IP Library › Granted Patent US 12,744,048
Granted Patent B2
US 12,744,048 · App. 18/920,904 · Granted Sep 22, 2026

Unified post-filter for an audio filter system for vehicle

Inventors: Moshe Tzur (Petah Tikva, IL); Elior Hadad (Ness-Ziona, IL); Amos Schreibman (Hod Hasharon, IL)
Assignee: GM Global Technology Operations LLC
G10L21/0216G10L25/18H04R3/005H04R3/04G10L2021/02166H04R2499/13
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,744,048
App. No.
18/920,904
Granted
Sep 22, 2026
Kind
B2
Abstract

A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations. The operations include receiving, from a sensor array, an audio signal at a unified post-filter, converting, via a conversion function, the audio signal into a Short-Time Fourier Transform (STFT) domain, determining, based on the converted audio signal, a speech-presence probability, and determining, based on the speech-presence probability, a noise smoothing factor. The operations also include estimating, via the unified post-filter, a noise power spectral density based on the noise smoothing factor, estimating, via the unified post-filter, a steering vector of a desired source, and generating, via the unified post-filter, a directionality-based mask and a coherence-based mask. The operations further include generating, based on the directionality-based mask and the coherence-based mask, a residual echo spectrum estimation and setting one or more spectral shaping factors based on the residual echo spectrum estimation.

Claims (52)

1 . A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations comprising:

receiving, from a sensor array, an audio signal at a unified post-filter;

converting, via a conversion function, the audio signal into a Short-Time Fourier Transform (STFT) domain;

determining, based on the converted audio signal, a speech-presence probability;

determining, based on the speech-presence probability, a noise smoothing factor;

estimating, via the unified post-filter, a noise power spectral density based on the noise smoothing factor;

estimating, via the unified post-filter, a steering vector of a desired source;

generating, via the unified post-filter, a directionality-based mask and a coherence-based mask;

generating, based on the directionality-based mask and the coherence-based mask, a residual echo spectrum estimation; and

setting one or more spectral shaping factors based on the residual echo spectrum estimation.

2 . The method of claim 1 , wherein the audio signal includes the desired source, residual ambient noise, and a residual echo.

3 . The method of claim 1 , wherein estimating the noise power spectral density includes determining an active speaker probability.

4 . The method of claim 1 , wherein generating the directionality-based mask includes utilizing spatial information and distinguishing the desired source from a residual echo of the audio signal.

5 . The method of claim 1 , wherein generating the coherence-based mask includes masking an estimated echo of the audio signal.

6 . The method of claim 1 , wherein generating the residual echo spectrum estimation includes extracting a residual echo of the audio signal from an original echo of the audio signal.

7 . The method of claim 1 , further including implementing, via the unified post-filter, a parametric variant of a Wiener filter.

8 . An audio filter system for a vehicle, the audio filter system comprising:

data processing hardware; and

memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:

receiving, from a sensor array, an audio signal at a unified post-filter;

converting, via a conversion function, the audio signal into a Short-Time Fourier Transform (STFT) domain;

determining, based on the converted audio signal, a speech-presence probability;

determining, based on the speech-presence probability, a noise smoothing factor;

estimating, via the unified post-filter, a noise power spectral density based on the noise smoothing factor;

estimating, via the unified post-filter, a steering vector of a desired source;

generating, via the unified post-filter, a directionality-based mask and a coherence-based mask;

generating, based on the directionality-based mask and the coherence-based mask, a residual echo spectrum estimation; and

setting one or more spectral shaping factors based on the residual echo spectrum estimation.

9 . The system of claim 8 , wherein the audio signal includes the desired source, residual ambient noise, and a residual echo.

10 . The system of claim 8 , wherein determining the noise power spectral density includes determining an active speaker probability.

11 . The system of claim 8 , wherein generating the directionality-based mask includes utilizing spatial information and distinguishing the desired source from a residual echo of the audio signal.

12 . The system of claim 8 , wherein generating the coherence-based mask includes masking an estimated echo of the audio signal.

13 . The system of claim 8 , wherein generating the residual echo spectrum estimation includes extracting a residual echo of the audio signal from an original echo of the audio signal.

14 . The system of claim 8 , further including implementing, via the unified post-filter, a parametric variant of a Wiener filter.

15 . An audio filter system for a vehicle, the audio filter system comprising:

data processing hardware; and

memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:

receiving, from a sensor array, an audio signal at a unified post-filter;

converting, via a conversion function, the audio signal into a Short-Time Fourier Transform (STFT) domain;

determining, based on the converted audio signal, a speech-presence probability;

determining, based on the speech-presence probability, a noise smoothing factor;

estimating, via the unified post-filter, a noise power spectral density based on the noise smoothing factor;

estimating, via the unified post-filter, a steering vector of a desired source;

generating, via the unified post-filter, a directionality-based mask and a coherence-based mask;

generating, based on the directionality-based mask and the coherence-based mask, a residual echo spectrum estimation;

setting one or more spectral shaping factors based on the residual echo spectrum estimation; and

implementing, via the unified post-filter, a parametric variant of a Wiener filter.

16 . The system of claim 15 , wherein the audio signal includes the desired source, residual ambient noise, and a residual echo.

17 . The system of claim 15 , wherein determining the noise power spectral density includes determining an active speaker probability.

18 . The system of claim 15 , wherein generating the directionality-based mask includes utilizing spatial information and distinguishing the desired source from a residual echo of the audio signal.

19 . The system of claim 15 , wherein generating the coherence-based mask includes masking an estimated echo of the audio signal.

20 . The system of claim 15 , wherein generating the residual echo spectrum estimation includes extracting a residual echo of the audio signal from an original echo of the audio signal.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 22, 2024
From: TZUR, MOSHE; HADAD, ELIOR; SCHREIBMAN, AMOS
To: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Reel/Frame 068971/0148 →
Continuity (1)
Related Publication 20260112380A1 · Apr 23, 2026
References Cited (15)
US 11462231B1 · Shankar · 2022 [cited by examiner]
US 20030177006A1 · Ichikawa · 2003 [cited by examiner]
US 20120158404A1 · Shin · 2012 [cited by examiner]
US 20180130482A1 · Michel et al. · 2018 [cited by applicant]
CN 110931036A · 2020 [cited by examiner]
CN 113851141A · 2021 [cited by examiner]
CN 110931036B · 2022 [cited by examiner]
CN 114708880A · 2022 [cited by examiner]
CN 114999521A · 2022 [cited by examiner]
CN 115713946A · 2023 [cited by examiner]
CN 117219108A · 2023 [cited by examiner]
CN 118053440A · 2024 [cited by examiner]
DE 102018117556A1 · 2019 [cited by applicant]
WO WO2016147020A1 · 2016 [cited by examiner]
WO WO2023228785A1 · 2023 [cited by examiner]