CN108877805A - Speech processes mould group and terminal with phonetic function - Google Patents
Speech processes mould group and terminal with phonetic function Download PDFInfo
- Publication number
- CN108877805A CN108877805A CN201810693654.5A CN201810693654A CN108877805A CN 108877805 A CN108877805 A CN 108877805A CN 201810693654 A CN201810693654 A CN 201810693654A CN 108877805 A CN108877805 A CN 108877805A
- Authority
- CN
- China
- Prior art keywords
- voice
- processing module
- main processor
- terminal
- collector
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title abstract description 8
- 230000008569 process Effects 0.000 title abstract description 8
- 238000012545 processing Methods 0.000 claims description 97
- 238000004891 communication Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 230000006870 function Effects 0.000 description 15
- 239000013598 vector Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
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
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/3293—Power saving characterised by the action undertaken by switching to a less power-consuming processor, e.g. sub-CPU
-
- 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
- G10L15/22—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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Telephone Function (AREA)
Abstract
The present embodiments relate to field of terminal, disclose a kind of speech processes mould group and the terminal with phonetic function.In the present invention, speech processes mould group, including：Receiving unit wakes up word recognition unit and wakeup unit；Receiving unit, for receiving voice signal；Word recognition unit is waken up, whether includes for identification scheduled wake-up word in received voice signal；Wakeup unit, for wake-up signal being sent to the primary processor independently of speech processes mould group, so that terminal is when using voice service when wake-up word recognition unit identifies scheduled wake-up word from voice signal, the higher primary processor of power consumption is in suspend mode, reduces the overall power of terminal.
Description
Technical Field
The embodiment of the invention relates to the field of terminals, in particular to a voice processing module and a terminal with a voice function.
Background
The voice is an important man-machine interaction mode, a user can obtain a feedback result from the terminal only by speaking, when the voice application is used for awakening the terminal, the user can awaken the terminal by sending specific voice information, and the user can use the terminal conveniently to a certain extent.
However, the inventors found that at least the following problems exist in the prior art: in the prior art, when a voice wake-up mode is adopted for a terminal, a main processor in the terminal needs to be always on to start a voice service, and the main processor monitors received voice wake-up information in real time and is further awakened when specific voice information is identified. Although the terminal is awakened, the main processor needs to start the voice service all the time and monitor the external voice information in real time, so that the power consumption of the main processor is increased, the power consumption of the terminal is large, and the user experience is poor.
Disclosure of Invention
The embodiment of the invention aims to provide a voice processing module and a terminal with a voice function, so that a main processor with higher power consumption is in a dormant state when the terminal adopts voice service, and the overall power consumption of the terminal is reduced.
To solve the above technical problem, an embodiment of the present invention provides a voice processing module, including: the device comprises a receiving unit, a wake-up word recognition unit and a wake-up unit; a receiving unit for receiving a voice signal; a wakeup word recognition unit for recognizing whether the received voice signal includes a predetermined wakeup word; and the awakening unit is used for sending an awakening signal to the main processor independent of the voice processing module when the awakening word recognition unit recognizes the preset awakening word from the voice signal.
An embodiment of the present invention further provides a terminal having a voice function, including: the voice processing module, the main processor and the voice collector; the voice processing module is respectively connected with the main processor and the voice collector; the voice signal received by the receiving unit in the voice processing module comes from the voice collector; and when the main processor receives the wake-up signal in the sleep state, the main processor exits the sleep state.
Compared with the prior art, the voice processing module comprises a receiving unit, a wake-up word recognition unit and a wake-up unit, the voice processing module is independent of the main controller, and the receiving unit in the voice processing module receives voice signals, so that the main processor does not need to be in an on state all the time. The main processor can increase the whole power consumption of the terminal after being started, so that the voice processing module monitors the received voice signals, and the main processor is usually in a dormant state, so that the whole power consumption of the terminal is greatly reduced. The awakening word recognition unit recognizes whether the received voice signal comprises the preset awakening word or not, and avoids the problem that in the prior art, the processing load of the main controller is increased due to the fact that the main controller recognizes the voice signal. When the awakening word recognition unit recognizes the preset awakening words from the voice signals, the awakening unit sends the awakening signals to the main processor independent of the voice processing module, so that effectiveness and timeliness of sending the awakening signals are guaranteed, the main processor in a dormant state can be awakened after receiving the awakening signals, normal work of the main processor is not influenced while power consumption is reduced, and use experience of a user is improved.
In addition, the voice processing module further comprises: the storage unit is used for prestoring standard characteristic parameters of a preset awakening word; and the awakening word recognition unit is specifically used for analyzing the received voice signal, extracting the first characteristic parameters in the voice signal and recognizing whether the extracted first characteristic parameters include standard characteristic parameters. By comparing the characteristic parameters of the voice signals, whether the received voice signals comprise the preset awakening words or not can be accurately identified.
In addition, the preset awakening words are input by the user, so that the personalized requirements of the user can be met, and convenience is provided for the user to use.
In addition, the preset awakening words are selected from the specific word bank by the user to be input, and the specific word bank defines the range for the awakening words input by the user, so that when the awakening word recognition unit recognizes whether the received voice signals include the preset awakening words, the complexity of an algorithm in the recognition process is reduced, the recognition time is reduced, the power consumption of the voice processing module is further reduced, and the overall power consumption of the terminal is greatly reduced.
In addition, the voice collector is an analog voice collector, and a receiving unit in the voice processing module is an analog-to-digital conversion ADC (analog-to-digital converter) sampler; or, the voice collector is a digital voice collector, and the receiving unit in the voice processing module is a serial audio communication I2S interface. The voice collector can be an analog voice collector or a digital voice collector, so that the realization of the voice collector is more diversified.
In addition, the terminal also comprises a change-over switch, one end of the change-over switch is connected with the voice collector, and the other end of the change-over switch can be switched and connected between the voice processing module and the main processor; the change-over switch determines to conduct the voice collector and the main processor or conduct the voice collector and the voice processing module according to the control signal of the main processor or the voice processing module. The change-over switch makes the connection mode of the voice collector change over more conveniently, quickly and accurately.
In addition, the voice collector is multiple, the voice processing module is provided with a plurality of receiving units, and the receiving units correspond to the voice collectors one by one; the voice processing module is also connected to the main processor through an I2S interface and used for transmitting the voice signals received from the plurality of voice collectors to the main processor, so that the main processor can obtain the voice signals received from the plurality of voice collectors.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
FIG. 1 is a schematic diagram of a voice processing module according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a voice processing module according to a second embodiment of the present invention;
fig. 3 is a schematic configuration diagram of a terminal having a voice function according to a third embodiment of the present invention;
fig. 4 is a diagram illustrating that a main processor in a voice-enabled terminal according to a third embodiment of the present invention exits a sleep state;
fig. 5 is a schematic configuration diagram of a terminal having a voice function according to a fourth embodiment of the present invention;
fig. 6 is a schematic configuration diagram of a terminal having a voice function according to a fifth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to a voice processing module. The core of this embodiment is a voice processing module, as shown in fig. 1, including: a receiving unit 101, a wake-up word recognition unit 102 and a wake-up unit 103; the following describes implementation details of the voice processing module according to the present embodiment in detail, and the following is only provided for easy understanding and is not necessary to implement the present embodiment.
The voice processing module in this embodiment specifically includes: a receiving unit 101 is used for receiving a voice signal. The receiving unit 101 receives a voice signal sent by the voice collector, if the voice collector is an analog voice collector, that is, the collected voice signal is directly an analog signal, the receiving unit 101 may be an analog-to-digital conversion ADC sampler, the analog voice collector sends the analog signal to the analog-to-digital conversion ADC sampler, and the analog-to-digital conversion ADC sampler converts the analog signal into a digital signal. If the voice collector is a digital voice collector, that is, the collected voice signal is directly a digital signal, the receiving unit 101 may be a serial audio communication I2S interface, and directly receive the digital signal sent by the digital voice collector. The voice signal can be a voice signal from one voice collector, and can also be a voice signal sent by a plurality of voice collectors. In practical applications, the voice collector may be a microphone, and the microphone may include a receiving analog microphone and a receiving digital microphone.
A wake word recognition unit 102, configured to recognize whether a predetermined wake word is included in the received voice signal. The predetermined wake-up word may be input by a user, and the predetermined wake-up word may be one or multiple, for example, the predetermined wake-up word may be a simple word group, a number, a letter, or any combination thereof, and the user may set the predetermined wake-up word according to the actual needs or personal preferences of the user, for example, the predetermined wake-up word may be words such as "make a call", "turn on a light", and "turn off a light", which is not specifically limited in this embodiment.
The wakeup unit 103 sends a wakeup signal to the main processor independent of the voice processing module when the wakeup word recognition unit 102 recognizes a predetermined wakeup word from the voice signal. The wake-up unit 103 may be a general purpose input/output GPIO interface, and the voice processing module may send a wake-up signal to the main processor through the GPIO interface, where the wake-up signal may be an interrupt signal, an electrical signal of the GPIO interface, a square wave signal, or the like. That is, the main processor is generally in a sleep state, and after receiving the wake-up signal sent by the wake-up unit 103, the main processor exits the sleep state, executes a corresponding program, and starts normal operation.
For example, when a user drives a vehicle, the vehicle-mounted terminal may be in a screen-off state or a screen-locking state, and when the user wants to wake up the vehicle-mounted terminal for navigation, a voice instruction may be sent out, that is, a predetermined wake-up word is spoken out, after the voice processing module in the vehicle-mounted terminal recognizes the predetermined wake-up word, a wake-up signal is sent to a main processor in the vehicle-mounted terminal, the main processor is woken up to start to work, and then navigation can be started according to the voice instruction of the user, the main processor in the vehicle-mounted terminal does not need to be in a working state all the time, power consumption of the vehicle-mounted terminal is reduced, and the main processor in a dormant. If the preset awakening word is 'on light', and the terminal is a Bluetooth sound box, the Bluetooth sound box can be awakened to send an on light instruction to the corresponding lamp after recognizing the awakening word 'on light'.
Compared with the prior art, the voice processing module in the embodiment of the invention is independent of the main controller, and the main processor does not need to be in an open state all the time by receiving the voice signal through the receiving unit in the voice processing module. The main processor is started to increase the overall power consumption of the terminal, so that the receiving unit in the voice processing module receives the voice signal, and the main processor is usually in a dormant state, so that the overall power consumption of the terminal is greatly reduced. The awakening word recognition unit recognizes whether the received voice signal comprises the preset awakening word or not, and avoids the problem that the processing burden of the main controller is increased due to the fact that the main controller recognizes the voice signal in the prior art. When the awakening word recognition unit recognizes the preset awakening words from the voice signals, the awakening unit sends the awakening signals to the main processor independent of the voice processing module, so that effectiveness and timeliness of sending the awakening signals are guaranteed, the main processor in a dormant state can be awakened after receiving the awakening signals, normal work of the main processor is not influenced while power consumption is reduced, and use experience of a user is improved. Meanwhile, the GPIO interface in this embodiment has lower power consumption (about 1 μ a, the operating current of μ C is 100 μ a), and can predetermine the response time, shorten or determine the response time between the external event and the interrupt, and at the same time, only 2 pieces of GPIO interface are needed to form the IIC bus or 3 pieces of GPIO interface to form the SPI bus, which makes the wiring simpler. Therefore, the awakening unit is a general purpose input/output GPIO interface, so that the voice processing module not only reduces power consumption, but also further improves performance.
A second embodiment of the invention relates to a voice processing module. The second embodiment is a further improvement of the first embodiment, and the main improvements are as follows: in a second embodiment of the present invention, the voice processing module further includes: and the storage unit is used for pre-storing the standard characteristic parameters of the preset awakening words, so that the awakening word recognition unit can compare the characteristic parameters of the voice signals, and whether the preset awakening words are included in the received voice signals or not can be recognized accurately.
As shown in fig. 2, the voice processing module of this embodiment specifically includes: a receiving unit 101, a wakeup word recognition unit 102, a wakeup unit 103, and a storage unit 204. The storage unit 204 prestores standard characteristic parameters of predetermined awakening words; the wakeup word recognition unit 102 analyzes the received voice signal, extracts a first feature parameter from the voice signal, and recognizes whether the extracted first feature parameter includes a standard feature parameter.
Specifically, the predetermined wake-up word may correspond to the standard feature parameter, and the voice processing module may further include a storage unit 204 configured to pre-store the standard feature parameter of the predetermined wake-up word, where the standard feature parameter may be a standard feature vector. Since the received voice signal usually contains components that are not recognizable, such as background noise, human emotion, etc., the wakeup word recognition unit 102 may analyze the received voice signal and extract the components that are recognizable in the voice signal. For the received voice signal, in the extraction of the feature parameters of the voice signal, the Mel Frequency Cepstrum Coefficient (MFCC) takes the auditory features of human into account, if the processing characteristics of human auditory perception can be simulated when the keywords in the voice signal are recognized, the recognition rate of the voice can be improved, and therefore, the feature parameters extracted from the voice signal can be feature vectors related to the Mel frequency cepstrum Coefficient. The process of extracting the characteristic parameters may be: pre-emphasis, framing and windowing are performed on a voice signal; each short time analysis window obtains a corresponding frequency spectrum through fast Fourier transform; the obtained frequency spectrum is processed by a Mel filter bank to obtain a Mel frequency spectrum; performing cepstral analysis on the Mel spectrum to obtain a series of cepstral vectors, each vector being the MFCC feature vector of each frame. The feature parameters extracted by the wakeup word recognition unit 102 may not only include feature vectors, but also may include parameters such as frequency and amplitude of the voice signal, and the wakeup word recognition unit 102 may determine whether the feature parameters include standard feature vectors corresponding to the prestored wakeup words according to the extracted feature parameters.
It should be noted that, in the present embodiment, the predetermined wake-up word may be selected by the user from a specific word bank. For example, the range of the specific thesaurus may be numbers 0 to 9 or letters a to Z, or a combination of numbers and letters, the wake-up word predetermined by the user needs to be selected from the specific thesaurus, that is, the embodiment defines a specific range for the wake-up word selected by the user, in practical applications, the specific thesaurus is not limited to numbers and letters, and any specific thesaurus is within the protection scope of the embodiment.
Compared with the prior art, the storage unit in the embodiment prestores the standard characteristic parameters of the preset awakening words; the awakening word recognition unit compares the characteristic parameters of the voice signals, so that whether the received voice signals contain the preset awakening words or not can be recognized accurately. Meanwhile, the embodiment defines a specific range for the user to select the awakening words, so that the awakening word recognition unit only recognizes a specific word bank in the recognition process, the complexity of an algorithm used in the recognition process is reduced, and the recognition speed is accelerated.
A third embodiment of the present invention relates to a terminal having a voice function, as shown in fig. 3, including: the terminal of the voice collector 301, the voice processing module 302 and the main processor 303 in the above embodiments may be an intelligent device with a voice function, such as a mobile phone, a tablet computer, a bluetooth speaker, etc., which is not limited in this embodiment.
Specifically, the voice signal received by the receiving unit 101 in the voice processing module 302 is from the voice collector 301, the voice collector 301 may be an analog voice collector, and when the voice collector 301 is an analog voice collector, the receiving unit 101 in the voice processing module 302 is an analog-to-digital converter ADC sampler. The voice capturing module 301 can also be a digital voice capturing module, and when the voice capturing module 301 is a digital voice capturing module, the receiving unit in the voice processing module 302 is a serial audio communication I2S interface. I2S (Inter-IC Sound) is a bus standard established for audio data transmission between digital audio devices, and adopts a design of independent wires to transmit clock and data signals, and by separating data and clock signals, distortion caused by time difference is avoided, and the cost for purchasing professional equipment for resisting audio jitter is saved for users.
The main processor 303 exits the sleep state when it receives the wake-up signal in the sleep state. Exiting the sleep state may be understood as the terminal exiting from the screen-off state to the screen-on state, or exiting from the screen-locking state to the unlocked state, and the control signal is transmitted between the main processor 303 and the voice processing module 302 through the I2C. In practical applications, if the main processor 303 is woken up, the main processor 303 may be directly connected to the voice collector 301 to directly receive the voice signal sent by the voice collector 301, or the voice processing module 302 may send the voice signal to the main processor 303 through an I2S interface.
The main processor 303 exiting from the sleep state can be realized according to fig. 4, when the EN enable terminal of the voice processing module 302 is pulled high, the voice processing module 302 chip works, that is, the voice processing module 302 is conducted with the voice collector 301 at this time. After the voice processing module 302 sends the wake-up signal to the main processor 303, the EN enable port of the voice processing module 302 can be pulled down, and at this time, the voice processing module 302 does not operate, that is, the voice processing module 302 is not conducted with the voice collector 301, but the voice collector 301 is conducted with the main processor 303, so that the main processor 303 exits from the sleep state. It should be noted that, in practical applications, the voice processing module 302 further has an interface with other functions, and since the EN enabling end of the voice processing module 302 is mainly used to implement the exit from the sleep state in this embodiment, other ports of the voice processing module 302 are not specifically limited.
Compared with the prior art, the terminal with the voice function in the embodiment comprises: the voice processing module, the main processor and the voice collector; the main processor with higher power consumption in the terminal is usually in a dormant state, the voice processing module with lower power consumption receives the voice signal and sends a wake-up signal to the main processor when recognizing that the voice signal comprises a preset wake-up word, so that the main processor exits the dormant state to start working, and the normal working of the terminal is not influenced while the whole power consumption of the terminal is reduced.
A fourth embodiment of the present invention relates to a terminal having a voice function, and is substantially the same as the third embodiment except that: the switching manner is different, and in the third embodiment, the switching is realized by an EN enable terminal of the voice processing module. In the embodiment, the switching is realized through the selector switch, and the connection mode switching of the voice collector is more convenient, quicker and more accurate through the selector switch.
As shown in fig. 5, the terminal having a voice function according to the present embodiment includes: a voice collector 301, a voice processing module 302 in the above embodiment, a main processor 303, and a switch 404. One end of the switch 404 is connected to the voice collector 301, and the other end can be switched between the voice processing module 302 and the main processor 303; the switch 404 determines to connect the voice collector 301 and the main processor 303 or to connect the voice collector 301 and the voice processing module 302 according to the control signal of the main processor 303 or the voice processing module 302.
Specifically, the switch 404 may be an electronic device such as a triode, a single-pole double-throw switch, or the like. The control signal may be a control signal for controlling the conduction of the voice processing module 302 and the main processor 303, and the control signal may be a control signal sent to the switch 404 by the main processor 303 after receiving the wake-up signal sent by the voice processing module 302, or a control signal sent to the switch 404 by the voice processing module 302 while sending the wake-up signal, so that the main processor 303 exits the sleep state. In practical applications, the control signal may also be a control signal for controlling the voice processing module 302 and the main processor 303 to be disconnected, so that the main processor 303 enters a sleep state.
Compared with the prior art, the embodiment of the invention enables the voice collector to be switched more accurately and rapidly under different conditions through the selector switch, so that the main controller can rapidly exit or enter the dormant state, and the normal work of the terminal is not influenced while the overall power consumption of the terminal is reduced.
A fifth embodiment of the present invention relates to a terminal having a voice function, and is a further improvement of the third embodiment, and is mainly characterized in that: in the fifth embodiment of the present invention, there are a plurality of voice collectors, so that the main processor can obtain voice signals received from a plurality of voice collectors.
Fig. 6 shows a terminal having a voice function according to the present embodiment. The voice processing module has a plurality of receiving units, which correspond to the voice collectors one by one, for example, the voice collector 3011 in fig. 6 corresponds to the receiving unit 1011, the voice collector 3012 corresponds to the receiving unit 1012, only 2 voice collectors and corresponding receiving units are shown in fig. 6, and the number of the voice collectors and corresponding receiving units in practical application is not limited to this.
Specifically, the receiving unit 1011 and the receiving unit 1012 respectively receive the voice signals sent by the voice collector 3011 and the voice collector 3012 at the same time, and the awakening word recognition unit 102 in the voice processing module 302 can select one of the voice signals sent by the voice collectors for recognition. After the recognition by the wakeup word recognition unit 102, if the main processor 303 is woken up, the voice processing module 302 may be connected to the main processor 303 through an I2S interface, and transmit the voice signals received from the voice picker 3011 and the voice picker 3012 to the main processor 303. The storage unit 204 in the voice processing module 302 can also store the voice signals received by the receiving unit 1011 and the receiving unit 1012. The main processor 303 and the voice processing module 302 transmit a control signal through I2C and transmit a voice signal through I2S, and the main processor 303 exits from the sleep state and starts to operate after receiving a wake-up signal sent by the voice processing module 302.
Compared with the prior art, the embodiment of the invention has the advantages that the number of the voice collectors is multiple, the voice processing module is provided with a plurality of receiving units, and the receiving units correspond to the voice collectors one by one; the voice processing module is also connected to the main processor through an I2S interface and used for transmitting voice signals received from a plurality of voice collectors to the main processor, so that the main processor can obtain the voice signals received from the plurality of voice collectors, and the technical problem that the main processor can only obtain the voice signals received by one voice collector in the prior art can be effectively solved.
In order to highlight the innovative part of the present invention, elements that are not so closely related to solving the technical problems proposed by the present invention are not introduced in the present embodiment, but this does not indicate that no other elements exist in the present embodiment.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (10)
1. A speech processing module, comprising: the device comprises a receiving unit, a wake-up word recognition unit and a wake-up unit;
the receiving unit is used for receiving a voice signal;
the awakening word recognition unit is used for recognizing whether the received voice signal comprises a preset awakening word;
and the awakening unit is used for sending an awakening signal to a main processor independent of the voice processing module when the awakening word recognition unit recognizes the preset awakening word from the voice signal.
2. The speech processing module of claim 1, further comprising: the storage unit is used for prestoring the standard characteristic parameters of the preset awakening words;
the awakening word recognition unit is specifically configured to analyze the received voice signal, extract a first feature parameter in the voice signal, and recognize whether the extracted first feature parameter includes the standard feature parameter.
3. The speech processing module of claim 1, wherein the predetermined wake-up word is input by a user.
4. The speech processing module of claim 3 wherein the predetermined wake-up word is selected by a user as input from a particular lexicon.
5. The speech processing module of claim 1, wherein the wake-up unit is: and a general purpose input/output GPIO interface.
6. A terminal having a voice function, comprising: the voice processing module, the main processor and the voice collector;
the voice processing module is as claimed in any one of claims 1 to 5, and is respectively connected with the main processor and the voice collector;
the voice signal received by the receiving unit in the voice processing module comes from the voice collector;
and when the main processor receives the wake-up signal in the sleep state, the main processor exits the sleep state.
7. The terminal with voice function according to claim 6, wherein the voice collector is an analog voice collector, and the receiving unit in the voice processing module is an analog-to-digital converter (ADC) sampler; or,
the voice collector is a digital voice collector, and the receiving unit in the voice processing module is a serial audio communication I2S interface.
8. The terminal with the voice function according to claim 6, further comprising a switch, wherein one end of the switch is connected to the voice collector, and the other end of the switch can be switched between the voice processing module and the main processor;
the change-over switch determines to conduct the voice collector and the main processor or conduct the voice collector and the voice processing module according to the control signal of the main processor or the voice processing module.
9. The terminal with voice function according to claim 6, wherein there are a plurality of voice collectors, the voice processing module has a plurality of receiving units, and the receiving units are in one-to-one correspondence with the voice collectors;
the voice processing module is also connected to the main processor through an I2S interface and used for transmitting voice signals received from the plurality of voice collectors to the main processor.
10. The voice-enabled terminal according to claim 9, wherein the voice processing module is the voice processing module according to claim 2, and the storage unit of the voice processing module is further configured to store voice signals received from the plurality of voice collectors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810693654.5A CN108877805A (en) | 2018-06-29 | 2018-06-29 | Speech processes mould group and terminal with phonetic function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810693654.5A CN108877805A (en) | 2018-06-29 | 2018-06-29 | Speech processes mould group and terminal with phonetic function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108877805A true CN108877805A (en) | 2018-11-23 |
Family
ID=64296956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810693654.5A Pending CN108877805A (en) | 2018-06-29 | 2018-06-29 | Speech processes mould group and terminal with phonetic function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108877805A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448720A (en) * | 2018-12-18 | 2019-03-08 | 维拓智能科技（深圳）有限公司 | Convenience service self-aided terminal and its voice awakening method |
| CN109979438A (en) * | 2019-04-04 | 2019-07-05 | Oppo广东移动通信有限公司 | Voice awakening method and electronic equipment |
| CN110223691A (en) * | 2019-06-11 | 2019-09-10 | 苏州思必驰信息科技有限公司 | Voice wakes up the method for handover control and device of identification |
| CN110427097A (en) * | 2019-06-18 | 2019-11-08 | 华为技术有限公司 | Voice data processing method, apparatus and system |
| CN110611524A (en) * | 2019-09-26 | 2019-12-24 | 联想(北京)有限公司 | Bluetooth data information transmission method and device |
| CN110703895A (en) * | 2019-09-30 | 2020-01-17 | 联想(北京)有限公司 | Control method and device |
| CN110968353A (en) * | 2019-12-06 | 2020-04-07 | 惠州Tcl移动通信有限公司 | Central processing unit awakening method and device, voice processor and user equipment |
| CN112233677A (en) * | 2019-06-28 | 2021-01-15 | 北京奇虎科技有限公司 | Intelligent interaction equipment |
| CN113031749A (en) * | 2019-12-09 | 2021-06-25 | Oppo广东移动通信有限公司 | Electronic device |
| CN114005442A (en) * | 2021-10-28 | 2022-02-01 | 北京乐驾科技有限公司 | Projector, and awakening system and method of projector |
| WO2023097761A1 (en) * | 2021-11-30 | 2023-06-08 | 中国科学院深圳先进技术研究院 | Terminal device based on voice control, and voice control system |
| WO2024169411A1 (en) * | 2023-02-15 | 2024-08-22 | Oppo广东移动通信有限公司 | Voice wake-up method and apparatus, electronic device, storage medium, and product |
-
2018
- 2018-06-29 CN CN201810693654.5A patent/CN108877805A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448720A (en) * | 2018-12-18 | 2019-03-08 | 维拓智能科技（深圳）有限公司 | Convenience service self-aided terminal and its voice awakening method |
| CN109979438A (en) * | 2019-04-04 | 2019-07-05 | Oppo广东移动通信有限公司 | Voice awakening method and electronic equipment |
| CN110223691A (en) * | 2019-06-11 | 2019-09-10 | 苏州思必驰信息科技有限公司 | Voice wakes up the method for handover control and device of identification |
| CN110427097A (en) * | 2019-06-18 | 2019-11-08 | 华为技术有限公司 | Voice data processing method, apparatus and system |
| WO2020253715A1 (en) * | 2019-06-18 | 2020-12-24 | 华为技术有限公司 | Voice data processing method, device and system |
| CN112233677A (en) * | 2019-06-28 | 2021-01-15 | 北京奇虎科技有限公司 | Intelligent interaction equipment |
| CN110611524A (en) * | 2019-09-26 | 2019-12-24 | 联想(北京)有限公司 | Bluetooth data information transmission method and device |
| CN110703895A (en) * | 2019-09-30 | 2020-01-17 | 联想(北京)有限公司 | Control method and device |
| CN110968353A (en) * | 2019-12-06 | 2020-04-07 | 惠州Tcl移动通信有限公司 | Central processing unit awakening method and device, voice processor and user equipment |
| CN113031749A (en) * | 2019-12-09 | 2021-06-25 | Oppo广东移动通信有限公司 | Electronic device |
| CN114005442A (en) * | 2021-10-28 | 2022-02-01 | 北京乐驾科技有限公司 | Projector, and awakening system and method of projector |
| WO2023097761A1 (en) * | 2021-11-30 | 2023-06-08 | 中国科学院深圳先进技术研究院 | Terminal device based on voice control, and voice control system |
| WO2024169411A1 (en) * | 2023-02-15 | 2024-08-22 | Oppo广东移动通信有限公司 | Voice wake-up method and apparatus, electronic device, storage medium, and product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108877805A (en) | Speech processes mould group and terminal with phonetic function | |
| CN106920548B (en) | Voice control device, voice control system, and voice control method | |
| CN106981290B (en) | Voice control device and voice control method | |
| CN107147792B (en) | Method and device for automatically configuring sound effect, mobile terminal and storage device | |
| CN108859992A (en) | Intelligent vehicle-carried bracket | |
| CN105976814B (en) | Control method and device of head-mounted equipment | |
| CN108108142A (en) | Voice information processing method, device, terminal device and storage medium | |
| CN107277904A (en) | A kind of terminal and voice awakening method | |
| CN105338459A (en) | MEMS (Micro-Electro-Mechanical System) microphone and signal processing method thereof | |
| CN108810280B (en) | Voice acquisition frequency processing method and device, storage medium and electronic equipment | |
| CN107919138B (en) | Emotion processing method in voice and mobile terminal | |
| CN111105796A (en) | Wireless earphone control device and control method, and voice control setting method and system | |
| CN101424924A (en) | Sound control intelligent household control system | |
| CN106847291A (en) | Speech recognition system and method that a kind of local and high in the clouds is combined | |
| CN203325186U (en) | Household voice box device for controlling household appliances | |
| CN105975063B (en) | A kind of method and apparatus controlling intelligent terminal | |
| CN112230877A (en) | Voice operation method and device, storage medium and electronic equipment | |
| CN109712623A (en) | Sound control method, device and computer readable storage medium | |
| CN110322880A (en) | Vehicle-mounted terminal equipment and the method for waking up its multiple interactive voice program | |
| CN109545216A (en) | A kind of audio recognition method and speech recognition system | |
| CN108172221A (en) | The method and apparatus of manipulation aircraft based on intelligent terminal | |
| CN201181413Y (en) | Acoustic control intelligent household control device | |
| CN108833648A (en) | Intelligent terminal protective shell | |
| KR20200045851A (en) | Electronic Device and System which provides Service based on Voice recognition | |
| CN202838948U (en) | Communication device speech-controlling air conditioning based on mobile communication terminal |
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 |