Method for processing signals, terminal device, and non-transitory readable storage medium

Patent metadata

Field	Value
Publication number	US-10923129-B2
Application number	US-201916246768-A
Country	US
Kind code	B2
Filing date	Jan 14, 2019
Priority date	Mar 30, 2018
Publication date	Feb 16, 2021
Grant date	Feb 16, 2021

Abstract

A method for processing signals, a terminal device, and a non-transitory readable storage medium are provided. The method includes the following operations. A sound signal of external environment is collected via an electroacoustic transducer of a headphone when a user talks through the headphone. Feature audio of the sound signal is identified and whether the feature audio matches a preset sound model is determined. The user is reminded in a preset reminding manner corresponding to the feature audio based on a determination that the feature audio matches the preset sound model.

First claim

What is claimed is:

1. A method for processing signals, comprising:
collecting, via an electroacoustic transducer of a headphone, a sound signal of external environment when a user talks through the headphone;
identifying feature audio of the sound signal and determining whether the feature audio matches a preset sound model; and
reminding the user in a preset reminding manner corresponding to the feature audio based on a determination that the feature audio matches the preset sound model;
wherein the electroacoustic transducer comprises at least one speaker configured to play an audio signal; and wherein collecting, via the electroacoustic transducer of the headphone, the sound signal of external environment when the user talks through the headphone comprises: collecting, by the at least one speaker of the headphone, the sound signal of the external environment, when the user talks through the headphone;
wherein the electroacoustic transducer further comprises a second microphone configured to collect a voice signal from the user; and wherein the method further comprises: denoising the voice signal from the user collected by the second microphone according to the sound signal of the external environment;
wherein the at least one speaker comprises a first speaker and a second speaker, and the method further comprises: acquiring the sound signal collected by the second microphone, the first speaker, and the second speaker of the headphone; acquiring location information of the sound signal relative to the headphone according to time delays of receiving the sound signal by the second microphone, the first speaker, and the second speaker; and reminding the user according to the location information;
wherein acquiring the location information of the sound signal relative to the headphone according to the time delays of receiving the sound signal by the second microphone, the first speaker, and the second speaker comprises: acquiring three time delays by using the second microphone, the first speaker, and the second speaker respectively as a reference microphone, wherein a time interval at which the sound signal reaches any two of the second microphone, the first speaker, and the second speaker is called a time delay; acquiring an average time delay according to the three time delays; and estimating the location information of the sound signal according to the average time delay and acquiring the location information of the sound signal relative to the headphone.

2. The method of claim 1 , wherein the electroacoustic transducer comprises a first microphone close to the at least one speaker of the headphone; and
wherein collecting, via the electroacoustic transducer of the headphone, the sound signal of external environment when the user talks through the headphone comprises:
collecting, by the first microphone of the headphone, the sound signal of the external environment, when the user talks through the headphone.

3. The method of claim 1 , wherein identifying the feature audio of the sound signal and determining whether the feature audio matches the preset sound model comprises at least one of:
extracting noise information in the sound signal and determining whether the noise information matches a preset noise model;
extracting voiceprint information in the sound signal and determining whether the voiceprint information matches a sample voiceprint information; and
extracting sensitive information in the sound signal, determining whether the sensitive information matches a preset keyword.

4. The method of claim 1 , wherein reminding the user in the preset reminding manner corresponding to the feature audio comprises:
determining the preset reminding manner corresponding to the feature audio according to a correspondence between feature audio and preset reminding manners, the preset reminding manner comprising at least one of preset reminder content display-remind, vibration-remind, display-remind, and simulation-remind; and
reminding the user in the preset reminding manner determined.

5. The method of claim 2 , further comprising:
acquiring the sound signal collected by the first microphone, the first speaker, and the second speaker of the headphone;
acquiring the location information of the sound signal relative to the headphone according to time delays of receiving the sound signal by the first microphone, the first speaker, and the second speaker; and
reminding the user according to the location information.

6. The method of claim 5 , wherein acquiring the location information of the sound signal relative to the headphone according to the time delays of receiving the sound signal by the first microphone, the first speaker, and the second speaker comprises:
acquiring three time delays by using the first microphone, the first speaker, and the second speaker respectively as a reference microphone;
acquiring an average time delay according to the three time delays; and
estimating the location information of the sound signal according to the average time delay and acquiring the location information of the sound signal relative to the headphone.

7. A terminal device, comprising:
at least one processor; and
a computer readable storage, coupled to the at least one processor and storing at least one computer executable instruction thereon which, when executed by the at least one processor, cause the at least one processor to carry out actions, comprising:
collecting, via an electroacoustic transducer of a headphone, a sound signal of external environment when a user talks through the headphone;
identifying feature audio of the sound signal and determining whether the feature audio matches a preset sound model; and
reminding the user in a preset reminding manner corresponding to the feature audio based on a determination that the feature audio matches the preset sound model;
wherein the electroacoustic transducer comprises at least one speaker configured to play an audio signal; and the at least one processor carrying out the action of collecting, via the electroacoustic transducer of the headphone, the sound signal of external environment when the user talks through the headphone is caused to carry out actions, comprising: collecting, by the at least one speaker of the headphone, the sound signal of the external environment, when the user talks through the headphone;
wherein the at least one processor is further caused to carry out actions, comprising: denoising a voice signal from the user collected by a second microphone according to the sound signal of the external environment;
wherein the at least one speaker comprises a first speaker and a second speaker, and the at least one processor is further caused to carry out actions, comprising: acquiring the sound signal collected by the second microphone, the first speaker, and the second speaker of the headphone; acquiring location information of the sound signal relative to the headphone according to time delays of receiving the sound signal by the second microphone, the first speaker, and the second speaker; and reminding the user according to the location information;
wherein the at least one processor carrying out the action of acquiring the location information of the sound signal relative to the headphone according to the time delays of receiving the sound signal by the second microphone, the first speaker, and the second speaker is caused to carry out actions, comprising: acquiring three time delays by using the second microphone, the first speaker, and the second speaker respectively as a reference microphone, wherein a time interval at which the sound signal reaches any two of the second microphone, the first speaker, and the second speaker is called a time delay; acquiring an average time delay accord

Assignees

• Guangdong Oppo Mobile Telecommunications Corp Ltd

Inventors

• Yan Bixiang

Classifications

• H04R1/1016 Primary

  Earpieces of the intra-aural type · CPC title

• H04M1/72448

  with means for adapting the functionality of the device according to specific conditions · CPC title

• G10L17/06

  Decision making techniques; Pattern matching strategies · CPC title

• G10L25/84

  for discriminating voice from noise · CPC title

• G10L25/51

  for comparison or discrimination · CPC title