CN106920548B - Voice control device, voice control system, and voice control method - Google Patents
Voice control device, voice control system, and voice control method Download PDFInfo
- Publication number
- CN106920548B CN106920548B CN201510989140.0A CN201510989140A CN106920548B CN 106920548 B CN106920548 B CN 106920548B CN 201510989140 A CN201510989140 A CN 201510989140A CN 106920548 B CN106920548 B CN 106920548B
- Authority
- CN
- China
- Prior art keywords
- voice
- voiceprint
- mode
- control
- template
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004891 communication Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 150000001875 compounds Chemical class 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 239000000284 extract Substances 0.000 description 6
- 230000003993 interaction Effects 0.000 description 5
- 241001672694 Citrus reticulata Species 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Telephonic Communication Services (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a voice control device, a voice control system and a voice control method, wherein the device comprises: the voice acquisition module is used for receiving voice signals; the voice recognition module is used for generating voice characteristics according to the voice signals, judging the voice characteristics according to the current working mode of the voice control device and generating a voice command when judging that the voice characteristics are matched with a voice template corresponding to the current working mode; the first communication module is used for carrying out wireless communication with the intelligent terminal; and the control module is used for generating a control instruction according to the voice command and sending the control instruction to the intelligent terminal through the first wireless communication module so that the intelligent terminal works according to the control instruction. Therefore, the working mode meeting the voice condition of the user can be selected according to the user, the voice recognition accuracy is improved, different requirements of different users on voice control can be met, and voice control such as voice awakening can be performed on the intelligent terminal.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a voice control apparatus, a voice control system, and a voice control method of a voice control apparatus.
Background
With the development of electronic product technology, users have higher and higher additional requirements on electronic products, and voice recognition control technology is more and more promoted. In the related art, the electronic product cannot accurately recognize the voice uttered by the user by using the voice recognition technology, for example, the electronic product cannot recognize the voice or dialect with an abnormal pronunciation, so that different requirements of different users on voice control cannot be met. In addition, related electronic products usually need to press a mechanical key to wake up when in standby, which affects the use of users.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art. To this end, it is an object of the present invention to provide a voice control device that can meet different requirements of different users for voice control.
The invention also aims to provide a voice control system, and the invention also aims to provide a voice control method of the voice control device.
In order to achieve the above object, an embodiment of the present invention provides a voice control apparatus, including: the voice acquisition module is used for receiving a voice signal; the voice recognition module is used for generating voice characteristics according to the voice signals, judging the voice characteristics according to the current working mode of the voice control device and generating a voice command when judging that the voice characteristics are matched with a voice template corresponding to the current working mode; the first communication module is used for carrying out wireless communication with the intelligent terminal; and the control module is used for generating a control instruction according to the voice command and sending the control instruction to the intelligent terminal through the first wireless communication module so that the intelligent terminal works according to the control instruction.
According to the voice control device provided by the embodiment of the invention, the voice recognition module can judge the voice characteristics according to the current working mode of the voice control device and generate a voice command when the voice characteristics are judged to be matched with the voice template corresponding to the current working mode, and the control module generates a control instruction according to the voice command and sends the control instruction to the intelligent terminal so that the intelligent terminal works according to the control instruction. Therefore, the device can select a working mode which meets the voice condition of the user according to the user, improves the voice recognition accuracy, and can meet different requirements of different users on voice control.
In order to achieve the above object, another embodiment of the present invention provides a voice control system, including: the voice control device; and the intelligent terminal is communicated with the voice control device.
According to the voice control system provided by the embodiment of the invention, the voice recognition accuracy can be improved through the voice control device, and the intelligent terminal is subjected to voice control such as voice awakening.
In order to achieve the above object, another embodiment of the present invention provides a voice control method for a voice control apparatus, including: receiving a voice signal and generating a voice characteristic according to the voice signal; acquiring a current working mode of a voice control device, and judging the voice characteristics according to the current working mode; generating a voice command when the voice characteristics are judged to be matched with the voice template corresponding to the current working mode, and generating a control instruction according to the voice command; and sending the control instruction to an intelligent terminal which is communicated with the voice control device so that the intelligent terminal works according to the control instruction.
According to the voice control method of the voice control device provided by the embodiment of the invention, the voice characteristics can be judged according to the current working mode of the voice control device, the voice command is generated when the voice characteristics are judged to be matched with the voice template corresponding to the current working mode, and then the control instruction is generated according to the voice command and is sent to the intelligent terminal, so that the intelligent terminal works according to the control instruction. Therefore, the method can work in a working mode meeting the voice condition of the user according to the selection of the user, improves the voice recognition accuracy, and can also meet different requirements of different users on voice control.
Drawings
FIG. 1 is a block schematic diagram of a voice-controlled apparatus according to an embodiment of the present invention;
FIG. 2 is a block diagram of a speech recognition module according to one embodiment of the present invention;
FIG. 3 is a schematic diagram of the operation of a voice control apparatus according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of the operating current of a voice control device according to one embodiment of the present invention;
FIG. 5 is a block diagram of a voice-controlled apparatus according to an embodiment of the present invention;
FIG. 6 is a block schematic diagram of a speech control system according to an embodiment of the present invention;
FIG. 7 is a flow chart of a voice control method of a voice control apparatus according to an embodiment of the present invention;
FIG. 8 is a flow chart of a voice control method of a voice control apparatus according to one embodiment of the present invention; and
fig. 9 is a flowchart of a voice recording method of an intelligent terminal according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
A voice control apparatus, a voice control system, and a voice control method of a voice control apparatus according to embodiments of the present invention will be described below with reference to the accompanying drawings, in which the voice control apparatus can control an intelligent terminal according to a sound made by a user.
Fig. 1 is a block schematic diagram of a voice control apparatus according to an embodiment of the present invention. As shown in fig. 1, the voice control apparatus 100 includes: the voice recognition system comprises a voice acquisition module 10, a voice recognition module 20, a first communication module 30 and a control module 40.
The voice acquisition module 10 is configured to receive a voice signal, and specifically, the voice acquisition module 10 may be a digital microphone; the voice recognition module 20 is connected to the voice acquisition module 10, and the voice recognition module 20 is configured to generate a voice feature according to the voice signal, judge the voice feature according to the current working mode of the voice control apparatus 100, and generate a voice command when judging that the voice feature matches with a voice template corresponding to the current working mode; the first communication module 30 is used for performing wireless communication with the intelligent terminal 200; the control module 40 is connected to the voice recognition module 20 and the first communication module 30, respectively, and the control module 40 is configured to generate a control instruction according to the voice command, and send the control instruction to the intelligent terminal 200 through the first wireless communication module 30, so that the intelligent terminal 200 operates according to the control instruction.
Specifically, the voice collecting module 10 may monitor the external sound in real time, and after the voice collecting module 10 receives the external voice signal, the voice recognition module 20 may condition and perform analog-to-digital conversion on the voice signal, i.e., the analog voice signal, to generate a digital voice signal, and then process the digital voice signal according to the current working mode to recognize the voice command corresponding to the voice signal. Then, the voice recognition module 20 may transmit the corresponding voice command to the control module 40, the control module 40 starts up after receiving the voice command and generates a control instruction according to the voice command, and transmits the control instruction to the intelligent terminal 200, and the intelligent terminal 200 executes the control instruction after receiving the control instruction, so that the intelligent terminal 200 may be controlled by sound without manual operation.
It should be understood that the control command may include a wake-up control command, a standby control command, a dial control command, and the like, so that when the intelligent terminal 200 receives the wake-up control command, the human-computer interaction interface may be controlled to be lit; when the intelligent terminal 200 receives the standby control instruction, the human-computer interaction interface can be controlled to be turned off; when the intelligent terminal 200 receives the dialing control instruction, a dialing interface may be displayed to dial the terminal specified in the dialing control instruction.
It should be noted that the voice command may be a hexadecimal or binary coded signal.
For example, the voice collecting module 10 may receive an "on" voice signal sent by a user, when the voice recognizing module 20 recognizes that a voice feature of the "on" voice signal matches an "on" voice feature in a voice template corresponding to the current working mode, the voice recognizing module 20 may send a voice command corresponding to the "on" voice feature in the voice template to the control module 40, the control module 40 sends a wake-up control instruction to the intelligent terminal 200 after receiving the voice command, and the intelligent terminal 200 may display a human-computer interaction interface after receiving the wake-up control instruction. Similarly, the voice acquisition module 10 may also receive a "close" voice signal sent by the user, and the control module 40 may send a standby control instruction to the intelligent terminal 200 after the voice recognition module 20 recognizes the "close" voice signal, and the intelligent terminal 200 will not display a human-computer interaction interface, thereby implementing operations such as standby or wakeup through the voice control intelligent terminal, without manually triggering a key, and freeing both hands.
According to a specific example of the present invention, the speech recognition module 20 may be an iM401D speech recognition chip, and the control module 40 may be a CSR8670 control chip. The speech recognition module 20 and the control module 40 may communicate with each other in an I2C bus (Inter-Integrated Circuit bus). The voice control device 100 and the smart terminal 200 may communicate with each other in a bluetooth communication manner.
According to an embodiment of the present invention, the control module 40 is turned off when the voice control apparatus 100 is in a standby state and turned on when a voice command is received.
Specifically, after the first communication module 30 in the voice control apparatus 100 establishes a communication connection with the smart terminal, the voice control apparatus 100 and the smart terminal 200 enter a standby state, in which the first communication module 30 and the control module 40 are turned off when the voice control apparatus 100 is in the standby state. The voice acquisition module 10 and the voice recognition module 20 are still turned on, the voice recognition module 20 recognizes the voice signal received by the voice acquisition module 10 and generates a voice command after recognizing the voice signal, the control module 40 is turned on after receiving the voice command and controls the first communication module 30 and other peripheral circuits to be turned on, the voice control device 100 enters an awake state, of course, the control module 40 also generates a control instruction according to the voice command and sends the control instruction to the intelligent terminal 200, and the intelligent terminal 200 receives the control instruction and enters the awake state.
Therefore, the control chip and other related circuits are started after receiving the voice command, and the power consumption can be greatly reduced.
According to an embodiment of the present invention, the operation modes of the voice control apparatus 100 include a voiceprint mode, a voice mode, and a compound mode, wherein the compound mode is composed of the voiceprint mode and the voice mode.
It should be noted that, in the voiceprint mode, the voice control apparatus 100 can recognize the personal voiceprint, and the voiceprint recognition can only recognize that the voiceprint records the voice command of the user, and other people who speak the same voice command are not effective and have special voice command authority. Briefly, personal voiceprint recognition is the process of identifying whether a certain segment of speech is spoken by a given person, and requires modeling the voiceprint of a speaker, which is a process called "training" or "learning". In the voice mode, the voice control apparatus 100 can recognize each person's voice, and the voice recognition can recognize that any person speaks the same voice command, is not limited to a certain person's voice command, and has a normal voice command authority.
Further, according to an embodiment of the present invention, when the current operating mode is the voiceprint mode, the speech recognition module 20 determines the speech characteristics according to a voiceprint recognition algorithm corresponding to the voiceprint mode and a personal voiceprint template established by the user voiceprint information. It should be noted that the personal voiceprint template includes a plurality of voiceprint information, each voiceprint information corresponds to a voice command, so that the voice recognition module 20 can extract the voiceprint information from the voice feature according to the voiceprint recognition algorithm, and can recognize the voice signal when the extracted voiceprint information is judged to be matched with one voiceprint information in the personal voiceprint template.
When the current operating mode is a voice mode, the voice recognition module 20 determines the voice characteristics according to a standard voice recognition algorithm corresponding to the voice mode and a pre-stored standard voice template. It should be noted that the standard voice template may be a mandarin voice template, a dialect voice template, etc., the standard voice template may be established according to voice data in a voice database, and the standard voice template may be produced and pre-stored in the voice control apparatus 100, and the standard voice template includes a plurality of voice content information, each of which corresponds to a voice command, so that a voice content may be extracted from a voice feature according to a standard voice recognition algorithm, and when it is determined that the extracted voice content matches with one of the voice content information in the standard voice template, a voice signal may be recognized.
When the current working mode is the compound mode, the voice recognition module 20 firstly determines the voice features according to the voiceprint recognition algorithm corresponding to the voiceprint mode and the personal voiceprint template established by the user voiceprint information, and then determines the voice features according to the standard voice recognition algorithm corresponding to the voice mode and the pre-stored standard voice template when the voice features are not matched with the personal voiceprint template established by the user voiceprint information.
It should be noted that the voice recognition module 20 may set a mode flag bit ID, and determine the current operating mode of the voice control apparatus according to the value of the mode flag bit ID, for example, when the ID is equal to 1, the current operating mode is a voiceprint mode; when the ID is 2, the current working mode is a voice mode; when the ID is 3, the current operation mode is the compound mode, in which the ID may be set to 1 at the initial setting.
Specifically, the voice recognition module 20 detects the mode flag ID. When detecting that the ID is 1, the voice recognition module 20 determines that the voice control apparatus is in the voiceprint mode, and then the voice control apparatus 100 and the smart terminal 200 enter a standby state. The voice collecting module 10 receives a voice signal, the voice recognizing module 20 generates a voice feature according to the voice signal and extracts voiceprint information from the voice feature, and compares the extracted voiceprint information with the personal voiceprint template, if the voiceprint information of the voice signal matches with one voiceprint information in the personal voiceprint template, the voice recognizing module 20 can obtain a voice command corresponding to the voice signal according to a corresponding relationship between the voiceprint information and the voice command in the personal voiceprint template, the control module 40 starts and sends a corresponding control instruction to the intelligent terminal 200 after receiving the voice command, and the intelligent terminal 200 can enter an awake state from a standby state and enter a related application scene, for example, start a recording or close an application scene such as a recording, etc. after receiving the control instruction. Of course, if the voiceprint information of the speech signal does not match each of the voiceprint information in the personal voiceprint template, speech recognition module 20 continues to recognize the speech signal.
It should be understood that different persons have different voiceprints, in the voiceprint mode, only the voice signal sent by the user who records the personal voiceprint template can control the intelligent terminal 200, and the voice signal sent by the user who does not record the personal voiceprint template can not control the intelligent terminal 200.
When detecting that the ID is 2, the voice recognition module 20 determines that the voice control apparatus is in a voice mode, in which a language, such as mandarin, dialect, etc., can be selected according to an instruction input by the user. After that, the voice control apparatus 100 and the smart terminal 200 enter a standby state. The voice collecting module 10 receives a voice signal, the voice recognizing module 20 generates a voice feature according to the voice signal and extracts a voice content from the voice feature, and compares the extracted voice content with a standard voice template, if the voice content of the voice signal matches with a voice content information in the standard voice template, the voice recognizing module 20 can obtain a voice command corresponding to the voice signal according to a corresponding relationship between the voice content information in the standard voice template and the voice command, the control module 40 starts and sends a corresponding control instruction to the intelligent terminal 200 after receiving the voice command, and the intelligent terminal 200 can enter an awake state from a standby state and enter a related application scene, for example, start or close an application scene such as recording. Of course, if the speech content of the speech signal does not match with the information of each speech content in the standard speech template, the speech recognition module 20 continues to recognize the speech signal.
It should be understood that in the voice mode, as long as the voice content of the voice signal is correct and the pronunciation of the user who utters the voice signal is accurate, the voice signal uttered by anyone can control the smart terminal 200.
When detecting that the ID is 3, the voice recognition module 20 determines that the voice control apparatus is in a voiceprint plus voice compound mode, in which the voice recognition module 20 preferentially recognizes the voiceprint information of the voice signal according to the voiceprint mode when the ID is 1, and if the voiceprint information of the voice signal cannot be recognized, recognizes the voice content of the voice signal according to the voice mode when the ID is 2.
For example, when the current working mode is in the voiceprint mode, if the voice collecting module 10 receives a "hello" voice signal sent by the user, the voice identifying module 20 identifies whether the voiceprint information of the "hello" voice signal matches with the "hello" voiceprint information in the personal voiceprint template, and acquires a voice instruction corresponding to the "hello" voiceprint information when matching, and at this time, because different people have different voiceprints, the recognition accuracy of the voice identifying module 20 will not be affected by abnormal pronunciation, dialect and the like.
When the current working mode is in the voice mode, if the voice collecting module 10 receives a "hello" voice signal sent by the user in mandarin, the voice identifying module 20 identifies whether the voice content "hello" of the "hello" voice signal matches with the "hello" voice content information in the personal voiceprint template, and acquires a voice instruction corresponding to the "hello" voice content information when matching, and at this time, the voice identifying module 20 can identify "hello" spoken by each person in more standard mandarin.
When the current working mode is in the compound mode, the voice recognition module 20 preferentially recognizes in the voiceprint mode, and recognizes in the voice mode after the voiceprint recognition fails.
Therefore, the voice control device provided by the embodiment of the invention can accurately identify the personal voiceprint or the standard voice, has strong compatibility, can be conveniently used by a user, can realize voice control such as voice awakening, and saves mechanical keys.
Further, the voice recognition module 20 is further configured to control the voice control apparatus 100 to enter a recording state according to a recording instruction sent by the intelligent terminal 200, generate voiceprint information according to a recorded voice signal, and establish a personal voiceprint template according to the voiceprint information.
That is, after receiving the recording command input by the user, the smart terminal 200 may forward the recording command to the voice control apparatus 100, the voice control apparatus 100 enters a recording state and starts recording, and the voice recognition module 20 may extract voiceprint information from the voice signal received by the voice acquisition module 10 and create a personal voiceprint template according to the extracted voiceprint information.
In another embodiment of the present invention, the voice recognition module 20 may generate voiceprint information according to the personal voice sample sent by the intelligent terminal 200, and establish a personal voiceprint template according to the generated voiceprint information. For example, in the initial use, after the bluetooth pairing between the voice control device 100 and the intelligent terminal 200 is successful, the control module 40 may send a recording prompt instruction to the intelligent terminal 200, the intelligent terminal 200 receives the recording prompt instruction to prompt the user, the intelligent terminal 200 starts to record a voice signal sent by the user after receiving the recording confirmation instruction of the user, stops recording after receiving the recording completion instruction, and sends the recorded personal voice sample to the voice control device 100, and the voice recognition module 20 may extract voiceprint information from the personal voice sample sent by the intelligent terminal 200, and establish a personal voiceprint template according to the extracted voiceprint information.
According to an embodiment of the present invention, as shown in fig. 2, the speech recognition module 20 includes a feature generation unit 201 and a signal processing unit 202.
Wherein, the feature generating unit 201 is used for generating voice features according to the voice signals; the signal processing unit 202 is configured to determine a voice feature according to the current working mode, and generate a voice command when it is determined that the voice feature matches a voice template corresponding to the current working mode. In one specific example of the present invention, the Signal processing unit 202 is a digital Signal processing (dsp) (digital Signal processing) chip or a micro Control unit (mcu).
Specifically, as shown in fig. 3, the speech recognition module 20 works as follows: the voice acquisition module receives a voice signal, for example, a human voice (frequency range is 20Hz to 20kHz), and then outputs an analog voice signal, the feature generation unit 201 in the voice recognition module 20 may perform filtering, windowing (1-20ms), analog-to-digital conversion, and other processing on the analog voice signal to generate a voice feature (digital voice signal), at this time, the feature generation unit 201 directly extracts the voice feature from the analog voice signal, and the voice feature cannot be used to reconstruct an original signal, so that privacy protection can be achieved. After generating the voice features, the signal processing unit 202 in the voice recognition module 20 may perform pattern recognition, tracking, and the like on the voice features, for example, compare the voice features with the voice template corresponding to the current operating mode to generate a voice command, and send the generated voice command to the control module 40 through I2C communication. After receiving the voice command, the control module 40 may generate a control command and send the control command to the smart terminal 200.
The feature generating unit 201 is further configured to extract byte voice features from the voice features, determine the extracted byte voice features according to the current working mode, and output a wake-up signal to the signal processing unit 202 when determining that the byte voice features are matched with the keyword information corresponding to the current working mode, so as to control the signal processing unit 202 to work.
It should be noted that the byte speech feature may refer to a speech feature corresponding to each byte in a segment of speech, for example, in an "on" speech signal, the speech feature corresponding to the "on" word and the speech feature corresponding to the "on" word are both byte speech features. The keyword information is the speech features corresponding to the keywords of each speech segment selected from the speech template to form the keyword information, for example, in the "on" speech signal, the "on" word can be selected as the keyword, and the speech features corresponding to the "on" word are entered into the keyword information. In this manner, when the byte voice feature extracted by the feature generation unit 201 matches the voice feature corresponding to "on", the signal processing unit 202 is controlled to operate.
The power-on initialization and control module 10 issues a driver to the voice recognition module 20, and then the control module 10 is in a standby state, while the voice collection module 10 and the voice recognition module 20 still work. In connection with the example of fig. 4, when the signal processing unit 202 is not operating, the feature generation unit 201 in the voice collection module 10 and the voice recognition module 20 operates at 270uA maximum operating current; when the signal processing unit 202 works, the voice signal is subjected to analog-to-digital conversion through the part C1, the maximum working current can reach 2mA, the voice signal after the analog-to-digital conversion is sent to the signal processing unit 202 for calculation, the maximum working current can reach 10mA instantly, the calculation can be completed within 10ms, and the maximum current in the whole process can reach 13mA instantly.
Therefore, by controlling the signal processing unit 202 to be started when the keyword is detected, the power consumption of the signal processing unit used for long time calculation can be greatly saved, and the power consumption can be saved by 85%.
In addition, according to an embodiment of the present invention, as shown in fig. 5, the voice control apparatus 100 may further include: lithium cell 50, lithium cell 50 is used for supplying power for voice acquisition module 10, speech recognition module 20, first communication module 30 and control module 40. The voice control device 100 further comprises components such as an indicator light 60, a key 70 and a USB interface 80, which are connected to the control module 40, wherein the indicator light 60 is used for prompting the state of the voice control device 100, the key 70 is used for receiving a command input by a user to perform function selection, and the USB interface 80 is used as a charging interface. The voice control apparatus 100 includes other components shown in fig. 5, which are not described in detail herein.
According to an example of the present invention, the carrier connected between each device in the voice control apparatus 100 is a Printed Circuit Board (PCB), and the PCB is processed by a die bonding process to form a PCBA (Printed Circuit Board + Assembly).
In summary, according to the voice control device provided in the embodiment of the present invention, the voice recognition module can determine the voice characteristics according to the current working mode of the voice control device, and generate the voice command when determining that the voice characteristics are matched with the voice template corresponding to the current working mode, and the control module generates the control instruction according to the voice command and sends the control instruction to the intelligent terminal, so that the intelligent terminal can work according to the control instruction. Therefore, the device can select a working mode which meets the voice condition of the user according to the user, improves the voice recognition accuracy, and can meet different requirements of different users on voice control. Moreover, the device can also carry out voice control, such as voice awakening, on the intelligent terminal.
The invention also provides a voice control system.
FIG. 6 is a block diagram of a speech control system according to an embodiment of the present invention. As shown in fig. 6, the voice control system includes the voice control apparatus 100 and the intelligent terminal 200, where the intelligent terminal 200 is configured to communicate with the voice control apparatus 100 to receive a control command sent by the voice control apparatus 100; the voice control apparatus 100 may generate a control instruction according to the received voice signal.
According to a specific example of the present invention, the voice control apparatus 100 may be a portable digital product such as a smart headset or a smart watch, and the smart terminal 200 may be a mobile phone, a tablet, or a vehicle-mounted terminal.
According to the voice control system provided by the embodiment of the invention, the voice recognition accuracy can be improved through the voice control device, and the intelligent terminal is subjected to voice control such as voice awakening.
The invention also provides a voice control method of the voice control device.
Fig. 7 is a flowchart of a voice control method of a voice control apparatus according to an embodiment of the present invention. As shown in fig. 7, the voice control method of the voice control apparatus includes the steps of:
s1: the voice signal is received, and voice features are generated according to the voice signal.
S2: and acquiring the current working mode of the voice control device, and judging the voice characteristics according to the current working mode.
S3: and generating a voice command when the voice characteristics are judged to be matched with the voice template corresponding to the current working mode, and generating a control instruction according to the voice command.
S4: and sending the control instruction to an intelligent terminal which is communicated with the voice control device so that the intelligent terminal works according to the control instruction.
According to one embodiment of the invention, the operation modes of the voice control device comprise a voiceprint mode, a voice mode and a compound mode, wherein the compound mode is composed of the voiceprint mode and the voice mode.
Further, according to an embodiment of the present invention, when the current working mode is the voiceprint mode, the voice characteristics are determined according to a voiceprint recognition algorithm corresponding to the voiceprint mode and a personal voiceprint template established by the voiceprint information of the user; when the current working mode is a voice mode, judging voice characteristics according to a standard voice recognition algorithm corresponding to the voice mode and a pre-stored standard voice template; when the current working mode is a compound mode, judging the voice characteristics according to a voiceprint recognition algorithm corresponding to the voiceprint mode and a personal voiceprint template established by user voiceprint information, and judging the voice characteristics according to a standard voice recognition algorithm corresponding to the voice mode and a pre-stored standard voice template when the voice characteristics are not matched with the personal voiceprint template established by the user voiceprint information.
Specifically, as shown in fig. 8, the voice control method of the voice control apparatus according to the embodiment of the present invention specifically includes the following steps:
s101: and the Bluetooth pairing with the intelligent terminal is successful.
S102: and the working mode of the voice control device is connected with the intelligent terminal and detected.
S103: and judging the value of the mode flag bit ID.
When the ID is 1, step S104 is performed; when the ID is 2, step S105 is performed; when the ID is 3, step S106 is performed.
S104: operating in voiceprint mode, step S107 is performed.
S105: operating in the voice mode, step S107 is performed.
S106: working in a voiceprint plus speech compound mode.
S107: it is determined whether a voice signal is received. If yes, go to step S108; if not, execution continues with step S107.
S108: and judging whether the voice characteristics of the voice signal are matched with the voice template. If yes, go to step S109; if not, return to step S107.
S109: and acquiring a control instruction corresponding to the voice signal, and sending the control instruction to the intelligent terminal.
According to an embodiment of the present invention, the voice control method of the voice control apparatus further includes: generating voiceprint information according to the personal voice sample sent by the intelligent terminal, and establishing a personal voiceprint template according to the voiceprint information.
Specifically, as shown in fig. 9, the voice recording process of the intelligent terminal includes the following steps:
s201: and the Bluetooth pairing with the voice control device is successful.
S202: information of the voice control apparatus is acquired and time, place, and the like are set in synchronization.
S203: and detecting and judging whether the personal voiceprint information needs to be recorded or not.
If yes, executing step S204; if not, step S206 is performed.
S204: and recording the personal voice sample, and judging whether the recording is successful.
If yes, go to step S205; if not, the process continues to step S204.
S205: the personal voice sample is sent to the voice control device.
S206: and entering a human-computer interaction interface.
In addition, according to an embodiment of the present invention, the voice control method of the voice control apparatus further includes:
extracting byte voice features from the voice features, and judging the extracted byte voice features according to the current working mode;
and controlling a signal processing unit in the voice control device to work when judging that the byte voice characteristics are matched with the keyword information corresponding to the current working mode.
Therefore, by controlling the signal processing unit to be started when the keyword is detected, the power consumption of the signal processing unit used for long time calculation can be greatly saved, and the power consumption can be saved by 85%.
In summary, according to the voice control method of the voice control apparatus provided in the embodiment of the present invention, the voice characteristic can be determined according to the current working mode of the voice control apparatus, and when it is determined that the voice characteristic matches the voice template corresponding to the current working mode, a voice command is generated, and then a control instruction is generated according to the voice command and sent to the intelligent terminal, so that the intelligent terminal can work according to the control instruction. Therefore, the method can work in a working mode meeting the voice condition of the user according to the selection of the user, improves the voice recognition accuracy, and can also meet different requirements of different users on voice control. Moreover, the method can also carry out voice control on the intelligent terminal, such as voice awakening.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (8)
1. A voice control apparatus, comprising:
the voice acquisition module is used for receiving a voice signal;
the voice recognition module is used for generating voice characteristics according to the voice signals, judging the voice characteristics according to the current working mode of the voice control device and generating a voice command when judging that the voice characteristics are matched with a voice template corresponding to the current working mode; when the current working mode is the voiceprint mode, the voice recognition module judges the voice characteristics according to a voiceprint recognition algorithm corresponding to the voiceprint mode and a personal voiceprint template established by user voiceprint information;
when the current working mode is the voice mode, the voice recognition module judges the voice characteristics according to a standard voice recognition algorithm corresponding to the voice mode and a pre-stored standard voice template;
when the current working mode is the compound mode, the voice recognition module judges the voice characteristics according to a voiceprint recognition algorithm corresponding to the voiceprint mode and a personal voiceprint template established by user voiceprint information, and judges the voice characteristics according to a standard voice recognition algorithm corresponding to the voice mode and a pre-stored standard voice template when the voice characteristics are not matched with the personal voiceprint template established by the user voiceprint information;
the first communication module is used for carrying out wireless communication with the intelligent terminal;
and the control module is used for generating a control instruction according to the voice command and sending the control instruction to the intelligent terminal through the first communication module so that the intelligent terminal works according to the control instruction.
2. The voice control device according to claim 1, wherein the voice recognition module is further configured to generate voiceprint information according to a personal voice sample sent by the intelligent terminal, and establish the personal voiceprint template according to the voiceprint information.
3. The voice-controlled apparatus according to claim 1, wherein the control module is turned off when the voice-controlled apparatus is in a standby state and turned on when the voice command is received.
4. The voice control apparatus according to claim 1, wherein the voice recognition module comprises:
a feature generation unit configured to generate the speech feature from the speech signal;
the signal processing unit is used for judging the voice characteristics according to the current working mode and generating a voice command when judging that the voice characteristics are matched with a voice template corresponding to the current working mode;
the feature generation unit is further configured to extract byte voice features from the voice features, determine the extracted byte voice features according to the current working mode, and output a wake-up signal to the signal processing unit to control the signal processing unit to operate when it is determined that the byte voice features are matched with keyword information corresponding to the current working mode.
5. A voice control system, comprising:
the voice control device according to any one of claims 1-4;
and the intelligent terminal is communicated with the voice control device.
6. The voice control system according to claim 5, wherein the voice control device is a smart headset or a smart watch, and the smart terminal is a mobile phone, a tablet or a vehicle-mounted terminal.
7. A voice control method of a voice control device is characterized by comprising the following steps:
receiving a voice signal and generating a voice characteristic according to the voice signal;
acquiring a current working mode of a voice control device, and judging the voice characteristics according to the current working mode; when the current working mode is the voiceprint mode, judging the voice characteristics according to a voiceprint recognition algorithm corresponding to the voiceprint mode and a personal voiceprint template established by user voiceprint information;
when the current working mode is the voice mode, judging the voice characteristics according to a standard voice recognition algorithm corresponding to the voice mode and a pre-stored standard voice template;
when the current working mode is the compound mode, judging the voice characteristics according to a voiceprint recognition algorithm corresponding to the voiceprint mode and a personal voiceprint template established by user voiceprint information, and when the voice characteristics are not matched with the personal voiceprint template established by the user voiceprint information, judging the voice characteristics according to a standard voice recognition algorithm corresponding to the voice mode and a pre-stored standard voice template;
generating a voice command when the voice characteristics are judged to be matched with the voice template corresponding to the current working mode, and generating a control instruction according to the voice command;
and sending the control instruction to an intelligent terminal which is communicated with the voice control device so that the intelligent terminal works according to the control instruction.
8. The voice control method of the voice control apparatus according to claim 7, characterized by further comprising:
generating voiceprint information according to the personal voice sample sent by the intelligent terminal, and establishing the personal voiceprint template according to the voiceprint information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510989140.0A CN106920548B (en) | 2015-12-25 | 2015-12-25 | Voice control device, voice control system, and voice control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510989140.0A CN106920548B (en) | 2015-12-25 | 2015-12-25 | Voice control device, voice control system, and voice control method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106920548A CN106920548A (en) | 2017-07-04 |
CN106920548B true CN106920548B (en) | 2020-06-19 |
Family
ID=59456686
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510989140.0A Active CN106920548B (en) | 2015-12-25 | 2015-12-25 | Voice control device, voice control system, and voice control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106920548B (en) |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108200492A (en) * | 2017-07-12 | 2018-06-22 | 北京金锐德路科技有限公司 | Voice control optimization method, device and the earphone and wearable device that integrate In-Ear microphone |
CN107393531A (en) * | 2017-07-20 | 2017-11-24 | Tcl医疗核磁技术(无锡)有限公司 | The phonetic controller and method of a kind of medical detection system |
CN107444318B (en) * | 2017-07-26 | 2020-07-03 | 奇瑞汽车股份有限公司 | Automobile rear tail door control method and system |
CN107426069B (en) * | 2017-08-23 | 2020-08-28 | 南京中感微电子有限公司 | Bluetooth-based intelligent household system and control method thereof |
CN107591152B (en) * | 2017-08-30 | 2021-06-08 | 百度在线网络技术(北京)有限公司 | Voice control method, device and equipment based on earphone |
CN107863098A (en) * | 2017-12-07 | 2018-03-30 | 广州市艾涛普电子有限公司 | A kind of voice identification control method and device |
CN108062950A (en) * | 2017-12-20 | 2018-05-22 | 歌尔科技有限公司 | The Dongle equipment and voice awakening method that a kind of voice wakes up |
CN108182941A (en) * | 2017-12-28 | 2018-06-19 | 重庆柚瓣家科技有限公司 | For the human-computer interaction module under noisy environment |
CN110400568B (en) * | 2018-04-20 | 2022-12-09 | 比亚迪股份有限公司 | Awakening method of intelligent voice system, intelligent voice system and vehicle |
CN109151637A (en) * | 2018-08-21 | 2019-01-04 | 歌尔科技有限公司 | Wireless headset, intelligent sound control system and method for wireless headset |
CN111199725A (en) * | 2018-10-31 | 2020-05-26 | 南京智能仿真技术研究院有限公司 | Multi-voice control system of electronic equipment based on artificial intelligence |
CN109725523A (en) * | 2018-12-25 | 2019-05-07 | 广东乐芯智能科技有限公司 | A kind of method and wrist-watch of smartwatch speech recognition controlled |
CN109545231A (en) * | 2019-01-08 | 2019-03-29 | 深圳市高觉科技有限公司 | A kind of method of portable control smart machine |
CN109461439A (en) * | 2019-01-08 | 2019-03-12 | 深圳市高觉科技有限公司 | A kind of acquisition method of voice messaging instruction |
CN111105796A (en) * | 2019-12-18 | 2020-05-05 | 杭州智芯科微电子科技有限公司 | Wireless earphone control device and control method, and voice control setting method and system |
CN111508490A (en) * | 2020-04-16 | 2020-08-07 | 程霖锋 | Tower crane intelligence voice control system |
CN111816183B (en) * | 2020-07-15 | 2024-05-07 | 前海人寿保险股份有限公司 | Voice recognition method, device, equipment and storage medium based on audio and video recording |
CN112190240A (en) * | 2020-09-21 | 2021-01-08 | 四川大学华西医院 | Old people health monitoring and alarming device and method based on Internet of things |
CN115223552A (en) * | 2021-04-21 | 2022-10-21 | 博泰车联网科技(上海)股份有限公司 | Voice control method, terminal and computer storage medium |
CN113467342A (en) * | 2021-08-09 | 2021-10-01 | 重庆宗灿科技发展有限公司 | Wisdom endowment system and intelligent watch based on internet of things |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103841248A (en) * | 2012-11-20 | 2014-06-04 | 联想(北京)有限公司 | Method and electronic equipment for information processing |
CN103051781A (en) * | 2012-12-07 | 2013-04-17 | 百度在线网络技术(北京)有限公司 | Method for controlling backstage through voice and mobile terminal |
CN104110779A (en) * | 2013-10-22 | 2014-10-22 | 广东美的制冷设备有限公司 | Voice air conditioner, control method thereof and air conditioner control system |
CN103594089A (en) * | 2013-11-18 | 2014-02-19 | 联想(北京)有限公司 | Voice recognition method and electronic device |
CN104978958A (en) * | 2014-04-14 | 2015-10-14 | 美的集团股份有限公司 | Voice control method and system |
CN104978957B (en) * | 2014-04-14 | 2019-06-04 | 美的集团股份有限公司 | Sound control method and system based on Application on Voiceprint Recognition |
CN105138882B (en) * | 2015-07-30 | 2019-04-09 | Oppo广东移动通信有限公司 | A kind of terminal unlock method and device |
CN105141768A (en) * | 2015-08-31 | 2015-12-09 | 努比亚技术有限公司 | Method and device for multi-user identification and mobile terminal |
-
2015
- 2015-12-25 CN CN201510989140.0A patent/CN106920548B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN106920548A (en) | 2017-07-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106920548B (en) | Voice control device, voice control system, and voice control method | |
CN106981290B (en) | Voice control device and voice control method | |
US8521525B2 (en) | Communication control apparatus, communication control method, and non-transitory computer-readable medium storing a communication control program for converting sound data into text data | |
CN108766441A (en) | A kind of sound control method and device based on offline Application on Voiceprint Recognition and speech recognition | |
CN104168353A (en) | Bluetooth earphone and voice interaction control method thereof | |
CN104795068A (en) | Robot awakening control method and robot awakening control system | |
CN108810280B (en) | Voice acquisition frequency processing method and device, storage medium and electronic equipment | |
CN111105796A (en) | Wireless earphone control device and control method, and voice control setting method and system | |
CN109272991B (en) | Voice interaction method, device, equipment and computer-readable storage medium | |
CN106155621B (en) | Keyword voice awakening system and method capable of identifying sound source position and mobile terminal | |
CN103886236A (en) | Acoustic control screen unlocking method and mobile terminal | |
CN109308900B (en) | Earphone device, voice processing system and voice processing method | |
CN105049802B (en) | A kind of speech recognition law-enforcing recorder and its recognition methods | |
CN109151637A (en) | Wireless headset, intelligent sound control system and method for wireless headset | |
US11315572B2 (en) | Speech recognition device, speech recognition method, and recording medium | |
TW201519172A (en) | Electronic device having function of lost reminding and using method of same | |
CN107371144B (en) | Method and device for intelligently sending information | |
CN103903615B (en) | A kind of information processing method and electronic equipment | |
KR20140067687A (en) | Car system for interactive voice recognition | |
CN104427125A (en) | Method and mobile terminal for answering call | |
CN108093350A (en) | Microphone control method and microphone | |
CN109922397B (en) | Intelligent audio processing method, storage medium, intelligent terminal and intelligent Bluetooth headset | |
CN110400568B (en) | Awakening method of intelligent voice system, intelligent voice system and vehicle | |
CN113259793A (en) | Intelligent microphone and signal processing method thereof | |
CN107231584A (en) | A kind of microphone apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |