CN109979455A - A kind of dialect phonetic AI control method, device and terminal - Google Patents
A kind of dialect phonetic AI control method, device and terminal Download PDFInfo
- Publication number
- CN109979455A CN109979455A CN201910268128.9A CN201910268128A CN109979455A CN 109979455 A CN109979455 A CN 109979455A CN 201910268128 A CN201910268128 A CN 201910268128A CN 109979455 A CN109979455 A CN 109979455A
- Authority
- CN
- China
- Prior art keywords
- control
- speech
- intertranslation
- module
- instruction
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- 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
- G10L15/005—Language recognition
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The present invention relates to intelligent sound control field, a kind of dialect phonetic AI control method, device and terminal.The dialect phonetic AI control method includes: to obtain to wake up word and control instruction;Language learning state is entered according to control instruction;Speech reproduction is carried out by the voice messaging repeatedly obtained;By the language message of duplication carry out analysis and with mainstream speech intertranslation;Intellectual product is controlled according to mutual translation entry.The study and the control to intellectual product that the method can realize dialect in the state of without networking through the invention.
Description
Technical field
The present invention relates to intelligent sound control fields, and in particular to a kind of dialect phonetic AI control method, device and terminal.
Background technique
AI is theory, method, technology and the application system of the intelligence of research, exploitation for simulating, extending and extending people
One new technological sciences, artificial intelligence are a branches of computer science, it attempts to understand the essence of intelligence, and produces
A kind of new intelligence machine that can be made a response in such a way that human intelligence is similar, the research in the field includes robot, language
Identification, image recognition, natural language processing and expert system etc..
Above-mentioned language identification can be language and Voice conversion at the process for the information that can be handled.It is big in the world at present
There are about 6000 ~ 10000 multilinguals, it is relatively more tired to carry out complete documentation to this speech like sound for the language of the most of not text of dialect
It is difficult.Have following defect in the prior art: AI speech-sound intelligent needs the mandarin of standard to control, and mandarin is nonstandard, can not make
With being easy to be defined as pseudo- intelligence.Network cloud sound bank big data is needed for the device of some language identifications, net cannot be fallen,
Otherwise it is not available.
To solve the above problems, a kind of dialect phonetic AI control method, device and terminal of the present invention, without connection
The study and the control to intellectual product that dialect is realized in the state of net.
Summary of the invention
Present invention solves the technical problem that being to provide a kind of dialect phonetic AI control method, device and terminal.Described
A kind of dialect phonetic AI control method, device and terminal realized in the state of without networking the study of dialect with to intellectual product
Control.
In order to solve the above technical problem, the present invention provides technical solution are as follows:
A kind of dialect phonetic AI control method:
It obtains and wakes up word and control instruction;
Language learning state is entered according to control instruction;
Speech reproduction is carried out by the voice messaging repeatedly obtained;
By the language message of duplication carry out analysis and with mainstream speech intertranslation;
Intellectual product is controlled according to mutual translation entry.
Preferably, when the acquisition control instruction, if inputting in the stipulated time without right instructions, auto-returned waits waking up
State.If obtaining and not receiving control instruction after waking up word, auto-returned waits for wake-up states.Energy-efficient effect is reached, simultaneously
Realize intelligent automaticization.
Preferably, the speech reproduction is to carry out complete documentation to user language by intelligent sound technology.Voice skill
Art is the key technology in computer field, there is automatic speech recognition technology and speech synthesis technique, allows computer capacity to listen, energy
It sees, can say, can feel.It is of the present invention according to voice technology after to be system obtain voice by microphone, by voice messaging
Completely recorded.
Preferably, it is described user language is recorded after include analyzing voice, specially analyze voice
Structure, syntactic structure, the change of tune of continuous speech and tone sandhi.
Preferably, the intertranslation is specially corresponding with mainstream speech according to result of voice analysis, basic meaning unit
Relationship carries out intertranslation.The advantages of carrying out intertranslation for basic meaning unit and analysis result is that the result office of intertranslation is unlimited
It is expressed in single syntax, so that the control instruction of user has more freedom during statement, identifies the knowledge of control instruction
Other effect is also more preferable.
Preferably, mutual translation entry is generated after the completion of the intertranslation, mutual translation entry is adjusted for being matched with control instruction
Intellectual product is controlled with matched control instruction.Mutual translation entry is the process for converting voice and text, text and control
After the completion of instruction is matched, matched control instruction is called to control intellectual product.
Preferably, the control model includes three kinds: selling field mode, home mode, kitchen mode.The sales field mould
Formula is filtered stable state noise and dynamic noise after obtaining copying voice information.Control model is divided into three kinds of situations, considers
It having arrived under various circumstances, the requirement of the acquisition of voice, under the mode situation of sales field, it is desirable that voice transmission range is closer,
More complicated noise processed is carried out to voice simultaneously, comprising: filter out most stable state noises, such as motor, blower.Filtering
Fall dynamic noise in some lives, such as the underwater sound, door slam etc..
This solution, satisfaction are demonstrated under the environment of sales field, filter out around some voices, musical sound etc. and to obtain
Instruction it is more accurate.Under home mode, it is contemplated that in more quiet situation, the phonetic order of acquisition has been better simply makes an uproar
Sound accelerates recognition speed, while desired controlled range is bigger to carry out simple noise processed.
A kind of dialect phonetic AI control device:
Instruction acquisition module: the instruction acquisition module wakes up word and control instruction for obtaining;
Selecting module: the selecting module is used to enter language learning state according to control instruction;
Speech reproduction module: the speech reproduction module is used to carry out speech reproduction by the voice messaging repeatedly obtained;
Intertranslation module: the intertranslation module be used for by the language message of duplication carry out analysis and with mainstream speech intertranslation;
Control module: the control module is for controlling intellectual product according to mutual translation entry.
Preferably, the instruction acquisition module wakes up word and control instruction for obtaining;The wake-up word is for controlling
System processed is opened, and control word is used to carry out system the input of control instruction.
Preferably, the selecting module is used to enter language learning state according to control instruction;Into after the state
It can carry out language learning.
Preferably, the speech reproduction module is used to carry out speech reproduction by the voice messaging repeatedly obtained;It is described
Language message carry out duplication use intelligent sound technology realize voice duplication, duplication is generallyd use for the duplication of voice
Three times the case where.
Preferably, the intertranslation module be used for by the language message of duplication carry out analysis and with mainstream speech intertranslation;Institute
The analytic process for the voice stated is, it is described user language is recorded after include analyzing voice, specially analyze
Phonetic structure, syntactic structure, the change of tune of continuous speech and tone sandhi out.The intertranslation is specially according to speech analysis knot
The corresponding relationship of fruit, basic meaning unit and mainstream speech carries out intertranslation.Basic meaning unit and analysis result are carried out
The advantages of intertranslation, is that the result office of intertranslation is not limited to single syntax expression, so that mistake of the control instruction of user in statement
Freedom is had more in journey, identifies that the recognition effect of control instruction is also more preferable.
Preferably, the control module is for controlling intellectual product according to mutual translation entry.The mutual translation word
Item is the text generated after a kind of intertranslation, by the matching of the text and control instruction, to carry out the control of intellectual product.
The present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage has computer
Program instruction, the program instruction are suitable for being loaded by processor and executing above-mentioned dialect phonetic AI control method.
The present invention also provides a kind of mobile terminals comprising processor and memory, the processor is for executing
The program stored in memory, to realize above-mentioned dialect phonetic AI control method.
Compared with prior art, the device have the advantages that are as follows: a kind of dialect phonetic AI control of the present invention
Study of the method without realizing dialect in the state of networking and the control to intellectual product.Specifically, by the duplication of language, dividing
Analysis and the intertranslation of mainstream speech, realize the study of voice dialect, the study of dialect without network can be realized dialect control electric appliance and
Light.Preparatory typing language is not needed simultaneously, it is local to learn the local dialect, control can be operated.The control solution of dialect will never
The people to speak standard Chinese pronunciation uses, for example local old man and child.Control method described herein is not necessarily to network, is not necessarily to APP, nothing
Any terminal and platform auxiliary tool, product is needed locally to can be operated.Product modular simultaneously lowers docking any products AI
Voice development and production cost.Network is not needed as platform, is suitable for single machine and operates.Using while learning without waiting does intelligence
To hommization.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is a kind of flow diagram of dialect phonetic AI control method of the present invention;
Fig. 2 is a kind of structure chart of dialect phonetic AI control device of the present invention.
Specific embodiment
In conjunction with the accompanying drawings, the present invention is further explained in detail.These attached drawings are simplified schematic diagram, only with
Illustration illustrates basic flow chart of the invention, therefore it only shows process related to the present invention.
Embodiment 1
As shown in Figure 1, the present invention is a kind of dialect phonetic AI control method, the method specifically:
S1. it obtains and wakes up word and control instruction;
S2. language learning state is entered according to control instruction;
S3. speech reproduction is carried out by the voice messaging repeatedly obtained;
S4. by the language message of duplication carry out analysis and with mainstream speech intertranslation;
S5. intellectual product is controlled according to mutual translation entry.
Step S1., which is obtained, wakes up word and control instruction, and there are three types of the instructions altogether of the control language brain:
The first: waking up word and control instruction, and it is all usually this mode on intelligent sound that this mode, which is referred to as One Shot, but
The mode of the most convenient of voice control, such as: it is small and lamp to be opened.
Second: individually say control control instruction, such as: lamp pass, after system wake-up, it can only say and control finger
It enables.
The third: individually saying wake up instruction, such as: it is small can it is small can, wake up system, generally as wake-up mode.
Step S2: language learning state is entered according to control instruction;Into after language learning state, including following several
Point requires:
In dialect study, ambient enviroment is kept quite state;Mouth is best at 1 meter or so with a distance from microphone;The language of acquisition
Speed needs to slow down, slightly slower than normal word speed;Speaking, it is full to pronounce distinctly;When learning training, if played, " instruction of study is not
Standardize, the study that please retell xth all over xx instructs " when, the content for indicating that recording training quality is not good enough or speaking is less than three
Word, trained speech content must be more than three words or three words;After learning training, if recognition effect is bad, need
After deletion, then relearn training one time.
Step S3: speech reproduction is carried out by the voice messaging repeatedly obtained;
Preferably, the speech reproduction is to carry out complete documentation to user language by intelligent sound technology.Voice technology is
Key technology in computer field has automatic speech recognition technology and speech synthesis technique, allow computer capacity to listen, can see,
It can say, can feel.It is of the present invention that after to be system obtain voice by microphone, voice messaging is carried out according to voice technology
Complete record.
Step S4: by the language message of duplication carry out analysis and with mainstream speech intertranslation;
The analysis of the voice point are as follows: preferably, it is described user language is recorded after include dividing voice
Analysis, specially analyzes phonetic structure, syntactic structure, the change of tune of continuous speech and tone sandhi.The phonetic structure includes:
Initial consonant, simple or compound vowel of a Chinese syllable, tone of syllabic language etc..
The intertranslation is specially to be carried out according to the corresponding relationship of result of voice analysis, basic meaning unit and mainstream speech
Intertranslation.The advantages of the method, is, the advantages of basic meaning unit and analysis result progress intertranslation is, the knot of intertranslation
Fruit office is not limited to single syntax expression, so that the control instruction of user has more freedom, identification control during statement
The recognition effect of instruction is also more preferable.
Such as: user issue it is small close whole light/small turn off whole light/small can light all turn off/it is small can
Light all closed/it is small light can be all turned off/it is small can light whole pass/it is small can the full pass of light/small can the full pass of lamp/
It is small can lamp close entirely/it is small can the full pass of lamp/it is small can lamp turn off entirely/it is small lamp is turned off can entirely/it is small can lamp whole pass/small can be
Lamp all closed/it is small can lamp all turn off/it is small lamp can be all turned off/it is small can lamp all passes/small can lamp all turn off/it is small can be lamp
It all closes and/small lamp all to be turned off the whole light of closing/turn off whole light/light and all turn off/light whole pass/lamp
Light all turns off/light whole pass/the complete full pass of pass/lamp of light/full pass of lamp/the full pass of lamp/lamp turns off entirely/lamp
Turn off entirely/lamp all closed/lamp whole pass/lamp is all turned off/lamp is all turned off/lamp all passes/lamp all turns off/lamp
It has all closed/lamp has all been turned off, above all of expression way all can recognize to close the instruction of whole light.
Step S5: intellectual product is controlled according to mutual translation entry.
Mutual translation entry is generated after the completion of the intertranslation, mutual translation entry calls matching for being matched with control instruction
Control instruction control intellectual product.Mutual translation entry be the process for converting voice and text, text and control instruction into
After the completion of row matching, matched control instruction is called to control intellectual product.
Embodiment 2
Exit the process of study are as follows:
If system plays " please say that xth is instructed all over the study of xxx ", user does not speak, and after 30 seconds, system can play " study
Time-out, during system reboot comes into force ", system can automatically exit from mode of learning.The dialect instruction of learning success can all retain, still
It can be with accent recognition.
Embodiment 3
System and device technical parameter:
System and device is powered using 5V USB port, is plugged microphone and loudspeaker, and after powering on, 8 seconds or so, loudspeaker played " xxx preparation
It is ready ".
Control model includes three kinds: selling field mode, home mode, kitchen mode.The sales field pattern acquiring replicates language
Voice is filtered to stable state noise and dynamic noise after message breath.When control model is set as home mode, environmental noise
No more than 60 decibels, identification distance is no more than 5 meters, and the projecting noise of sound of speaking can be identified effectively, user needs face
Microphone can not bow towards other directions.
When control model is set as selling field mode, identification distance is no more than 1 meter, the projecting noise of one's voice in speech,
Can effectively it identify.The best face microphone of mouth can not bow or towards other directions.
As shown in Fig. 2, the present invention provides a kind of dialect phonetic AI control devices:
Instruction acquisition module 1: the instruction acquisition module wakes up word and control instruction for obtaining;
Selecting module 2: the selecting module is used to enter language learning state according to control instruction;
Speech reproduction module 3: the speech reproduction module is used to carry out speech reproduction by the voice messaging repeatedly obtained;
Intertranslation module 4: the intertranslation module be used for by the language message of duplication carry out analysis and with mainstream speech intertranslation;
Control module 5: the control module is for controlling intellectual product according to mutual translation entry.
The instruction acquisition module 1: word and control instruction are waken up for obtaining;The wake-up word is used for control system
It opens, control word is used to carry out system the input of control instruction.
The selecting module 2: for entering language learning state according to control instruction;It can be carried out after into the state
Language learning.
The speech reproduction module 3: speech reproduction is carried out for the voice messaging by repeatedly obtaining;The language
Information carries out duplication and uses the duplication that intelligent sound technology realizes voice, and the duplication of voice is generallyd use and is replicated three times
Situation.
The intertranslation module 4: for by the language message of duplication carry out analysis and with mainstream speech intertranslation;The language
The analytic process of sound is, it is described user language is recorded after include analyzing voice, specially analyze voice
Structure, syntactic structure, the change of tune of continuous speech and tone sandhi.The intertranslation be specially based on the analysis results, basic meaning
Intertranslation is carried out between any text or voice and mainstream speech of the corresponding relationship and language of unit and mainstream speech.For base
The advantages of this meaning unit and analysis result carry out intertranslation is that the result office of intertranslation is not limited to single syntax expression, makes
The control instruction for obtaining user has more freedom during statement, identifies that the recognition effect of control instruction is also more preferable.
The control module 5: for being controlled according to mutual translation entry intellectual product.The mutual translation entry is one
The language text generated after kind intertranslation, by the matching of the text and control instruction, to carry out the control of intellectual product.
Above-listed detailed description is illustrating for possible embodiments of the present invention, and above embodiments are not to limit this
The scope of the patents of invention, all equivalence enforcements or change without departing from carried out by the present invention, is intended to be limited solely by the scope of the patents of this case.
Claims (11)
1. a kind of dialect phonetic AI control method characterized by comprising
It obtains and wakes up word and control instruction;
Language learning state is entered according to control instruction;
Speech reproduction is carried out by the voice messaging repeatedly obtained;
By the language message of duplication carry out analysis and with mainstream speech intertranslation;
Intellectual product is controlled according to mutual translation entry.
2. a kind of dialect phonetic AI control method according to claim 1, which is characterized in that the acquisition control instruction
When, if inputting in the stipulated time without right instructions, auto-returned waits for wake-up states.
3. a kind of dialect phonetic AI control method according to claim 1, which is characterized in that the speech reproduction is logical
It crosses intelligent sound technology and complete documentation is carried out to user speech.
4. a kind of dialect phonetic AI control method according to claim 3, which is characterized in that it is described to user speech into
Include analyzing voice after row record, specially analyzes phonetic structure, syntactic structure, the change of tune of continuous speech and company
Continuous modified tone, generates result of voice analysis.
5. a kind of dialect phonetic AI control method according to claim 1, which is characterized in that the intertranslation is specially root
Intertranslation is carried out according to the corresponding relationship of result of voice analysis, basic meaning unit and mainstream speech.
6. a kind of dialect phonetic AI control method according to claim 5, which is characterized in that raw after the completion of the intertranslation
At mutual translation entry, mutual translation entry calls matched control instruction control intellectual product for being matched with control instruction.
7. a kind of dialect phonetic AI control method according to claim 1, which is characterized in that the control model includes
Three kinds: selling field mode, home mode, kitchen mode.
It include being filtered to stable state noise and dynamic noise after sales field pattern acquiring copying voice information described in 8..
9. a kind of dialect phonetic AI control device, comprising:
Instruction acquisition module: the instruction acquisition module wakes up word and control instruction for obtaining;
Selecting module: the selecting module is used to enter language learning state according to control instruction;
Speech reproduction module: the speech reproduction module is used to carry out speech reproduction by the voice messaging repeatedly obtained;
Intertranslation module: the intertranslation module be used for by the language message of duplication carry out analysis and with mainstream speech intertranslation;
Control module: the control module is for controlling intellectual product according to mutual translation entry.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence instruction, which is suitable for by processor load and perform claim requires 1 ~ 8 described in any item methods.
11. a kind of mobile terminal, which is characterized in that including processor and memory, the processor is for executing storage
The program stored in device, to realize the described in any item methods of claim 1 ~ 8.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910268128.9A CN109979455A (en) | 2019-04-03 | 2019-04-03 | A kind of dialect phonetic AI control method, device and terminal |
CN201910625720.XA CN110379421A (en) | 2019-04-03 | 2019-07-11 | A kind of dialect phonetic AI control method, device and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910268128.9A CN109979455A (en) | 2019-04-03 | 2019-04-03 | A kind of dialect phonetic AI control method, device and terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109979455A true CN109979455A (en) | 2019-07-05 |
Family
ID=67082943
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910268128.9A Pending CN109979455A (en) | 2019-04-03 | 2019-04-03 | A kind of dialect phonetic AI control method, device and terminal |
CN201910625720.XA Pending CN110379421A (en) | 2019-04-03 | 2019-07-11 | A kind of dialect phonetic AI control method, device and terminal |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910625720.XA Pending CN110379421A (en) | 2019-04-03 | 2019-07-11 | A kind of dialect phonetic AI control method, device and terminal |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN109979455A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111354360A (en) * | 2020-03-17 | 2020-06-30 | 北京百度网讯科技有限公司 | Voice interaction processing method and device and electronic equipment |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1645363A (en) * | 2005-01-04 | 2005-07-27 | 华南理工大学 | Portable realtime dialect inter-translationing device and method thereof |
CN101269638A (en) * | 2008-04-10 | 2008-09-24 | 清华大学 | Vehicle electrical apparatus sound control method based on command word list |
US9697824B1 (en) * | 2015-12-30 | 2017-07-04 | Thunder Power New Energy Vehicle Development Company Limited | Voice control system with dialect recognition |
KR101836430B1 (en) * | 2017-08-07 | 2018-03-08 | 고현선 | Voice recognition and translation method and, apparatus and server therefor |
CN107657950B (en) * | 2017-08-22 | 2021-07-13 | 广州小鹏汽车科技有限公司 | Automobile voice control method, system and device based on cloud and multi-command words |
CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
CN109410936A (en) * | 2018-11-14 | 2019-03-01 | 广东美的制冷设备有限公司 | Air-conditioning equipment sound control method and device based on scene |
CN109360563B (en) * | 2018-12-10 | 2021-03-02 | 珠海格力电器股份有限公司 | Voice control method and device, storage medium and air conditioner |
-
2019
- 2019-04-03 CN CN201910268128.9A patent/CN109979455A/en active Pending
- 2019-07-11 CN CN201910625720.XA patent/CN110379421A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111354360A (en) * | 2020-03-17 | 2020-06-30 | 北京百度网讯科技有限公司 | Voice interaction processing method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN110379421A (en) | 2019-10-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11854527B2 (en) | Electronic device and method of controlling speech recognition by electronic device | |
Gerosa et al. | A review of ASR technologies for children's speech | |
RU2653283C2 (en) | Method for dialogue between machine, such as humanoid robot, and human interlocutor, computer program product and humanoid robot for implementing such method | |
Kandali et al. | Emotion recognition from Assamese speeches using MFCC features and GMM classifier | |
CN110148427A (en) | Audio-frequency processing method, device, system, storage medium, terminal and server | |
CN107972028B (en) | Man-machine interaction method and device and electronic equipment | |
CN106874265A (en) | A kind of content outputting method matched with user emotion, electronic equipment and server | |
CN109036395A (en) | Personalized speaker control method, system, intelligent sound box and storage medium | |
Michael | Automated Speech Recognition in language learning: Potential models, benefits and impact | |
CN101357269A (en) | Intelligent toy and use method thereof | |
US7222076B2 (en) | Speech output apparatus | |
CN112837401B (en) | Information processing method, device, computer equipment and storage medium | |
Catania et al. | CORK: A COnversational agent framewoRK exploiting both rational and emotional intelligence | |
CN110379421A (en) | A kind of dialect phonetic AI control method, device and terminal | |
KR20020060975A (en) | System and method of templating specific human voices | |
CN1494053A (en) | Speaking person standarding method and speech identifying apparatus using the same | |
CN112965603A (en) | Method and system for realizing man-machine interaction | |
Kuljic et al. | Mobile robot controlled by voice | |
CN112242134A (en) | Speech synthesis method and device | |
WO2022057759A1 (en) | Voice conversion method and related device | |
US20220230626A1 (en) | Creative work systems and methods thereof | |
Cavalcante et al. | Proof-of-concept evaluation of the mobile and personal speech assistant for the recognition of disordered speech | |
JP2001188788A (en) | Device and method for processing conversation and recording medium | |
JP2009500679A (en) | Communication method and communication device | |
CN115132204B (en) | Voice processing method, equipment, storage medium and computer program product |
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 |
Application publication date: 20190705 |
|
WD01 | Invention patent application deemed withdrawn after publication |