# US 2025/0157480 A1 · Embedded enablement for optimal gain-mask machine learning, audio channel-based signal enhancement

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

- Number: US 2025/0157480 A1
- Document ID: US20250157480A1
- Status: Published application
- Kind: A1
- Application number: 18/506,434
- Filed: 2023-11-10
- Published: 2025-05-15
- Earliest claimed: 2023-11-10
- Assignees: Cypress Semiconductor Corporation
- Applicants: Cypress Semiconductor Corporation
- Inventors: Anand Dubey; Monisankha PAL; Ted WADA; Arvind RAMANATHAN; Ashutosh PANDEY
- Web page: https://patentgrep.com/patent/US20250157480A1

## CPC

- G10L 21/0208: Noise filtering
- G10L 21/0232: Processing in the frequency domain
- G10L 25/18: the extracted parameters being spectral information of each sub-band
- G10L 25/30: using neural networks
- G10L 2021/02082: {the noise being echo, reverberation of the speech}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A system includes memory storing instructions and a processing device coupled to the memory. The processing device executes the instructions to: receive a noisy audio signal from an audio receiver; pass the noisy audio signal through a deep neural network (DNN) model to generate a mask of a magnitude spectrogram of the noisy audio signal; retrieve a clean-only audio spectra and a noise-only spectra of one or more frequencies that exist within the noisy audio signal; generate a loss function as a combination of the clean-only audio spectra multiplied by the mask and the noise-only spectra multiplied by the mask; and train the DNN model while minimizing the loss function to generate a trained DNN model useable in audio noise suppression and dereverberation.

## Claims

### Claim 1

A system comprising:
memory storing instructions; and
a processing device coupled to the memory, the processing device to execute the instructions to:
receive a noisy audio signal from an audio receiver;
pass the noisy audio signal through a deep neural network (DNN) model to generate a mask of a magnitude spectrogram of the noisy audio signal;
retrieve a clean-only audio spectra and a noise-only spectra of one or more frequencies that exist within the noisy audio signal;
generate a loss function as a combination of the clean-only audio spectra multiplied by the mask and the noise-only spectra multiplied by the mask; and
train the DNN model while minimizing the loss function to generate a trained DNN model useable in audio noise suppression and dereverberation.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processing device is further to:
perform a signal-to-noise ratio (SNR) estimation and normalization on the clean-only audio spectra to generate normalized estimated SNR values;
measure noise spectral stationarity of the noise-only spectra to generate a measured noise spectral stationarity values that characterize the flatness of the noise-only spectra; and
incorporate weighted versions of the normalized estimated SNR values and the measured noise spectral stationarity values in a regression function that generates a tradeoff parameter output useable in training the DNN model.

### Claim 3 (depends on 1)

The system of claim 1, wherein the processing device is further to perform, using the trained DNN model, at least one of channel-based noise suppression or channel-based dereverberation during active operation.

### Claim 4 (depends on 3)

The system of claim 3, wherein the processing device is further to:
process the clean-only audio spectra with a Short-Term Fourier Transform (STFT) function and determine a first magnitude of the processed clean-only audio spectra;
process the noisy audio signal with the STFT function;
determine a second magnitude and a first phase of the processed noisy audio signal;
input, to the trained DNN model, the first magnitude as a target audio signal and the second magnitude as a predicted audio signal;
employ an output of the trained DNN model as an output magnitude and the phase as an output phase to generate an output audio signal; and
apply an inverse STFT function to the output audio signal to generate a denoised audio signal.

### Claim 5 (depends on 1)

The system of claim 1, wherein the mask is an ideal ratio mask, comprising only ones and zeros, determined a-priori based on at least the clean-only audio spectra.

### Claim 6 (depends on 1)

The system of claim 1, wherein the DNN model comprises:
multiple sets of intermediate layers, each set including a convolutional layer followed by a batch normalization layer followed by a sigmoid layer; and
a final regression layer to learn from outputs of the multiple sets of intermediate layers and estimate values of the mask.

### Claim 7 (depends on 1)

The system of claim 1, wherein the clean-only audio spectra multiplied by the mask is a filtered audio spectrum and the noise-only spectra multiplied by the mask is a filtered noise spectrum, and wherein the loss function includes: a scalar value multiplied by the filtered noise spectrum; and one minus the scalar value multiplied by a difference between the filtered audio spectrum and the clean-only audio spectra.

### Claim 8 (depends on 7)

The system of claim 7, wherein the scalar value is between a zero value and a one value, and wherein the processing device is further to tune the scalar value such as to minimize the filtered noise spectrum and minimize distortion of the filtered audio spectrum.

### Claim 9 (depends on 1)

The system of claim 1, wherein the processing device is further to:
determine an ideal ratio mask as the clean-only audio spectra divided by a combination of the clean-only audio spectra and the noise-only spectra;
determine a time-frequency-based loss function as an absolute magnitude of a difference of a predicted ratio mask and the ideal ratio mask over time and the one or more frequencies; and
modify the loss function with the time-frequency-based loss function.

### Claim 10

A method comprising:
receiving a noisy audio signal from an audio receiver;
passing the noisy audio signal through a deep neural network (DNN) model to generate a mask of a magnitude spectrogram of the noisy audio signal;
retrieving a clean-only audio spectra and a noise-only spectra of one or more frequencies that exist within the noisy audio signal;
generating, by a processing device, a loss function as a combination of the clean-only audio spectra multiplied by the mask and the noise-only spectra multiplied by the mask; and
training, by the processing device, the DNN model while minimizing the loss function to generate a trained DNN model useable in audio noise suppression and dereverberation.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
perform a signal-to-noise ratio (SNR) estimation and normalization on the clean-only audio spectra to generate normalized estimated SNR values;
measure noise spectral stationarity of the noise-only spectra to generate a measured noise spectral stationarity values that characterize the flatness of the noise-only spectra; and
incorporate weighted versions of the normalized estimated SNR values and the measured noise spectral stationarity values in a regression function that generates a tradeoff parameter output useable in training the DNN model.

### Claim 12 (depends on 10)

The method of claim 10, further comprising performing, using the trained DNN model, at least one of channel-based noise suppression or channel-based dereverberation during active operation.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
processing the clean-only audio spectra with a Short-Term Fourier Transform (STFT) function and determine a first magnitude of the processed clean-only audio spectra;
processing the noisy audio signal with the STFT function;
determine a second magnitude and a first phase of the processed noisy audio signal;
inputting, to the trained DNN model, the first magnitude as a target audio signal and the second magnitude as a predicted audio signal;
employing an output of the trained DNN model as an output magnitude and the phase as an output phase to generate an output audio signal; and
applying an inverse STFT function to the output audio signal to generate a denoised audio signal.

### Claim 14 (depends on 10)

The method of claim 10, wherein the mask is an ideal mask, comprising only ones and zeros, determined a-priori based on at least the clean-only audio spectra.

### Claim 15 (depends on 10)

The method of claim 10, wherein the DNN model comprises:
multiple sets of intermediate layers, each set including a convolutional layer followed by a batch normalization layer followed by a sigmoid layer; and
a final regression layer to learn from outputs of the multiple sets of intermediate layers and estimate values of the mask.

### Claim 16 (depends on 10)

The method of claim 10, wherein the clean-only audio spectra multiplied by the mask is a filtered audio spectrum and the noise-only spectra multiplied by the mask is a filtered noise spectrum, and wherein the loss function includes: a scalar value multiplied by the filtered noise spectrum; and one minus the scalar value multiplied by a difference between the filtered audio spectrum and the clean-only audio spectra.

### Claim 17 (depends on 16)

The method of claim 16, wherein the scalar value is between a zero value and a one value, the method further comprising tuning the scalar value such as to minimize the filtered noise spectrum and minimize distortion of the filtered audio spectrum.

### Claim 18 (depends on 10)

The method of claim 10, further comprising:
determining an ideal ratio mask as the clean-only audio spectra divided by a combination of the clean-only audio spectra and the noise-only spectra;
determining a time-frequency-based loss function as an absolute magnitude of a difference of a predicted ratio mask and the ideal ratio mask over time and the one or more frequencies; and
modifying the loss function with the time-frequency-based loss function.

### Claim 19

A non-transitory computer-readable storage medium storing instructions, which when executed, cause a processing device to perform operations comprising:
receiving a noisy audio signal from an audio receiver;
passing the noisy audio signal through a deep neural network (DNN) model to generate a mask of a magnitude spectrogram of the noisy audio signal;
retrieving a clean-only audio spectra and a noise-only spectra of one or more frequencies that exist within the noisy audio signal;
generating a loss function as a combination of the clean-only audio spectra multiplied by the mask and the noise-only spectra multiplied by the mask; and
training the DNN model while minimizing the loss function to generate a trained DNN model useable in audio noise suppression and dereverberation.

### Claim 20 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the operations further comprise:
perform a signal-to-noise ratio (SNR) estimation and normalization on the clean-only audio spectra to generate normalized estimated SNR values;
measure noise spectral stationarity of the noise-only spectra to generate a measured noise spectral stationarity values that characterize the flatness of the noise-only spectra; and
incorporate weighted versions of the normalized estimated SNR values and the measured noise spectral stationarity values in a regression function that generates a tradeoff parameter output useable in training the DNN model.

### Claim 21 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the operations further comprise performing, using the trained DNN model, at least one of channel-based noise suppression or channel-based dereverberation during active operation.

### Claim 22 (depends on 21)

The non-transitory computer-readable storage medium of claim 21, wherein the operations further comprise:
processing the clean-only audio spectra with a Short-Term Fourier Transform (STFT) function and determine a first magnitude of the processed clean-only audio spectra;
processing the noisy audio signal with the STFT function;
determine a second magnitude and a first phase of the processed noisy audio signal;
inputting, to the trained DNN model, the first magnitude as a target audio signal and the second magnitude as a predicted audio signal;
employing an output of the trained DNN model as an output magnitude and the phase as an output phase to generate an output audio signal; and
applying an inverse STFT function to the output audio signal to generate a denoised audio signal.

### Claim 23 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the clean-only audio spectra multiplied by the mask is a filtered audio spectrum and the noise-only spectra multiplied by the mask is a filtered noise spectrum, and wherein the loss function includes: a scalar value multiplied by the filtered noise spectrum; and one minus the scalar value multiplied by a difference between the filtered audio spectrum and the clean-only audio spectra.

### Claim 24 (depends on 23)

The non-transitory computer-readable storage medium of claim 23, wherein the scalar value is between a zero value and a one value, wherein the operations further comprise tuning the scalar value such as to minimize the filtered noise spectrum and minimize distortion of the filtered audio spectrum.

### Claim 25 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the operations further comprise:
determining an ideal ratio mask as the clean-only audio spectra divided by a combination of the clean-only audio spectra and the noise-only spectra;
determining a time-frequency-based loss function as an absolute magnitude of a difference of a predicted ratio mask and the ideal ratio mask over time and the one or more frequencies; and
modifying the loss function with the time-frequency-based loss function.