阅读说明：本技术 一种智能家居声控开关系统及控制方法 (Intelligent household voice-operated switch system and control method ) 是由 江新 于 2020-04-09 设计创作，主要内容包括：本发明提供一种智能家居声控开关系统及控制方法,涉及电子设备技术领域,所述系统包括采集模块、处理模块、识别模块、指令选择模块及中央处理器,所述采集模块包括多个声音采集器,多个声音采集器分布于各个房间内,用于获取各个房间内的语音；处理模块用于每个房间内的语音进行预处理,并采集语音的声纹特征和信号幅度值；所述识别模块根据声纹特征和信号幅度值对语音进行判断,生成判断结果；指令选择模块根据识别模块的判断结果选择至少一种语音,并提取语音内的关键字生成语音指令；本发明用于解决现有技术中智能家居声控开关系统对语音的采集不够灵敏,易受到外部环境的干扰,无法准确的判断是噪音还是控制语音,易产生误操作的技术问题。(The invention provides an intelligent household voice-operated switch system and a control method, which relate to the technical field of electronic equipment, wherein the system comprises an acquisition module, a processing module, an identification module, an instruction selection module and a central processing unit, wherein the acquisition module comprises a plurality of sound collectors which are distributed in each room and used for acquiring voices in each room; the processing module is used for preprocessing the voice in each room and acquiring the voiceprint characteristics and the signal amplitude value of the voice; the recognition module judges the voice according to the voiceprint characteristics and the signal amplitude value to generate a judgment result; the instruction selection module selects at least one voice according to the judgment result of the recognition module and extracts keywords in the voice to generate a voice instruction; the voice control switch system is used for solving the technical problems that in the prior art, an intelligent household voice control switch system is not sensitive to voice collection, is easily interfered by an external environment, cannot accurately judge whether noise or control voice is generated, and is easy to generate misoperation.)

1. An intelligent household sound control switch system used for controlling the on-off of household appliances is characterized by comprising an acquisition module, a processing module, an identification module, an instruction selection module and a central processing unit,

the acquisition module comprises a plurality of sound collectors distributed in each room and used for acquiring the voice in each room;

the processing module is used for preprocessing the voice in each room and acquiring the voiceprint characteristics and the signal amplitude value of the voice;

the recognition module judges the voice according to the voiceprint characteristics and the signal amplitude value to generate a judgment result;

the instruction selection module selects at least one voice according to the judgment result of the recognition module and extracts keywords in the voice to generate a voice instruction;

and the central processing unit identifies and processes the voice command, converts the voice command into a control signal and outputs the control signal to the corresponding household appliance controller.

2. The intelligent home voice-activated switch system according to claim 1, characterized in that: the processing module comprises a noise reduction processing unit and an extraction unit;

the noise reduction processing unit is used for performing noise reduction processing on voice;

the extraction unit is used for carrying out voiceprint normalization processing on the voice subjected to noise reduction processing, and extracting a voiceprint characteristic point value and a signal amplitude value.

3. The intelligent home voice-activated switch system according to claim 2, characterized in that: the identification module comprises a voiceprint comparison unit and a signal amplitude value comparison unit;

the voiceprint comparison unit is used for comparing voiceprint characteristics of a plurality of voices and judging whether the voices come from the same person or not;

the signal amplitude value comparison unit is used for comparing the signal amplitude values of a plurality of voices to obtain the voice with the maximum signal amplitude value.

4. The intelligent home voice-activated switch system according to claim 3, characterized in that: the instruction selection module comprises an integration unit, an amplification processing unit and a keyword extraction unit;

the integration unit is used for integrating the voices of the same person collected by the plurality of voice collectors to be used as selected voices;

the amplification processing unit is used for performing sound amplification processing on the voice with the maximum signal amplitude value to serve as the selected voice, and performing sound weakening processing on the sounds with the small other signal amplitude values;

the keyword extraction unit is used for extracting keywords in the selected voice and generating a voice instruction according to the keywords.

5. A control method of an intelligent household voice-operated switch is characterized by comprising the following steps:

s1: acquiring voices in each room;

s2: preprocessing the voice in each room, and collecting voiceprint characteristics and signal amplitude values of the voice;

s3: judging the voice according to the voiceprint characteristics and the signal amplitude value to generate a judgment result;

s4: selecting at least one voice according to the judgment result, and extracting keywords in the voice to generate a voice instruction;

s5: and recognizing and processing the voice command, converting the voice command into a control signal and outputting the control signal to the corresponding household appliance controller.

6. The control method of the intelligent household sound control switch according to claim 5, characterized in that: the S2 specifically includes:

s21: carrying out noise reduction processing on voice;

s22: and carrying out voiceprint normalization processing on the voice subjected to noise reduction processing, and extracting a voiceprint characteristic point value and a signal amplitude value.

7. The control method of the intelligent household sound control switch according to claim 5, characterized in that: the S3 specifically includes:

s31: comparing the voiceprint characteristics of a plurality of voices and judging whether the voices come from the same person or not;

s32: and comparing the signal amplitude values of the plurality of voices to obtain the voice with the maximum signal amplitude value.

8. The control method of the intelligent household sound control switch according to claim 7, characterized in that: the S4 specifically includes:

s41: integrating the languages of the same person collected by a plurality of sound collectors to be used as selected voices;

s42: if the voices from different people come, performing voice amplification processing on the voice with the largest signal amplitude value to serve as the selected voice, and performing voice weakening processing on the voices with smaller signal amplitude values;

s43: and extracting keywords in the selected voice, and generating a voice instruction according to the keywords.

Technical Field

The invention relates to the technical field of electronic equipment, in particular to an intelligent household voice-operated switch system and a control method.

Background

With the development of science and technology, smart homes are more and more popular with users, wherein a program of pressing a remote control voice key is omitted in the smart home voice control switch system, and users can execute a control command according to the command by only speaking the command, so that the smart home devices in a room are controlled, such as music playing, household appliance control and the like, and the smart home voice control switch system becomes very important user experience. At present, an intelligent voice control system is embedded into a plurality of intelligent homes, such as an intelligent sound box, an intelligent television, a vehicle, a watch, and various switch boxes and control boxes in the traditional home industry, so that the intelligent voice control system becomes a man-machine interaction and control center of a new generation of intelligent home.

The intelligent home voice control switch system integrates artificial intelligent voice search to change user experience, on one hand, voice recognition is carried out through the front end, for far-field voice recognition, sound source positioning is mainly carried out through microphone array hardware at the front end, voice enhancement is formed through self-adaptive wave beams, far-field pickup is further completed, and influences caused by noise, reverberation, echo and the like are solved; on the other hand, the recognition engine is carried out through the background, and the artificial intelligence algorithm is combined to realize natural man-machine interaction, so that a user can realize 'conversation' with an intelligent television or an intelligent box.

Then, the collection of current intelligent house acoustic control switching system to pronunciation is sensitive inadequately, and the speech acquisition ware sets up at a certain room usually, and the speech acquisition ware just can accurate discernment pronunciation need be walked to the place that sets up of speech acquisition ware to under the relatively noisy condition of people's voice, intelligent speech control system easily receives the interference of external environment, and the judgement that can't be accurate is the noise or controls pronunciation, easily produces the maloperation, consequently, it is intelligent still can't reach people's requirement.

Disclosure of Invention

In view of the above disadvantages of the prior art, an object of the present invention is to provide an intelligent home voice-operated switch system and a control method thereof, for solving the technical problems that the intelligent home voice-operated switch system in the prior art is not sensitive enough to voice collection, is easily interfered by an external environment, cannot accurately judge whether noise or control voice, and is easy to generate misoperation.

The invention provides an intelligent household sound control switch system which is used for controlling the on-off of household appliances and comprises an acquisition module, a processing module, an identification module, an instruction selection module and a central processing unit,

the acquisition module comprises a plurality of sound collectors distributed in each room and used for acquiring the voice in each room;

the processing module is used for preprocessing the voice in each room and acquiring the voiceprint characteristics and the signal amplitude value of the voice;

the recognition module judges the voice according to the voiceprint characteristics and the signal amplitude value to generate a judgment result;

the instruction selection module selects at least one voice according to the judgment result of the recognition module and extracts keywords in the voice to generate a voice instruction;

and the central processing unit identifies and processes the voice command, converts the voice command into a control signal and outputs the control signal to the corresponding household appliance controller.

In an embodiment of the present invention, the processing module includes a noise reduction processing unit and an extraction unit;

the noise reduction processing unit is used for performing noise reduction processing on voice;

the extraction unit is used for carrying out voiceprint normalization processing on the voice subjected to noise reduction processing, and extracting a voiceprint characteristic point value and a signal amplitude value to obtain a voiceprint characteristic point value 1, a signal amplitude value 1, a voiceprint characteristic point value 2, a signal amplitude value 2.

In an embodiment of the present invention, the identification module includes a voiceprint comparison unit and a signal amplitude value comparison unit;

the voiceprint comparison unit is used for comparing voiceprint characteristics of a plurality of voices and judging whether the voices come from the same person or not; specifically, comparing the voiceprint characteristic point values 1 and the voiceprint characteristic point values 2 one by one;

the signal amplitude value comparison unit is used for comparing signal amplitude values of a plurality of voices to obtain the voice with the largest signal amplitude value, and specifically, comparing the signal amplitude value 1 with the signal amplitude value 2

In an embodiment of the present invention, the instruction selection module includes an integration unit, an amplification processing unit, and a keyword extraction unit;

the integration unit is used for integrating the voices of the same person collected by the plurality of voice collectors to be used as selected voices;

the amplification processing unit is used for performing sound amplification processing on the voice with the maximum signal amplitude value to serve as the selected voice, and performing sound weakening processing on the sounds with the small other signal amplitude values;

the keyword extraction unit is used for extracting keywords in the selected voice and generating a voice instruction according to the keywords.

A control method of an intelligent household voice-operated switch comprises the following steps:

s1: acquiring voices in each room;

s2: preprocessing the voice in each room, and collecting voiceprint characteristics and signal amplitude values of the voice;

s3: judging the voice according to the voiceprint characteristics and the signal amplitude value to generate a judgment result;

s4: selecting at least one voice according to the judgment result, and extracting keywords in the voice to generate a voice instruction;

s5: and recognizing and processing the voice command, converting the voice command into a control signal and outputting the control signal to the corresponding household appliance controller.

In an embodiment of the present invention, the S2 specifically includes:

s21: carrying out noise reduction processing on voice;

s22: performing voiceprint normalization processing on the voice subjected to noise reduction processing, and extracting a voiceprint characteristic point value and a signal amplitude value;

in an embodiment of the present invention, the S3 specifically includes:

s31: comparing the voiceprint characteristics of a plurality of voices and judging whether the voices come from the same person or not;

s32: and comparing the signal amplitude values of the plurality of voices to obtain the voice with the maximum signal amplitude value.

In an embodiment of the present invention, the S4 specifically includes:

s41: integrating the languages of the same person collected by a plurality of sound collectors to be used as the selected voices, wherein for example, if the voiceprint characteristic point value 1 is the same as the voiceprint characteristic point value 2, the voiceprint characteristic point value 1 and the voiceprint characteristic point value 2 indicate that the sound 1 and the sound 2 come from the sound of the same person, and then the sound 1 and the sound 2 are integrated;

s42: if the voices from different people come, performing voice amplification processing on the voice with the largest signal amplitude value to serve as the selected voice, and performing voice weakening processing on the voices with smaller signal amplitude values;

s43: and extracting keywords in the selected voice, and generating a voice instruction according to the keywords.

As described above, the present invention has the following advantageous effects:

1. according to the invention, the plurality of sound collectors are arranged in each room, so that the speaking sound in each room can be collected, the sensitivity of sound collection is improved, and the voice control switch is more intelligent.

2. According to the voice recognition method, the voice print characteristics are recognized and judged, so that whether the voice collected by each voice collector is the voice of the same person or not is obtained through analysis, if the voice is the voice of the same person, misoperation cannot be caused, and all the voices only need to be integrated into one voice and a voice instruction is generated; if the sounds of different persons are obtained through analysis, which voice is the control voice needs to be judged at the moment, the signal amplitude value needs to be compared, the voice with the maximum signal amplitude value is selected as the voice command, and other sounds are weakened, so that the probability of misoperation is effectively reduced.

Drawings

FIG. 1 is a block diagram of the system architecture disclosed in the present invention;

FIG. 2 is a diagram illustrating a relationship between an identification module and an instruction selection module according to the present disclosure;

FIG. 3 is a diagram illustrating the steps of the disclosed method;

FIG. 4 is a detailed step diagram of S2 disclosed in the present invention;

FIG. 5 is a detailed step diagram of S3 disclosed in the present invention;

fig. 6 shows a detailed step diagram of S4 disclosed in the present invention.

Detailed Description

The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.

Referring to fig. 1 and 2, the present invention provides an intelligent home voice-controlled switch system for controlling the switching of household appliances, the system includes an acquisition module, a processing module, an identification module, an instruction selection module and a central processing unit,

the acquisition module comprises a plurality of sound collectors distributed in each room and used for acquiring voices in each room and ensuring that speeches in each room can be acquired;

the processing module is used for preprocessing the voice in each room and acquiring the voiceprint characteristics and the signal amplitude value of the voice;

the recognition module judges the voice according to the voiceprint characteristics and the signal amplitude value to generate a judgment result;

the instruction selection module selects at least one voice according to the judgment result of the recognition module and extracts keywords in the voice to generate a voice instruction;

in this embodiment, the collection module includes a sound collector 1 and a sound collector 2.. sound collector n, which respectively collect sound 1 and sound 2.. sound n,

the central processing unit identifies and processes the voice command, converts the voice command into a control signal and outputs the control signal to the corresponding household appliance controller; for example: the voice instruction content is 'turn on the air conditioner', the central processing unit sends a control signal to a controller of the air conditioner, and the air conditioner is turned on; the voice command content is 'light of living room is turned off', the central processing unit sends a control signal to the controller of the air conditioner to turn off … the light of the living room, and the like.

In this embodiment, the system further includes a wake-up voice library and a keyword library, where the wake-up voice library includes statements for waking up the acquisition module, such as "smallness", "hello love", "ding dong", and the like, and wakes up each sound collector in the acquisition module through the wake-up statements; the keyword library comprises control sentences and keywords.

Based on the above embodiment, the processing module includes a noise reduction processing unit and an extraction unit;

the noise reduction processing unit is used for performing noise reduction processing on voice;

the extraction unit is used for carrying out voiceprint normalization processing on the voice subjected to noise reduction processing so as to improve the stability of analysis and extracting voiceprint characteristic point values and signal amplitude values.

Based on the above embodiment, the identification module includes a voiceprint comparison unit and a signal amplitude value comparison unit;

the voiceprint comparison unit is used for comparing voiceprint characteristics of a plurality of voices and judging whether the voices come from the same person.

The signal amplitude value comparison unit is used for comparing signal amplitude values of a plurality of voices to obtain the voice with the largest signal amplitude value;

preferably, the signal amplitude comparison unit further determines whether the voice is a command voice or not and whether the voice is speaking to the voice-operated switch system or not according to the voice of the speaker.

Based on the above embodiment, the instruction selection module includes an integration unit, an amplification processing unit, and a keyword extraction unit;

the integration unit is used for integrating the voices of the same person collected by the plurality of voice collectors to be used as selected voices;

the amplification processing unit is used for performing sound amplification processing on the voice with the maximum signal amplitude value to serve as the selected voice, and performing sound weakening processing on the sounds with the small other signal amplitude values;

the keyword extraction unit is used for extracting keywords in the selected voice (judging according to the keywords in the keyword library) and generating voice commands according to the keywords.

In the embodiment, whether the voice collected by each voice collector is the voice of the same person is judged, if the voice is the voice of the same person, misoperation cannot be caused, and all the voices are integrated into one voice and a voice instruction is generated; if the sounds of different persons are obtained through analysis, which voice is the control voice needs to be judged at the moment, the signal amplitude value needs to be compared, the voice with the maximum signal amplitude value is selected as the voice command, and other sounds are weakened, so that the probability of misoperation is effectively reduced.

Referring to fig. 3, a method for controlling an intelligent home voice-operated switch includes the following steps:

s1: acquiring voices in each room;

s2: preprocessing the voice in each room, and collecting voiceprint characteristics and signal amplitude values of the voice;

s3: judging the voice according to the voiceprint characteristics and the signal amplitude value to generate a judgment result;

s4: selecting at least one voice according to the judgment result, and extracting keywords in the voice to generate a voice instruction;

s5: and recognizing and processing the voice command, converting the voice command into a control signal and outputting the control signal to the corresponding household appliance controller.

Referring to fig. 4, based on the above embodiment, the S2 specifically includes:

s21: carrying out noise reduction processing on voice;

s22: and carrying out voiceprint normalization processing on the voice subjected to noise reduction processing, and extracting a voiceprint characteristic point value and a signal amplitude value.

Referring to fig. 5, based on the above embodiment, the S3 specifically includes:

s31: comparing the voiceprint characteristics of a plurality of voices and judging whether the voices come from the same person or not;

s32: and comparing the signal amplitude values of the plurality of voices to obtain the voice with the maximum signal amplitude value.

Referring to fig. 6, based on the above embodiment, the S4 specifically includes:

s41: integrating the languages of the same person collected by a plurality of sound collectors to be used as selected voices;

s42: if the voices from different people come, performing voice amplification processing on the voice with the largest signal amplitude value to serve as the selected voice, and performing voice weakening processing on the voices with smaller signal amplitude values;

s43: and extracting keywords in the selected voice, and generating a voice instruction according to the keywords.

In summary, the voice collector is arranged in each room, so that the problem of low voice collection sensitivity is effectively solved, and the voice is identified and selected by the identification module and the instruction selection module, so that the probability that misjudgment is easily caused when a plurality of voice collectors collect voice at the same time is reduced. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.