阅读说明：本技术 一种噪声消除方法、智能音箱及存储介质 (Noise elimination method, intelligent sound box and storage medium ) 是由 凌华东 于 2019-10-28 设计创作，主要内容包括：本发明公开了一种噪声消除方法、智能音箱及存储介质。本发明中本发明中语音交互设备与电视机之间无线连接,语音交互设备当被唤醒后,发送被唤醒通知至电视机；接收电视机通过无线传输方式发送的当前播放的电视音频信号；拾取包括电视噪声信号和用户语音信号的混合声音信号,并基于电视音频信号将混合声音信号中的电视噪声信号消除。本发明中可基于电视机发送的电视音频信号将拾取的混合声音信号中电视噪声信号消除,从而消除电视噪声信号对语音识别的干扰,提升语音识别准确率,提升用户体验。(The invention discloses a noise elimination method, an intelligent sound box and a storage medium. According to the invention, the voice interaction equipment is wirelessly connected with the television, and after being awakened, the voice interaction equipment sends an awakened notification to the television; receiving a currently played television audio signal sent by a television in a wireless transmission mode; a mixed sound signal including a television noise signal and a user speech signal is picked up, and the television noise signal in the mixed sound signal is canceled based on a television audio signal. According to the invention, the television noise signal in the picked mixed sound signal can be eliminated based on the television audio signal sent by the television, so that the interference of the television noise signal to voice recognition is eliminated, the voice recognition accuracy is improved, and the user experience is improved.)

1. A noise elimination method is applied to a voice interaction device, the voice interaction device is in wireless connection with a television, and the noise elimination method comprises the following steps:

when the television is awakened, sending an awakened notification to the television;

receiving a currently played television audio signal sent by a television in a wireless transmission mode;

a mixed sound signal comprising a television noise signal and a user speech signal is picked up and the television noise signal in the mixed sound signal is cancelled based on the television audio signal.

2. The method of claim 1, wherein the step of canceling the television noise signal in the mixed sound signal based on the television audio signal comprises the steps of:

adjusting the amplitude and phase of the television audio signal to generate a television noise reference signal; the amplitude and the phase of the television noise reference signal are respectively equal to the amplitude and the phase of the television noise signal;

canceling the television noise signal in the mixed sound signal based on the television noise reference signal.

3. The method of claim 2, wherein the step of adjusting the amplitude and phase of the television audio signal to generate the television noise reference signal comprises:

performing spectral analysis on the television audio signal;

extracting a television noise signal having the same frequency distribution as in the spectral analysis result from the mixed sound signal based on the spectral analysis result;

calculating the amplitude difference and the phase difference of the television audio signal and the television noise signal;

adjusting the amplitude and phase of the television audio signal based on the amplitude difference and the phase difference to generate a television noise reference signal.

4. The method according to claim 3, wherein the step of canceling the TV noise signal in the mixed sound signal based on the TV noise reference signal comprises:

carrying out self-adaptive filtering processing on the television noise reference signal to obtain a cancellation estimation signal;

subtracting the cancellation estimate signal from the mixed sound signal to cancel the television noise signal in the mixed sound signal.

5. The method of claim 4, wherein the step of adaptively filtering the television noise reference signal comprises:

and carrying out self-adaptive filtering processing on the television noise reference signal based on a minimum mean square algorithm or a recursive least square algorithm.

6. The noise cancellation method according to claim 1, further comprising:

and after being awakened, sending an awakened notification to the television so that the television can reduce the volume of the television audio signal according to the awakened notification.

7. The noise cancellation method according to claim 6, characterized in that the noise cancellation method further comprises:

and after quitting and awakening, sending a quit and awakening notice to the television so that the volume of the television audio signal is increased by the television according to the quit and awakening notice.

8. A noise cancellation method, characterized in that the noise cancellation method comprises:

when the voice interaction equipment is awakened, the voice interaction equipment sends an awakened notification to the television;

the television sends the currently played television audio signal to the voice interaction equipment in a wireless transmission mode according to the awakened notification;

the voice interaction device picks up a mixed sound signal comprising a television noise signal and a user voice signal and cancels the television noise signal in the mixed sound signal based on the television audio signal.

9. A smart sound box comprising a processor and a memory, wherein the processor is coupled to the memory and executes instructions to implement the noise cancellation method of any one of claims 1 to 7 when in operation.

10. A storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the noise cancellation method of any one of claims 1 to 7.

Technical Field

The present invention relates to the field of speech processing technologies, and in particular, to a noise cancellation method, an intelligent speaker, and a storage medium.

Background

Along with the development of science and technology, more and more families begin to use the intelligent audio amplifier equipment that has the speech recognition function, in the family, the user can place intelligent audio amplifier by TV set on the TV bench usually, when TV set broadcast sound, TV set sound can be picked up to intelligent audio amplifier, TV set sound is great and be the non-noise form, intelligent audio amplifier can be with TV set sound identification for user's sound, and then the misidentification user instruction in the follow user's sound, thereby make the unexpected response of user, seriously reduce user experience.

Disclosure of Invention

The invention mainly provides a noise elimination method, which can solve the problems that the existing intelligent sound box can make unexpected responses of a user due to the fact that the sound of a television is mistakenly identified as a user instruction, and the user experience is reduced.

In order to solve the technical problems, the invention adopts a technical scheme that: the noise elimination method is applied to voice interaction equipment which is in wireless connection with a television, and comprises the following steps:

when the television is awakened, sending an awakened notification to the television;

receiving a currently played television audio signal sent by a television in a wireless transmission mode;

a mixed sound signal comprising a television noise signal and a user speech signal is picked up and the television noise signal in the mixed sound signal is cancelled based on the television audio signal.

Preferably, the step of canceling the television noise signal in the mixed sound signal based on the television audio signal specifically includes the steps of:

adjusting the amplitude and phase of the television audio signal to generate a television noise reference signal; the amplitude and the phase of the television noise reference signal are respectively equal to the amplitude and the phase of the television noise signal;

canceling the television noise signal in the mixed sound signal based on the television noise reference signal.

Preferably, the step of adjusting the amplitude and the phase of the television audio signal to generate the television noise reference signal specifically includes:

performing spectral analysis on the television audio signal;

extracting a television noise signal having the same frequency distribution as in the spectral analysis result from the mixed sound signal based on the spectral analysis result;

calculating the amplitude difference and the phase difference of the television audio signal and the television noise signal;

adjusting the amplitude and phase of the television audio signal based on the amplitude difference and the phase difference to generate a television noise reference signal.

Preferably, the step of canceling the tv noise signal in the mixed sound signal based on the tv noise reference signal specifically includes:

carrying out self-adaptive filtering processing on the television noise reference signal to obtain a cancellation estimation signal;

subtracting the cancellation estimate signal from the mixed sound signal to cancel the television noise signal in the mixed sound signal.

Preferably, the step of performing adaptive filtering processing on the television noise reference signal specifically includes:

and carrying out self-adaptive filtering processing on the television noise reference signal based on a minimum mean square algorithm or a recursive least square algorithm.

Preferably, the noise canceling method further includes:

and after being awakened, sending an awakened notification to the television so that the television can reduce the volume of the television audio signal according to the awakened notification.

Preferably, the noise canceling method further includes:

and after quitting and awakening, sending a quit and awakening notice to the television so that the volume of the television audio signal is increased by the television according to the quit and awakening notice.

In order to solve the technical problem, the invention adopts another technical scheme that: there is provided a noise canceling method including:

when the voice interaction equipment is awakened, the voice interaction equipment sends an awakened notification to the television;

the television sends the currently played television audio signal to the voice interaction equipment in a wireless transmission mode according to the awakened notification;

the voice interaction device picks up a mixed sound signal comprising a television noise signal and a user voice signal and cancels the television noise signal in the mixed sound signal based on the television audio signal.

In order to solve the technical problem, the invention adopts another technical scheme that: the processor is coupled with the memory, and executes instructions to realize the noise elimination method when in work.

In order to solve the technical problem, the invention adopts another technical scheme that: there is provided a storage medium having stored thereon a computer program to be executed by a processor to implement the noise cancellation method described above.

The invention has the beneficial effects that: different from the situation of the prior art, the voice interaction device is wirelessly connected with the television, and after being awakened, the voice interaction device sends an awakened notification to the television; receiving a currently played television audio signal sent by a television in a wireless transmission mode; a mixed sound signal including a television noise signal and a user speech signal is picked up, and the television noise signal in the mixed sound signal is canceled based on a television audio signal. According to the invention, the television noise signal in the picked mixed sound signal can be eliminated based on the television audio signal sent by the television, so that the interference of the television noise signal to voice recognition is eliminated, the voice recognition accuracy is improved, and the user experience is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive efforts, wherein:

fig. 1 is a flow chart of a noise cancellation method according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating an implementation of step S300 in FIG. 1;

FIG. 3 is a flow chart of a noise cancellation method according to another embodiment of the present invention;

fig. 4 is a schematic structural diagram of an intelligent sound box according to another embodiment of the present invention;

fig. 5 is a schematic structural diagram of a storage medium according to another embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.