CN109002274A - The method of the electronic device and adjustment output sound of adjustable output sound - Google Patents
The method of the electronic device and adjustment output sound of adjustable output sound Download PDFInfo
- Publication number
- CN109002274A CN109002274A CN201710423290.4A CN201710423290A CN109002274A CN 109002274 A CN109002274 A CN 109002274A CN 201710423290 A CN201710423290 A CN 201710423290A CN 109002274 A CN109002274 A CN 109002274A
- Authority
- CN
- China
- Prior art keywords
- speech message
- voice print
- print database
- hearing
- message
- 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 claims description 23
- 230000000153 supplemental effect Effects 0.000 claims description 48
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000001755 vocal effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 1
- 241000238558 Eucarida Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
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
- G06F3/162—Interface to dedicated audio devices, e.g. audio drivers, interface to CODECs
-
- 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of electronic device of adjustable output sound, can judge the hearing situation of user, and the frequency of output sound is adjusted according to judging result, so that hearing situation of the sound of output together in user by sound-groove identification.
Description
Technical field
A kind of method of the present invention about adjustment output sound, it is especially a kind of to be adjusted according to the hearing situation of user
The method of whole output sound frequency.
Background technique
As the internet of things era flourishes, there are more and more devices equipped with intelligent sound service function, remove energy
The problem of providing outside user's acoustic control, capable of more answering user.By taking the Siri voice assistant software that Apple Inc. produces as an example,
The most problem of user can be replied with voice mode.
However, the sound frequency that existing intelligent voice service function is issued is all default, once user has in hearing
Obstacle, such as high-frequency sound compared with the old man not heard, the sound that will can not probably catch system and replied, cause using
Upper inconvenience.
Summary of the invention
The main object of the present invention is providing a kind of electronics dress that according to the hearing situation of user, can adjust output sound
The method for setting and adjusting output sound.
To reach above-mentioned purpose, the electronic device of adjustable output sound of the invention includes microphone, processing list
Member and loudspeaker.Speech message of the microphone to receive user's sending.Processing unit and microphone are electrically connected, and processing is single
Member includes that reply message obtains module, sound comparison module, judgment module and sound adjustment module.Reply message obtains module
To obtain the corresponding original answer speech message for being suitable for replying the speech message.Sound comparison module disappears to analyze voice
Breath, to obtain a voice print database, and compares whether the voice print database is consistent with built-in voice print database.Judgment module is in vocal print
When data are not coincident with built-in voice print database, the age of user, and the age according to judgement are judged according to speech message, is determined
One estimation hearing supplemental characteristic.Sound adjusts module to adjust original answer speech message according to estimation hearing supplemental characteristic
Sound frequency, with generate first reply speech message.Loudspeaker and processing unit are electrically connected, and loudspeaker export the first answer language
Sound message.
The present invention separately provides a kind of method of adjustment output sound, is suitable for an electronic device.Adjustment output of the invention
The method of sound includes the following steps: receiving the speech message that a user issues；It obtains and accordingly disappears suitable for replying the voice
The original answer speech message of breath；Voice message, to obtain a voice print database, and compare the voice print database whether with it is built-in
Voice print database is consistent；If it is not, judging the age of the user according to speech message, and the age according to judgement, an estimation is determined
Hearing supplemental characteristic；According to estimation hearing supplemental characteristic, the original sound frequency for replying speech message is adjusted, is answered with generating first
Multiple speech message；And export the first answer speech message.
Detailed description of the invention
Fig. 1 is the device architecture figure of the electronic device of adjustable output sound of the invention.
Fig. 2 is pair indicated between sound characteristic analysis result and age data, gender data and estimation hearing supplemental characteristic
Answer relational graph.
Fig. 3 is the corresponding relationship indicated between built-in voice print database and user's hearing supplemental characteristic.
Fig. 4 is the step flow chart of the method for adjustment output sound of the invention.
Wherein appended drawing reference are as follows:
Electronic device 1
Microphone 10
Processing unit 20
Reply message obtains module 21
Sound comparison module 22
Judgment module 23
Data search module 24
Sound adjusts module 25
Loudspeaker 30
Wireless communication module 40
Memory 50
Sound characteristic analyzes result 51
Gender data 52
Age data 53
Estimate hearing supplemental characteristic 54
Built-in voice print database 55
User's hearing supplemental characteristic 56
Second replies speech message 70
First replies speech message 80
User 90
Speech message 91
Specific embodiment
For that can allow your juror that can know more about technology contents of the invention, spy lifts preferred embodiment and is described as follows.
Below please first together referring to figs. 1 to Fig. 3.Wherein Fig. 1 is the electronic device of adjustable output sound of the invention
Device architecture figure；Fig. 2 is to indicate that sound characteristic is analyzed between result and age data, gender data and estimation hearing supplemental characteristic
Corresponding relationship；Fig. 3 is the corresponding relationship indicated between built-in voice print database and user's hearing supplemental characteristic.
As shown in Figure 1, in one of present invention embodiment, the electronic device 1 of adjustable output sound of the invention includes
There are microphone 10, processing unit 20, loudspeaker 30, wireless communication module 40 and memory 50.
In one of present invention embodiment, speech message 91 of the microphone 10 to receive a user 90 sending, even if
90 one's voice in speech of user can be received by microphone 10.
In one of present invention embodiment, processing unit 20 is to be electrically connected with microphone 10.Processing unit 20 includes
Reply message obtains module 21, sound comparison module 22, judgment module 23, data search module 24 and sound and adjusts module
25.It is noted that above-mentioned modules are in addition to it can be configured to hardware device, software program, firmware or combinations thereof, it also can be by electricity
Road circuit or other appropriate pattern configurations；Also, modules are except can be individually in addition to pattern configuration, the pattern that can also combine
Configuration.One preferred embodiment is that each module is all that software program is stored on memory 50, executes each mould by processing unit 20
Block is to reach function of the invention.In addition, present embodiment only illustrates presently preferred embodiments of the present invention, to avoid repeating, not
All possible variation combination is recorded in detail.However, the usual skill of this field, it is to be appreciated that above-mentioned each module or component not
It must be all necessary.It also may include the existing module or component of other more details and to implement the present invention.Each module or component is all
It may be omitted or be modified depending on demand, and other module or components may not be not present in wantonly two intermodule.
In one of present invention embodiment, it is corresponding suitable for replying the speech message to obtain that reply message obtains module 21
91 original answer speech message.The original corresponding relationship replied between speech message and speech message 80 is preset in advance.?
In the present embodiment, reply message obtains the meaning of one's words of the meeting voice message 91 of module 21, and according to analysis as a result, finding out opposite
The original answer speech message answered.For example, it is assumed that 91 content of speech message that user 90 issues is that " today can rain
? ", then to the speech message of this content 91, the original content for replying speech message may be set to " rainfall today probability X% " (X
Depending on Practical Meteorological Requirements prediction), it is " meeting today when reply message obtains module 21 to analyze the content of speech message 91 therefore
Rain? " or when similar to the meaning of one's words, it is that can correspond to find out " rainfall today probability X% " as former that reply message, which obtains module 21,
Begin to reply speech message.
It is noted that original answer speech message, which removes, to be looked by reply message acquirement module 21 according to lexical analysis result
It looks for acquirement outer, in other embodiments, can also be obtained from a server system (not shown)；In detail, in other embodiments,
Electronic device 1 can online one with intelligent sound service function server system, reply message obtain module 21 first by voice
Message 91 is sent to server system, by server system to the speech message 91 carry out lexical analysis, and according to analysis as a result,
Obtain the original answer speech message for accordingly being suitable for replying the speech message 91；Reply message obtains module 21 again from service later
Device system, which receives, obtains the original answer speech message.
It is above-mentioned to speak the analysis of the meaning of one's words about the mankind, and appropriate answer is responded based on the analysis results, it is existing technology
(such as: voice assistant's Siri software that Apple Computer produces, and can refer to text-to-speech (TTS) the relevant technologies text
Offer), it is to have known to usually intellectual in sound processing techniques field, therefore no longer repeat herein more.
In one embodiment of this invention, sound comparison module 22 is to voice message 91, to obtain a vocal print number
According to, and compare whether the voice print database is consistent with built-in voice print database 55.Wherein built-in voice print database 55 is in being stored in advance
It deposits in 50, and there are corresponding relationship (as shown in Figure 3), built-in voice print database 55 and users with user's hearing supplemental characteristic 56
Corresponding relationship between hearing supplemental characteristic can potentially may be filed in user's input by electronic device 1, wherein user's hearing
Supplemental characteristic 56 is the minimal volume data audible for the sound of different frequency of user 90.Related Acoustic Fingerprinting is
The prior art, particular content and principle have sporadically appeared in many patents or technical literature, have usual skill for fields
It is known, therefore no longer repeat herein more.
In one embodiment of this invention, judgment module 23 is not to be coincident with built-in voice print database 55 in voice print database
When, age and the gender of user 90, and age and gender according to judgement are judged according to speech message 91, determine that an estimation is listened
Force parameter data 54.Related to judge its age and gender according to mankind's voice, when being to apply the prior art,
Particular content and principle have pertinent literature to provide a reference, such as the speech recognition paper delivered by Microsoft, therefore herein i.e. not
It is again to repeat more.Judgment module 23 is after judging 90 age of user and gender, using such as chart shown in Fig. 2, to look into
Table mode obtains estimation hearing supplemental characteristic 54.For example, it is assumed that 90 age of user is 51 years old, and gender is male, reference
Fig. 2, judgment module 23 can correspond to acquirement " 1010101020303040 " as estimation hearing supplemental characteristic 54.
In one embodiment of this invention, data search module 24 is to be coincident with built-in voice print database 55 in voice print database
When, it searches and obtains user's hearing supplemental characteristic 56 corresponding with the built-in voice print database 55.For example, it is assumed that analyze
The voice print database of user is " 0110 ", meets a wherein built-in voice print database 55, at this point, data search module 24 can pass through
Such as chart shown in Fig. 3 obtains user's hearing supplemental characteristic that content is " 1010101010102020 " with lookup table mode
56。
In one embodiment of this invention, sound adjustment module 25 is to according to estimation hearing supplemental characteristic 54 or use
Person's hearing supplemental characteristic 56, adjust it is original reply speech message sound frequency, with generate one first reply speech message 80 or
One second replies speech message 70.More specifically, when the voice print database that analysis obtains is not coincident with built-in voice print database 55,
The estimation hearing supplemental characteristic 54 that sound adjustment module 25 is obtained according to judgment module 23 adjusts the original sound for replying speech message
Voice frequency, and generate first and reply speech message 80.Conversely, when the voice print database that analysis obtains meets a wherein built-in vocal print number
When according to 55, user's hearing supplemental characteristic 56 that sound adjustment module 25 is obtained according to data search module 24 adjusts original answer
The sound frequency of multiple speech message, and generate second and reply speech message 70.
In addition, in other embodiments, setting built-in voice print database 55 when user 90 only inputs, and setting pair is not inputted
When the user's hearing supplemental characteristic 56 answered, then in the case of voice print database has with built-in voice print database 55 and is consistent, sound tune
The meeting of mould preparation block 25 is according to default default hearing supplemental characteristic itself, to adjust the original sound frequency for replying speech message,
Speech message is replied to generate second.
In one embodiment of this invention, loudspeaker 30 are to be electrically connected with processing unit 20.Loudspeaker 30 can be used to export
One replies speech message 80 or the second answer speech message 70.
In one embodiment of this invention, wireless communication module 40 is to be electrically connected with processing unit 20, radio communication mold
Block 40 realizes wireless communication to on-line network, to provide electronic device 1.
In one embodiment of this invention, memory 50 is to be electrically connected with processing unit 20.Memory 50 is original to store
Reply the correspondence relationship information between speech message and speech message 80, sound characteristic analyzes result and age data, gender data
And estimate the correspondence relationship information between hearing supplemental characteristic and pair between built-in voice print database and user's hearing supplemental characteristic
Answer relation information.
Then, please also refer to Fig. 1 to Fig. 4, wherein Fig. 4 is the step process of the method for adjustment output sound of the invention
Figure, below will together referring to figs. 1 to Fig. 3, with each step shown in sequentially explanatory diagram 4.Though only it is noted that below be with
Before take off the electronic device 1 of the adjustable output sound for, illustrate the method for adjustment output sound of the invention, but this hair
The method of bright announcement is not limited with being applied to the electronic device 1.
Firstly, executing step S1: receiving the speech message that a user issues.
After user 90 starts the intelligent sound service function of electronic device 1, once it speaks against electronic device 1
(i.e. sending speech message), the speech message 91 issued can be received by microphone 10.
It executes step S2: obtaining the original answer speech message for accordingly being suitable for replying the speech message.
After receiving speech message 91, the reply message acquirement module 21 of processing unit 20 can be obtained accordingly to be suitable for replying and is somebody's turn to do
The original answer speech message of speech message 91.In an embodiment of the present invention, the reply message of processing unit 20 obtains module
The meaning of one's words of 21 meeting voice messages 91, and according to analysis as a result, obtaining corresponding original answer speech message to search.Its
In original answer speech message and speech message 91 can have corresponding relationship, this corresponding relationship can simultaneously be stored in advance.
Accordingly it is suitable for replying the original answer speech message of speech message not with above-mentioned side it must be noted that obtaining
Formula is limited.In other embodiments, original answer speech message can also be obtained module 21 from a server system by reply message
It is obtained in (not shown)；In detail, electronic device 1 can online one with intelligent sound service function server system, reply
Information, which obtains module 21, to be first sent to server system for speech message 91, carried out by server system to the speech message 91
Lexical analysis, and according to analysis as a result, obtaining the corresponding original answer speech message for being suitable for replying the speech message 91；It answers later
Complex information obtains module 21 and receives the acquirement original answer speech message from server system again.
Execute step S3: voice message, to obtain a voice print database, and compare the voice print database whether with built-in sound
Line data are consistent.
Original answer speech message after receiving speech message 91, in addition to obtaining the speech message for accordingly being suitable for replying
Outside, the sound comparison module 22 of processing unit 20 can also analyze the speech message 91, to obtain a voice print database.Sound compares mould
Block 22 simultaneously can compare whether voice print database is consistent with built-in voice print database 55.Wherein built-in voice print database 55 is in being stored in advance
It deposits in 50, and with user's hearing supplemental characteristic 56 there are corresponding relationship (as shown in Figure 3), the two can be possible by electronic device 1
Potential one or more users are previously entered setting.
It executes step S4: judging the age of the user, and age and gender according to judgement according to speech message, determine
One estimation hearing supplemental characteristic.
When comparison voice print database is not consistent with any built-in voice print database 55, the judgment module 23 of processing unit 20
Then age and the gender of user 90 can be judged, and according to the age and gender judged, using for example according to speech message 91
Chart shown in Fig. 2 obtains estimation hearing supplemental characteristic 54 with lookup table mode.For example, it is assumed that 90 age of user is 51
In year, gender is male, and referring to Fig. 2, judgment module 23 can correspond to acquirement " 1010101020303040 " as estimation hearing ginseng
Number data 54.Its age and gender are judged about according to mankind's spoken sounds, and located by prior art when being to apply is specific interior
Hold and principle has pertinent literature to provide a reference, therefore no longer repeats herein more.
It executes step S5: according to estimation hearing supplemental characteristic, the original sound frequency for replying speech message is adjusted, to generate
First replies speech message.
After the completion of step S4, then, the sound adjustment module 25 of processing unit 20 i.e. can be according to estimation hearing supplemental characteristic
54, the original sound frequency for replying speech message is adjusted, replies speech message 80 to generate first.
Execute step S6: output first replies speech message 80.
After first replies the generation of speech message 80, then the first answer speech message 80 can be transmitted to by processing unit 20
Loudspeaker 30 reply speech message 80 (play first and reply speech message 80) by the output of loudspeaker 30 first.
It executes step S7: searching and obtain user's hearing supplemental characteristic corresponding with built-in voice print database.
In an embodiment of the present invention, meet a wherein built-in vocal print number if comparing to have to voice print database in step S3
When according to 55, then the data search module 24 of processing unit 20 can search acquirement use corresponding with the built-in voice print database 55
Person's hearing supplemental characteristic 56.Taking what is shown in fig. 3 as an example, it is assumed that the voice print database for analyzing user is " 0110 ", meets wherein one
Built-in voice print database 55, at this point, data search module 24 can lookup table mode, obtain user's hearing supplemental characteristic 56 be
“1010101010102020”。
It executes step S8: according to user's hearing supplemental characteristic, the original sound frequency for replying speech message is adjusted, to produce
Raw second replies speech message.
In an embodiment of the present invention, after the completion of step S6, sound adjusts module 25 will be according to the use for searching acquirement
Person's hearing supplemental characteristic 56 and adjust it is original reply speech message sound frequency, with generate second reply speech message 70.
It must be noted that built-in voice print database 55 is set when user 90 only inputs in other embodiments, and
When not inputting the corresponding user's hearing supplemental characteristic 56 of setting, then there are the feelings being consistent with built-in voice print database 55 in voice print database
Under shape, sound adjusts module 25 can be according to default default hearing supplemental characteristic itself, to adjust original answer speech message
Sound frequency, with generate second reply speech message 70.
Execute step S9: output second replies speech message.
After second replies the generation of speech message 70, then the second answer speech message 70 can be transmitted to by processing unit 20
Loudspeaker 30 reply speech message 70 (play second and reply speech message 70) by the output of loudspeaker 30 second.
Illustrate via preceding taking off it is found that the method for adjustment output sound of the invention can be not defeated in the user of electronic device 1
Enter setting when being coincident with the hearing supplemental characteristic of one's own listening situation, by the analysis for the speech message that user issues, obtains
The hearing supplemental characteristic for being closer to user's hearing situation is taken, so that the speech frequency that electronic device 1 exports can relatively meet use
The hearing situation of person.
To sum up institute is old, and no matter the present invention is showing its totally different spy in the prior art with regard to purpose, means and effect
Sign.Only it should be noted that above-mentioned many embodiments are only to illustrate for ease of description, the right model that the present invention is advocated
It encloses from that should subject to the claims, not just the above examples.
Claims (10)
1. a kind of electronic device of adjustable output sound characterized by comprising
One microphone receives the speech message that a user issues；
One processing unit, to be electrically connected with the microphone, which includes:
One reply message obtains module, obtains the original answer speech message for accordingly being suitable for replying the speech message；
One sound comparison module, analyzes the speech message, to obtain a voice print database, and compare the voice print database whether with one in
Voice print database is built to be consistent；
One judgment module judges the use according to the speech message when the voice print database is not coincident with the built-in voice print database
The age of person, and the age according to judgement determine an estimation hearing supplemental characteristic；And one sound adjust module, estimated according to this
Hearing supplemental characteristic is counted, the original sound frequency for replying speech message is adjusted, replies speech message to generate one first；And
One loudspeaker, to be electrically connected with the processing unit, which exports the first answer speech message.
2. electronic device as described in claim 1, which is characterized in that the processing unit further includes a data search module, should
It is corresponding with the built-in voice print database to search acquirement when the voice print database is coincident with the built-in voice print database for data search module
User's hearing supplemental characteristic；Sound adjustment module simultaneously adjusts the original answer according to user's hearing supplemental characteristic
The sound frequency of speech message replies speech message to generate one second；The loudspeaker export the second answer speech message.
3. electronic device as described in claim 1, which is characterized in that sound adjustment module is more coincident in the voice print database
When the built-in voice print database, according to a default hearing supplemental characteristic, the original sound frequency for replying speech message is adjusted, to produce
Raw one second replies speech message；The loudspeaker export the second answer speech message.
4. electronic device as described in any one of claims 1 to 3, which is characterized in that the reply message obtains module analysis should
Speech message, and according to the result of analysis to obtain the original answer speech message.
5. electronic device as described in any one of claims 1 to 3, which is characterized in that the electronic device online server system
System after the reply message obtains module as the speech message is first sent to the server system, then is received from the server
The original answer speech message of system, which is the server system according to the analysis speech message
As a result it obtains.
6. a kind of method of adjustment output sound, is suitable for an electronic device, which is characterized in that this method includes the following steps:
Receive a speech message of user sending；
Obtain the original answer speech message for accordingly being suitable for replying the speech message；
The speech message is analyzed, to obtain a voice print database, and compares whether the voice print database is consistent with a built-in voice print database；
If it is not, judging the age of the user according to the speech message, and the age according to judgement, determine that force parameter is listened in an estimation
Data；
According to the estimation hearing supplemental characteristic, the original sound frequency for replying speech message is adjusted, is replied with generating one first
Speech message；And
Export the first answer speech message.
7. method as claimed in claim 6, which is characterized in that, should if the voice print database is coincident with the built-in voice print database
Method further includes the following steps:
It searches and obtains user hearing supplemental characteristic corresponding with the built-in voice print database；
According to user's hearing supplemental characteristic, the original sound frequency for replying speech message is adjusted, second is answered with generating this
Multiple speech message.
8. method as claimed in claim 6, which is characterized in that, should if the voice print database is coincident with the built-in voice print database
Method further includes the following steps:
According to a default hearing supplemental characteristic, the original sound frequency for replying speech message is adjusted, is replied with generating one second
Speech message.
9. such as the described in any item methods of claim 6 to 8, which is characterized in that the step of obtaining the original answer speech message
Include:
The speech message is analyzed, and according to the result of analysis to obtain the original answer speech message.
10. such as the described in any item methods of claim 6 to 8, which is characterized in that the online server system of the electronic device,
The step of obtaining the original answer speech message include:
The speech message is sent to the server system, so that the server system is obtained according to the result for analyzing the speech message
The original answer speech message；And
Receive the original answer speech message from the server system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710423290.4A CN109002274A (en) | 2017-06-07 | 2017-06-07 | The method of the electronic device and adjustment output sound of adjustable output sound |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710423290.4A CN109002274A (en) | 2017-06-07 | 2017-06-07 | The method of the electronic device and adjustment output sound of adjustable output sound |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109002274A true CN109002274A (en) | 2018-12-14 |
Family
ID=64572805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710423290.4A Pending CN109002274A (en) | 2017-06-07 | 2017-06-07 | The method of the electronic device and adjustment output sound of adjustable output sound |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109002274A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111031445A (en) * | 2019-11-29 | 2020-04-17 | 深圳普罗声声学科技有限公司 | Volume compensation method and device, computer equipment and storage medium |
| CN111416903A (en) * | 2019-01-08 | 2020-07-14 | 塞舌尔商元鼎音讯股份有限公司 | Sound playing system and method for adjusting output sound |
| CN112019972A (en) * | 2019-05-30 | 2020-12-01 | 原相科技股份有限公司 | Electronic device and equalizer adjusting method thereof |
| US11205440B2 (en) | 2018-12-28 | 2021-12-21 | Pixart Imaging Inc. | Sound playback system and output sound adjusting method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080031475A1 (en) * | 2006-07-08 | 2008-02-07 | Personics Holdings Inc. | Personal audio assistant device and method |
| CN103139351A (en) * | 2011-11-24 | 2013-06-05 | 联想(北京)有限公司 | Volume control method and device, and communication terminal |
| CN103236259A (en) * | 2013-03-22 | 2013-08-07 | 乐金电子研发中心(上海)有限公司 | Voice recognition processing and feedback system, voice response method |
| CN104123938A (en) * | 2013-04-29 | 2014-10-29 | 富泰华工业（深圳）有限公司 | Voice control system, electronic device and voice control method |
| CN106228978A (en) * | 2016-08-04 | 2016-12-14 | 成都佳荣科技有限公司 | A kind of audio recognition method |
-
2017
- 2017-06-07 CN CN201710423290.4A patent/CN109002274A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080031475A1 (en) * | 2006-07-08 | 2008-02-07 | Personics Holdings Inc. | Personal audio assistant device and method |
| CN103139351A (en) * | 2011-11-24 | 2013-06-05 | 联想(北京)有限公司 | Volume control method and device, and communication terminal |
| CN103236259A (en) * | 2013-03-22 | 2013-08-07 | 乐金电子研发中心(上海)有限公司 | Voice recognition processing and feedback system, voice response method |
| CN104123938A (en) * | 2013-04-29 | 2014-10-29 | 富泰华工业（深圳）有限公司 | Voice control system, electronic device and voice control method |
| CN106228978A (en) * | 2016-08-04 | 2016-12-14 | 成都佳荣科技有限公司 | A kind of audio recognition method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11205440B2 (en) | 2018-12-28 | 2021-12-21 | Pixart Imaging Inc. | Sound playback system and output sound adjusting method thereof |
| CN111416903A (en) * | 2019-01-08 | 2020-07-14 | 塞舌尔商元鼎音讯股份有限公司 | Sound playing system and method for adjusting output sound |
| CN112019972A (en) * | 2019-05-30 | 2020-12-01 | 原相科技股份有限公司 | Electronic device and equalizer adjusting method thereof |
| CN111031445A (en) * | 2019-11-29 | 2020-04-17 | 深圳普罗声声学科技有限公司 | Volume compensation method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107623614B (en) | Method and device for pushing information | |
| US20200365155A1 (en) | Voice activated device for use with a voice-based digital assistant | |
| TWI643184B (en) | Method and apparatus for speaker diarization | |
| AU2016216737B2 (en) | Voice Authentication and Speech Recognition System | |
| US9552815B2 (en) | Speech understanding method and system | |
| CN108962255B (en) | Emotion recognition method, emotion recognition device, server and storage medium for voice conversation | |
| TWI638352B (en) | Electronic device capable of adjusting output sound and method of adjusting output sound | |
| CN105489221B (en) | A kind of audio recognition method and device | |
| CN109002274A (en) | The method of the electronic device and adjustment output sound of adjustable output sound | |
| CN109785828A (en) | Spatial term based on user speech style | |
| CN110634472B (en) | Speech recognition method, server and computer readable storage medium | |
| CN108766441A (en) | A kind of sound control method and device based on offline Application on Voiceprint Recognition and speech recognition | |
| CN106663446A (en) | User environment aware acoustic noise reduction | |
| CN110246507B (en) | Voice recognition method and device | |
| CN110491414A (en) | Use the adjustable automatic speech recognition for monitoring time-out of dynamic | |
| CN110232912A (en) | Speech recognition arbitrated logic | |
| CN101262524A (en) | Rubbish voice filtration method and system | |
| US11115539B2 (en) | Smart voice system, method of adjusting output voice and computer readable memory medium | |
| KR20180046780A (en) | Method for providing of voice recognition service using double wakeup and apparatus thereof | |
| CN109785827A (en) | The neural network used in speech recognition arbitration | |
| JP6268916B2 (en) | Abnormal conversation detection apparatus, abnormal conversation detection method, and abnormal conversation detection computer program | |
| CN114694651A (en) | Intelligent terminal control method and device, electronic equipment and storage medium | |
| CN102857650B (en) | Method for dynamically regulating voice | |
| CN109427344A (en) | The method of electronic device and adjustment output sound with intelligent sound service function | |
| CN112735381B (en) | Model updating method and 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201026 Address after: Taiwan, Hsinchu, China Science and Technology Industrial Park, Hsinchu County Road, building 5, No. 5 Applicant after: PixArt Imaging Inc. Address before: Room 1, business centre, Eden, Seychelles Applicant before: SEYCHELLES SHANGYUANDING AUDIO Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181214 |
|
| WD01 | Invention patent application deemed withdrawn after publication |