CN112562660A - Combined speech recognition processing method - Google Patents
Combined speech recognition processing method Download PDFInfo
- Publication number
- CN112562660A CN112562660A CN201910913166.5A CN201910913166A CN112562660A CN 112562660 A CN112562660 A CN 112562660A CN 201910913166 A CN201910913166 A CN 201910913166A CN 112562660 A CN112562660 A CN 112562660A
- Authority
- CN
- China
- Prior art keywords
- voice
- processing method
- speech recognition
- recognition processing
- dsp
- 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
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
Abstract
The invention discloses a combined speech recognition processing method, which comprises the following steps: mark ke feng, DSP speech signal processing, Spi Flash, wireless communication module, MCU. According to the voice processing method, voice instructions can be collected through Mark wind, through DSP voice signal processing, direct off-line comparison is conducted on direct voice instructions stored locally in the Spi Flash to achieve control over on and off of the intelligent device, or collected fuzzy voice instructions such as dialects are transmitted to an external cloud terminal through the wireless communication module to be analyzed, and then instructions are sent to the switch according to cloud terminal analysis results. The processing method can perform voice processing under the condition of networking or network disconnection, and effectively recognize voice instructions, thereby controlling equipment more effectively. Need not to add the gateway, also need not to change current circuit wiring of family, equipment internal control procedure, just can realize voice control equipment to improve the flexibility of system, speech recognition processing time is faster, and the recognition effect is more accurate, can greatly improve user experience.
Description
Technical Field
The invention relates to the technical field of voice recognition processing and intelligent home control, in particular to a combined voice recognition processing method.
Background
With the gradual development of science and technology, smart home gradually enters common people, voice processing also becomes a necessary means for various intelligent devices, and intelligent control over various devices can be realized by simply one voice instruction. However, the existing voice processing method is simple, and only adaptation can be performed by comparing with a locally pre-stored voice command, or only by means of a network, and under the conditions of no network or poor network speed, the phenomena of wrong or invalid command recognition can occur, which results in poor effect of controlling equipment by the voice command, and further greatly affects user experience.
Disclosure of Invention
The invention provides a combined voice recognition processing method aiming at the defects of the technology, which can perform voice processing under the condition of networking or network disconnection, effectively recognize voice instructions and further effectively control equipment. Need not to add the gateway, also need not to change current circuit wiring of family, equipment internal control procedure, just can realize voice control equipment to improve the flexibility of system, speech recognition processing time is faster, and the recognition effect is more accurate, can greatly improve user experience.
The invention provides a combined voice recognition processing method, which comprises the following steps: mark ke feng, DSP speech signal processing, Spi Flash, wireless communication module, MCU.
The marker is used for receiving a voice command sent by a user and transmitting the voice command to the DSP voice signal for further processing;
the Spi Flash is used for storing an information base with preset voice instructions;
the DSP voice signal processing is used for processing the voice signals so as to obtain some voice parameters to realize more efficient transportation or storage;
the wireless communication module comprises any one of a ZigBee module, a Wi-Fi module, a Bluetooth module, a GSM module and a 4G module and is used for transmitting the acquired fuzzy voice instruction to an external cloud for analysis; the method can also be used for upgrading a local prestored instruction library on line;
MCU is used for forming the computer of chip level, can be based on the received voice command of mark microphone and the gained information of DSP speech signal processing, can compare with the voice command information base that prestores in Spi Flash under the off-line state, will compare the instruction that matches and issue again, or the switch of the voice command controlgear that obtains based on high in the clouds analysis under the networking state.
Based on the technical scheme provided by the invention, compared with the prior art, the method has the following beneficial effects:
according to the voice processing method provided by the invention, the voice instruction can be collected through Mark wind, the voice instruction is processed through a DSP voice signal, the direct voice instruction which is locally pre-stored in the Spi Flash is directly compared in an off-line mode to control the on and off of the intelligent device, or the collected fuzzy voice instruction such as dialect is transmitted to an external cloud terminal through the wireless communication module to be analyzed, and then the instruction is sent to the switch according to the analysis result of the cloud terminal, so that the intelligent device can be used in a networking state and an off-line state, the instruction recognition efficiency is higher, the accuracy degree is higher, and the user experience can be effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the description of the embodiments will be briefly introduced below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and that other drawings may be obtained from these drawings by those of ordinary skill in the art without inventive effort.
FIG. 1 is a flow chart of a combined speech recognition processing method of the present invention.
FIG. 2 is a block diagram of a combined speech recognition processing method according to the present invention.
FIG. 3 is a diagram of an embodiment of a combined speech recognition processing method according to the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It is to be understood that these examples are intended to clearly and completely describe the present invention and are not to be construed as limiting the present invention. Moreover, it should be understood that all other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any inventive work are within the scope of the present invention.
Please refer to fig. 1-3.
Referring to fig. 1, an embodiment of the present invention provides a combined speech recognition processing method, which includes: mic receives an instruction sent by a user, compares the instruction with a voice instruction information base prestored in Spi Flash after the instruction is processed by a DSP voice signal, directly sends the instruction if the instruction is matched, and then executes the instruction; if the instructions are not matched, the instructions are sent to the cloud end for analysis, and then the instructions are issued and executed.
As shown in fig. 2, an embodiment of the present invention provides a combined speech recognition processing method, which mainly includes: mark ke feng, DSP speech signal processing, Spi Flash, wireless communication module, MCU.
Mark gram wind for the voice command that the receiving user sent.
The Spi Flash is used for storing an information base with preset voice instructions.
DSP speech signal handles, and DSP speech signal handles the output of connecting mark wind and MCU's input, can carry out parameter processing to the pronunciation instruction who gathers via mark wind, carries out various digital signal processing algorithm fast in real time.
The wireless communication module comprises any one of a ZigBee module, a Wi-Fi module, a Bluetooth module, a GSM module and a 4G module and is used for transmitting the acquired fuzzy voice instruction to an external cloud for analysis; and the method can also be used for upgrading a local prestored instruction library on line.
MCU is used for forming the computer of chip level, can be based on the received voice command of mark microphone and the gained information of DSP speech signal processing, can compare with the voice command information base that prestores in Spi Flash under the off-line state, will compare the instruction that matches and issue again, or the switch of the voice command controlgear that obtains based on high in the clouds analysis under the networking state.
As shown in fig. 3, the embodiment of the present invention provides a combined speech recognition processing method, which can be implemented on an intelligent switch. Exemplarily, a switch of an offline/networked combined voice-controlled luminaire can be specifically realized: after receiving the voice command, the Mark microphone processes the parameters of the voice voltage signal through DSP voice signal processing, then directly compares the voice command with the voice command voltage signal which is pre-stored locally in the Spi Flash voice command information base, when the similarity does not exceed a certain threshold value, the signal detection circuit judges that the voice command is a certain set voice, and finally the MCU processes and receives the matched voice signal to control the switch lamp, or the voice command received by the Mark microphone is a fuzzy voice command, such as dialect, the fuzzy voice command is transmitted to an external cloud terminal to be analyzed, and then the command is transmitted to the switch according to the cloud terminal analysis result, so that the accuracy and the effect of voice recognition are further improved.
Preferably, the voice processing method can be used for intelligent switches and other intelligent devices controlled by voice instructions.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are included in the scope of the present invention.
Claims (5)
1. A combined speech recognition processing method, comprising: mark ke feng, DSP speech signal processing, Spi Flash, wireless communication module, MCU.
2. The combined speech recognition processing method of claim 1, wherein: and the marker is used for receiving a voice instruction sent by a user and transmitting the voice instruction to the DSP for further processing.
3. The combined speech recognition processing method of claim 1, wherein: the Spi Flash is used for storing an information base with preset voice instructions.
4. The combined speech recognition processing method of claim 1, wherein: and the DSP voice signal processing is used for processing the voice signals so as to obtain some voice parameters to realize more efficient transportation or storage.
5. The combined speech recognition processing method of claim 1, wherein: the wireless communication module comprises any one of a ZigBee module, a Wi-Fi module, a Bluetooth module, a GSM module and a 4G module and is used for transmitting the acquired fuzzy voice instruction to an external cloud for analysis; and the method can also be used for upgrading a local prestored instruction library on line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910913166.5A CN112562660A (en) | 2019-09-25 | 2019-09-25 | Combined speech recognition processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910913166.5A CN112562660A (en) | 2019-09-25 | 2019-09-25 | Combined speech recognition processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112562660A true CN112562660A (en) | 2021-03-26 |
Family
ID=75029411
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910913166.5A Pending CN112562660A (en) | 2019-09-25 | 2019-09-25 | Combined speech recognition processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112562660A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114286362A (en) * | 2021-11-08 | 2022-04-05 | 厦门阳光恩耐照明有限公司 | Method and system for local voice network distribution and electronic equipment |
CN114527711A (en) * | 2021-11-08 | 2022-05-24 | 厦门阳光恩耐照明有限公司 | Intelligent equipment control method and device based on local voice and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102708865A (en) * | 2012-04-25 | 2012-10-03 | 北京车音网科技有限公司 | Method, device and system for voice recognition |
CN103247291A (en) * | 2013-05-07 | 2013-08-14 | 华为终端有限公司 | Updating method, device, and system of voice recognition device |
CN106452997A (en) * | 2016-09-30 | 2017-02-22 | 无锡小天鹅股份有限公司 | Household electrical appliance and control system thereof |
CN106997763A (en) * | 2017-03-17 | 2017-08-01 | 浙江大学 | A kind of air conditioning control device based on the processing of voice signal frequency domain |
CN107682240A (en) * | 2017-09-27 | 2018-02-09 | 四川长虹电器股份有限公司 | A kind of distributed sound interactive system for intelligent domestic |
-
2019
- 2019-09-25 CN CN201910913166.5A patent/CN112562660A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102708865A (en) * | 2012-04-25 | 2012-10-03 | 北京车音网科技有限公司 | Method, device and system for voice recognition |
CN103247291A (en) * | 2013-05-07 | 2013-08-14 | 华为终端有限公司 | Updating method, device, and system of voice recognition device |
CN106452997A (en) * | 2016-09-30 | 2017-02-22 | 无锡小天鹅股份有限公司 | Household electrical appliance and control system thereof |
CN106997763A (en) * | 2017-03-17 | 2017-08-01 | 浙江大学 | A kind of air conditioning control device based on the processing of voice signal frequency domain |
CN107682240A (en) * | 2017-09-27 | 2018-02-09 | 四川长虹电器股份有限公司 | A kind of distributed sound interactive system for intelligent domestic |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114286362A (en) * | 2021-11-08 | 2022-04-05 | 厦门阳光恩耐照明有限公司 | Method and system for local voice network distribution and electronic equipment |
CN114527711A (en) * | 2021-11-08 | 2022-05-24 | 厦门阳光恩耐照明有限公司 | Intelligent equipment control method and device based on local voice and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10380992B2 (en) | Natural language generation based on user speech style | |
US20200312329A1 (en) | Performing speech recognition using a local language context including a set of words with descriptions in terms of components smaller than the words | |
KR102025566B1 (en) | Home appliance and voice recognition server system using artificial intelligence and method for controlling thereof | |
US10083685B2 (en) | Dynamically adding or removing functionality to speech recognition systems | |
CN110232912B (en) | Speech recognition arbitration logic | |
EP3416164A1 (en) | Voice agent forwarding | |
CN106098062A (en) | Intelligent sound control system for identifying that processing locality is combined with wireless network and method | |
US10721661B2 (en) | Wireless device connection handover | |
US9601107B2 (en) | Speech recognition system, recognition dictionary registration system, and acoustic model identifier series generation apparatus | |
CN206097455U (en) | Speech recognition controlgear | |
CN106847291A (en) | Speech recognition system and method that a kind of local and high in the clouds is combined | |
CN112562660A (en) | Combined speech recognition processing method | |
CN107729433B (en) | Audio processing method and device | |
US10008205B2 (en) | In-vehicle nametag choice using speech recognition | |
CN109473095A (en) | A kind of intelligent home control system and control method | |
CN109617772A (en) | A kind of smart home system based on speech recognition | |
JP2000310999A (en) | Facilities control system | |
CN108735217A (en) | Control method of electronic device, device, storage medium and electronic equipment | |
US20190147855A1 (en) | Neural network for use in speech recognition arbitration | |
CN103208285A (en) | Household electrical appliance control method and system based on voice interaction of mobile communication terminals | |
CN108648752A (en) | A kind of intelligent sound control system and its control method based on cloud processing | |
CN105813355A (en) | Speech recognition-based intelligent lighting method and system | |
CN205620724U (en) | Intelligence pronunciation remote control system | |
CN105407445B (en) | A kind of connection method and the first electronic equipment | |
CN112203902B (en) | Device control apparatus and control method for controlling device |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210326 |