer-executable instructions; and
the set of computer-executable instructions stored in a non-transitory medium, wherein when executed, the instructions cause the one or more electronic processors to
input a first tensor including a set of elements to the Generator, each tensor element being a value and the set of elements representing a distribution of values;
operate the Generator to output a tensor representing a generated distribution of values;
process the output tensor to convert the generated distribution of values to the frequency domain;
determine one or more error terms from the converted generated distribution;
obtain a second tensor including a set of elements, each tensor element being a value and the set of elements representing an actual distribution of values;
convert the actual distribution of values to the frequency domain;
determine one or more error terms from the converted actual distribution;
input the converted generated distribution and the converted actual distribution to the Discriminator;
operate the Discriminator to determine an adversarial loss term, the adversarial loss term including a Generator loss term and a Discriminator loss term; and
use the Generator loss term, the error term from the converted generated distribution and the error term from the converted actual distribution to modify the Generator and use the Discriminator loss term to modify the Discriminator.

### Claim 12 (depends on 11)

The system of claim 11, wherein converting the generated distribution of values to the frequency domain and converting the actual distribution of values to the frequency domain further comprises using a Fourier Transform.

### Claim 13 (depends on 11)

The system of claim 11, wherein determining one or more error terms from the converted generated distribution and determining one or more error terms from the converted actual distribution further comprise determining an Lp loss.

### Claim 14 (depends on 11)

The system of claim 11, wherein the Generator includes a set of layers, with each layer containing a plurality of nodes, with a plurality of connections between a set of nodes in a first layer and a set of nodes in a second layer adjacent to the first layer, and with a set of weights with each weight in the set of weights associated with one of the plurality of connection, and the instructions further cause the one or more electronic processors to repeat the training cycle until weights between layers of the Generator and weights between layers of the Discriminator become stable.

### Claim 15 (depends on 12)

The system of claim 12 wherein the instructions further cause the one or more electronic processors to use the Generator as an inference engine to generate realistic examples of a tensor input to the Generator.

### Claim 16

A non-transitory medium including a set of computer-executable instructions that when executed by one or more programmed electronic processors, cause the processors to train a generative adversarial network including a Generator and a Discriminator by performing one or more training cycles by:
inputting a first tensor including a set of elements to the Generator, each tensor element being a value and the set of elements representing a distribution of values;
operating the Generator to output a tensor representing a generated distribution of values;
processing the output tensor to convert the generated distribution of values to the frequency domain;
determining one or more error terms from the converted generated distribution;
obtaining a second tensor including a set of elements, each tensor element being a value and the set of elements representing an actual distribution of values;
converting the actual distribution of values to the frequency domain;
determining one or more error terms from the converted actual distribution;
inputting the converted generated distribution and the converted actual distribution to the Discriminator;
operating the Discriminator to determine an adversarial loss term, the adversarial loss term including a Generator loss term and a Discriminator loss term; and
using the Generator loss term, the error term from the converted generated distribution and the error term from the converted actual distribution to modify the Generator and using the Discriminator loss term to modify the Discriminator.

### Claim 17 (depends on 16)

The non-transitory medium of claim 16, wherein converting the generated distribution of values to the frequency domain and converting the actual distribution of values to the frequency domain further comprises using a Fourier Transform.

### Claim 18 (depends on 16)

The non-transitory medium of claim 16, wherein determining one or more error terms from the converted generated distribution and determining one or more error terms from the converted actual distribution further comprise determining an Lp loss.

### Claim 19 (depends on 16)

The non-transitory medium of claim 16, wherein the Generator includes a set of layers, with each layer containing a plurality of nodes, with a plurality of connections between a set of nodes in a first layer and a set of nodes in a second layer adjacent to the first layer, and with a set of weights with each weight in the set of weights associated with one of the plurality of connection, and the instructions further cause the one or more electronic processors to repeat the training cycle until weights between layers of the Generator and weights between layers of the Discriminator become stable.

### Claim 20 (depends on 16)

The non-transitory medium of claim 16, wherein the instructions further cause the one or more electronic processors to use the Generator as an inference engine to generate realistic examples of a tensor input to the Generator.
