User selectable noise suppression in a voice communication

Patent metadata

Field	Value
Publication number	US-12537012-B2
Application number	US-202218146842-A
Country	US
Kind code	B2
Filing date	Dec 27, 2022
Priority date	Dec 27, 2022
Publication date	Jan 27, 2026
Grant date	Jan 27, 2026

Abstract

An apparatus for audio communication includes a memory configured to receive audio data from a user of a voice communication, and one or more processors in communication with the memory. The one or more processors are configured to receive the audio data for the voice communication, which includes voice data of the user and background audio data. The processors are further configured to classify the background audio data into a plurality of types of background audio data, determine to not suppress a subset of the plurality of types of background audio data, process the audio data to not suppress the subset of the plurality of types of background audio data to generate output audio data, and transmit the output audio data.

First claim

What is claimed is:

1 . An apparatus configured for audio communication, the apparatus comprising:
a memory configured to receive audio data from a user of a voice communication; and one or more processors in communication with the memory, the one or more processors configured to:
receive the audio data for the voice communication, the audio data including voice data of the user and background audio data;
classify the background audio data into a plurality of types of background audio data;
determine to suppress a subset of the plurality of types of background audio data based on a noise suppression configuration, wherein the noise suppression configuration includes the indication of a noise suppression aggressiveness;
process the audio data to suppress-the subset of the plurality of types of background audio data to generate output audio data based on the noise suppression aggressiveness; and
transmit the output audio data.

2 . The apparatus of claim 1 , wherein to determine to suppress the subset of the plurality of types of background audio data, the one or more processors are configured to:
receive an input from the user that specifies the noise suppression configuration that indicates the subset of the plurality of types of background audio data.

3 . The apparatus of claim 2 , further comprising a display, wherein the one or more processors are configured to:
generate a graphical user interface on the display, wherein the graphical user interface provides a plurality of selections corresponding to the plurality of types of background audio data; receive one or more second indications, via the graphical user interface, which identifies the subset of the plurality of background audio data to suppress; and determine to suppress a subset of the plurality of types of background audio data based on the one more second indications.

4 . The apparatus of claim 3 , wherein to generate the graphical user interface, the one or more processors are configured to:
adaptively detect the plurality of types of background audio data; and adaptively update the plurality of selections based on the plurality of types of background audio data based detected.

5 . The apparatus of claim 1 , wherein the subset of the plurality of types of background audio data include background audio data related to security.

6 . The apparatus of claim 1 , wherein to classify the background audio data into the plurality of types of background audio data, the one or more processors are configured to:
process the audio data using an artificial intelligence process to identify the plurality of types of background audio data.

7 . The apparatus of claim 6 , wherein the artificial intelligence process is one or more of a neural network, an artificial neural network, a deep neural network, a predictive analytics system, supervised learning, unsupervised learning, semi-supervised learning, or transfer learning.

8 . The apparatus of claim 1 , wherein to process the audio data to suppress, based on the indication of noise aggressiveness, the subset of the plurality of types of background audio data to generate output audio data, the one or more processors are configured to:
perform, on a first stream of the audio data, a noise suppression process to suppress the background audio data to generate voice only audio data; extract, on a second stream of the audio data, the subset of the plurality of types of background audio data; and combine the voice only audio data with the subset of the plurality of types of background audio data to generate the output audio data.

9 . The apparatus of claim 1 , wherein to process the audio data to suppress the subset of the plurality of types of background audio data to generate output audio data, the one or more processors are configured to:
perform a noise suppression process on the audio data to suppress types of background audio data not in the subset of the plurality of types of background audio data to generate the output audio data.

10 . The apparatus of claim 1 , wherein the plurality of types of background audio data may include one or more of environmental noise, human-generated noise, animal-generated noise, mechanical noise, or electronic noise.

11 . The apparatus of claim 1 , wherein the apparatus is a mobile communications device.

12 . The apparatus of claim 1 , wherein to transmit the output audio data, the one or more processors are configured to:
transmit the output audio data via a wireless communication standard.

13 . The apparatus of claim 1 , wherein the indication of the noise suppression aggressiveness indicates that a user set a specific level of noise suppression for the subset of the plurality of types of background audio data.

14 . The apparatus of claim 1 , wherein a user need not reselect what types of background noise, in the subset of the plurality of types of background audio data, are passed through for every voice communication.

15 . The apparatus of claim 1 , wherein the noise suppression configuration is reset and updated for each voice communication.

16 . A method for audio communication, the method comprising:
receiving audio data for the voice communication, the audio data including voice data of the user and background audio data; classifying the background audio data into a plurality of types of background audio data; determining to suppress a subset of the plurality of types of background audio data based on a noise suppression configuration, wherein the noise suppression configuration includes an indication of a noise suppression aggressiveness; processing the audio data to suppress the subset of the plurality of types of background audio data to generate output audio data based on a noise suppression configuration, wherein the noise suppression configuration includes the indication of a noise suppression aggressiveness; and transmitting the output audio data.

17 . The method of claim 16 , wherein determining to not suppress the subset of the plurality of types of background audio data comprises:
receiving an input from the user that specifies the noise suppression configuration indicating the subset of the plurality of types of background audio data.

18 . The method of claim 17 , further comprising:
generating a graphical user interface on a display, wherein the graphical user interface provides a plurality of selections corresponding to the plurality of types of background audio data; receiving one or more second indications, via the graphical user interface, which identifies the subset of the plurality of background audio data to suppress; and determining to suppress a subset of the plurality of types of background audio data based on the one more second indications.

19 . The method of claim 18 , wherein generating the graphical user interface comprises:
adaptively detecting the plurality of types of background audio data; and adaptively updating the plurality of selections based on the plurality of types of background audio data based detected.

20 . The method of claim 16 , wherein the subset of the plurality of types of background audio data include background audio data related to security.

21 . The method of claim 16 , wherein classifying the background audio data into the plurality of types of background audio data comprises:
processing the audio data using an artificial intelligence process to identify the plurality of types of background audio data.

Assignees

• Qualcomm Inc

Inventors

• Gogineni Ravi Teja
• Challa Deepak Kumar
• Lee Jeesok
• Gajjala Durga Prasad Reddy

Classifications

• G10L2015/225

  Feedback of the input speech · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/08

  Speech classification or search · CPC title

• G10L21/0208 Primary

  Noise filtering · CPC title

• G10L25/51

  for comparison or discrimination · CPC title