CN108877822A - Intelligent voice system, the method for voice output adjustment and computer-readable memory media - Google Patents
Intelligent voice system, the method for voice output adjustment and computer-readable memory media Download PDFInfo
- Publication number
- CN108877822A CN108877822A CN201710320114.8A CN201710320114A CN108877822A CN 108877822 A CN108877822 A CN 108877822A CN 201710320114 A CN201710320114 A CN 201710320114A CN 108877822 A CN108877822 A CN 108877822A
- Authority
- CN
- China
- Prior art keywords
- speech message
- voice
- answer
- force parameter
- user
- 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 31
- 238000011156 evaluation Methods 0.000 claims abstract description 40
- 230000004044 response Effects 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims description 10
- 230000005611 electricity Effects 0.000 claims 1
- 238000004891 communication Methods 0.000 description 31
- 238000012545 processing Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 206010048865 Hypoacusis Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 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
- G06F3/165—Management of the audio stream, e.g. setting of volume, audio stream path
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
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)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
Abstract
A kind of intelligent voice system includes data reception module, speech message receiving module, voice response module and speech message output module.Data reception module receives the hearing evaluation data about a user, to just listen force parameter according to hearing evaluation data acquirement.Speech message receiving module receives the speech message that user issues.Voice response module obtains the answer speech message for being suitable for replying the speech message, wherein the sound frequency of the voice response information and listens force parameter according to this and is adjusted.Speech message output module exports the answer speech message.
Description
Technical field
The present invention may be adapted to user about a kind of intelligent voice system and voice output method of adjustment, especially one kind
Hearing situation output speech message intelligent voice system and voice output method of adjustment.
Background technique
With artificial intelligence development in science and technology, intelligent sound assistant is gradually matured.Existing intelligent sound assistant is logical
It crosses the utilization of big data and constantly updates, the considerable problem of the mankind can have been replied, thus be gradually widely used in daily
In life.However, though current intelligent sound assistant can generate the sound of different intonation according to difference the problem of answer,
Only sound frequency can not be adjusted according to the hearing situation of user, for the elderly or person hard of hearing, it is possible to produce
Life, which can not hear or can not hear clearly, replies the situation of content.
Therefore, it is really necessary to invent a kind of intelligent voice system of adjustable sound output frequency, problem is taken off before having improved.
Summary of the invention
The main purpose of the present invention is to provide a kind of intelligence of hearing situation output speech message that can be suitable for user
It can voice service function.
To reach above-mentioned purpose, the present invention discloses a kind of intelligent voice system comprising has data reception module, voice
Message reception module, voice response module and speech message output module.Data reception module is to receive about a user
Hearing evaluation data, with according to the hearing evaluation data acquirement just listen force parameter, wherein this listen force parameter be the user couple
In the audible minimal volume data of the sound of different frequency.Language of the speech message receiving module to receive user sending
Sound message.Voice response module is to obtain the answer speech message for being suitable for replying the speech message, and wherein the voice response is believed
The sound frequency of breath is simultaneously listened force parameter according to this and is adjusted.Speech message output module is to export the answer speech message.
To reach above-mentioned purpose, a kind of method that the present invention separately discloses voice output adjustment, it is suitable for voice clothes
Business server, and voice service server and electronic device are online.Voice output method of adjustment of the invention includes the following steps：
The hearing evaluation data about a user are received, to just listen force parameter according to hearing evaluation data acquirement, wherein this is listened
Force parameter is the user minimal volume data audible for the sound of different frequency；Receive the voice of user sending
Message；The speech message is analyzed, and finds out the answer text information for being suitable for replying the speech message based on the analysis results；According to
The answer text information generates a voice response information, wherein the sound frequency of the voice response information and listens force parameter according to this
And it is adjusted；And export the answer speech message.
According to another embodiment of the present invention, the method for the voice output adjustment is suitable for electronic device, wherein electronics
Device is online with voice service server online.This method includes the following steps：Receive the hearing evaluation number about a user
According to just listen force parameter according to hearing evaluation data acquirement, it is the user for different frequency that wherein this, which listens force parameter,
The audible minimal volume data of sound；Receive the speech message of user sending；The speech message is sent to a voice
Service server；The original answer speech message from the voice service server is received, wherein the original answer voice disappears
Breath searches acquirement according to the speech message for the voice service server；Force parameter is listened according to this, adjusts the original answer language
The sound frequency of sound message, to generate answer speech message；And export the answer speech message.
The present invention more discloses a kind of computer-readable memory media of internally stored program, after computer loads the program,
The method for the voice output adjustment that the achievable present invention discloses.
Detailed description of the invention
Fig. 1 is the implementation environment schematic diagram of the first embodiment of intelligent voice system of the present invention.
Fig. 2 is the implementation environment schematic diagram of the second embodiment of intelligent voice system of the present invention.
Fig. 3 is to indicate gender data, age data and the schematic diagram for listening the corresponding relationship between force parameter.
Fig. 4 is to indicate to just listen force parameter datagram.
Fig. 5 is the step flow chart of the first embodiment of the method for voice output of the present invention adjustment.
Fig. 6 is the step flow chart of the second embodiment of the method for voice output of the present invention adjustment.
Appended drawing reference is：
Intelligent voice system 1,1A
Data reception module 10,10A
Speech message receiving module 20,20A
Voice response module 30,30A
Lexical analysis unit 31
Speech message generates unit 32
Frequency adjustment unit 33,33A
Ask a question unit 34A
Reply receiving unit 35A
Speech message output module 40,40A
Voice service server 80,80A
Second wireless communication module 81,81A
Database 82,82A
Memory 83,96A
Reply module 84A
Electronic device 90,90A
Input interface 91,91A
First wireless communication module 92,92A
Microphone 93,93A
Audio processing chip 94,94A
Loudspeaker 95,95A
Hearing evaluation data H
Speech message V
User U
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.
It please refer to Fig. 1 below, and please also refer to Fig. 3 and Fig. 4.Wherein Fig. 1 is the of intelligent voice system of the present invention
The implementation environment schematic diagram of one embodiment；Fig. 3 is to indicate gender data, age data and listen showing for the corresponding relationship between force parameter
It is intended to；Fig. 4 is to indicate to just listen force parameter datagram.
As shown in Figure 1, in the first embodiment of the present invention, intelligent voice system 1 is installed on a voice service server
In 80.In addition to intelligent voice system 1, voice service server 80 further includes the second wireless communication module 81, database 82 and interior
Deposit 83.Voice service server 80 can be by the online electronic device 90 of the second wireless communication module 81, more specifically, at this
In embodiment, electronic device 90 includes input interface 91, the first wireless communication module 92, microphone 93, audio processing chip
94 and loudspeaker 95, and voice service server 80 can be by between the second wireless communication module 81 and the first wireless communication module 92
Communication establish, with online with electronic device 90.In a specific embodiment of the present invention, the second wireless communication module 81 and first
Wireless communication module 92 is wireless network card, but invention is not limited thereto.
Input interface 91, may be, for example, Touch Screen, be available for users to hearing evaluation data H of the U input about its own,
So that voice service server 80 is searched according to the hearing evaluation data H, acquirement is corresponding to listen force parameter (aftermentioned in detail).In this hair
In bright specific embodiment, age data and gender data of the hearing evaluation data H for user U, however, the present invention is not limited thereto,
It can also be to listen data of force parameter itself, and also must need to not include gender data.
Speech message V of the microphone 93 to receive user's sending can receive the user U sound issued
Sound.
Processing of the audio processing chip 94 to the speech message V progress analog/digital conversion for receiving microphone 93,
To generate the speech message V of number format.Also, the speech message V of number format can via the first wireless communication module 92 and
It is sent to voice service server 80.
Loudspeaker 95 plays sound to handle the signal generated according to audio processing chip 94.
In the first embodiment of the present invention, intelligent voice system 1 includes data reception module 10, speech message reception
Module 20, voice response module 30 and speech message output module 40.It can be configured to it is noted that above-mentioned modules remove
Hardware device, software program, firmware or combinations thereof are outer, can also configure by circuit loop or other appropriate patterns；Also, each mould
Block except can individually pattern configuration it is outer, the pattern that can also be combined configures.In one embodiment, each module is all software program
It is stored in memory 83, executes each module by the processor (not shown) in voice service server 80 to reach the present invention
Function.In another embodiment, each module can also be stored in a computer-readable memory media in form of software programs
In, after loading the program by computer, each module is executed to reach function of the invention.Present embodiment only illustrates the present invention again
Preferred embodiment do not record all possible variation combination in detail to avoid repeating.However, the usual knowledge of this field
Person is, it is to be appreciated that above-mentioned each module or device may not be all necessary.And to implement the present invention, it may also include other more details
Existing module or device.Each module or device all may be omitted or be modified depending on demand, and wantonly two intermodule may not be not present
Other modules or device.
In the first embodiment of the present invention, data reception module 10 is to receive the hearing evaluation from electronic device 90
Data H.Specifically, in the present embodiment, electronic device 90 is receiving the hearing inputted by user U by input interface 91
After assessing data H, which can be sent to voice service clothes via the first wireless communication module 92
Business device 80, is received by data reception module 10.But not limited to this for one of specific embodiment, can make electronic device 90
Display (not shown) on display one input picture, for user U input hearing evaluation data H；User U is in the input picture
The hearing evaluation data H inputted on face can be sent to voice service server 80.Data reception module 10 receives hearing evaluation
After data H, it can further be obtained according to the hearing evaluation data H and just listen force parameter, it is the user that wherein this, which listens force parameter,
The minimal volume data audible for the sound of different frequency.After force parameter is listened in acquirement, data reception module 10 simultaneously can should
Force parameter is listened to store into memory 83.
For the mapping table shown in Fig. 3, once age data and gender data difference in hearing evaluation data H
For " 71~80 " and " male ", then data reception module 10 can (this mapping table can be stored according to corresponding relationship shown in Fig. 2
In database 82) it finds out and listens force parameter to should be " 1010202040506060 " about the user, such as Fig. 4 institute can be used
The chart that shows indicates.Chart system shown in Fig. 4 represents user for audio 250 and 500 hertz of sound, it is audible most
Small volume is 10 decibels；For audio 1000 and 2000 hertz of sound, audible minimal volume is 20 decibels；For audio
3000 hertz of sound, audible minimal volume are 40 decibels；For 4000 hertz of sound of audio, audible minimum sound
Amount is 50 decibels；For audio 6000 and 8000 hertz of sound, audible minimal volume is 60 decibels.
In the first embodiment of the present invention, a language of the speech message receiving module 20 to receive user U sending
Sound message V.More specifically, in the present embodiment, the sound (i.e. speech message V) that user U is issued connects by microphone 93
Receive, and via audio processing chip 94 handle after, voice service server 80 can be sent to by the first wireless communication module 92,
And it is received by speech message receiving module 20.
In the first embodiment of the present invention, voice response module 30 is suitable for replying answering for speech message V to obtain
Multiple speech message wherein the sound frequency of the voice response information and is listened force parameter and is adjusted according to above-mentioned.In this implementation
In example, voice response module 30 includes lexical analysis unit 31, speech message generation unit 32 and frequency adjustment unit 33.Language
Analytical unit 31 anticipate to analyze the speech message V received by speech message receiving module 20, and based on the analysis results to look into
Find out answer text information (the corresponding pass between the analysis result and answer text information of the meaning of one's words for being suitable for replying speech message V
System can be stored in database 82).Speech message generates unit 32 will reply Text extraction as an original answer
Speech message.About the lexical analysis that the mankind speak, and appropriate answer is responded based on the analysis results, be existing technology (example
Such as：The Siri software that Apple Computer produces, and can refer to text-to-speech (TTS) relevant technical literature), it is at sound
It manages in technical field and has known to usually intellectual, therefore no longer repeat herein more.Frequency adjustment unit 33 should to foundation
Force parameter is listened, the original sound frequency for replying speech message is adjusted, to generate the answer speech message.
It must be noted that in other embodiments, above-mentioned speech message generates unit 32 can also direct basis hearing
Parameter and will reply Text extraction becomes voice response information, that is, during executing text-to-speech, i.e. foundation
Listen the frequency of force parameter adjustment output sound.
In the first embodiment of the present invention, speech message output module 40 is to export the answer speech message to second
Wireless communication module 81, and by the second wireless communication module 81 the answer speech message is sent to electronic device 90.It should
It, can be by loudspeaking after replying conversion process of the speech message via the digital-to-analog of the audio processing chip 94 of electronic device 90
The output of device 95 (i.e. broadcasting voice).Sound frequency due to replying speech message is foundation and user's hearing state is relevant listens
Force parameter and adjust, therefore the voice exported may be adapted to user and listen to.
Then, implementation environment schematic diagram of the Fig. 2 about the second embodiment of intelligent voice system of the present invention is please referred to.
In the second embodiment of the present invention, intelligent voice system 1A of the invention is mounted in electronic device 90A, electronics
Device 90A can be online to a voice service server 80A.Voice service server 80A includes the second wireless communication module
81A, database 82A and reply module 84A, voice service server 80A can thoroughly by the second wireless communication module 81A and and electronics
Device 90A realizes wireless communication.Electronic device 90A is in addition to intelligent voice system 1A, still wirelessly including input interface 91A, first
Communication module 92A, microphone 93A, audio processing chip 94A, loudspeaker 95A and memory 96A, and due to the function of these devices
It all ditto takes off described in first embodiment, therefore no longer repeats herein more.
In the second embodiment of the present invention, intelligent voice system 1A of the invention includes data reception module 10A, language
Sound message reception module 20A, voice response module 30A and speech message output module 40A.
In the second embodiment of the present invention, data reception module 10A is commented to receive the hearing from electronic device 90
Estimate data H.Specifically, in the present embodiment, the hearing evaluation data H that user U is inputted via input interface 91A can be passed
It send to intelligent voice system 1A, is received by data reception module 10A.After data reception module 10A receives hearing evaluation data H,
It can further be obtained according to the hearing evaluation data H and just listen force parameter, it is the user for difference that wherein this, which listens force parameter,
The audible minimal volume data of the sound of frequency.After force parameter is listened in acquirement, this can simultaneously be listened force parameter by data reception module 10A
Storage is into memory 96A.
In the second embodiment of the present invention, speech message receiving module 20A disappears to receive the voice of user U sending
Cease V.More specifically, in the present embodiment, the sound (i.e. speech message V) that user U is issued is received by microphone 93A,
And after handling via audio processing chip 94, it can be sent to intelligent voice system 1A, and connect by speech message receiving module 20A
It receives.
In the second embodiment of the present invention, voice response module 30A is suitable for replying answering for speech message V to obtain
Multiple speech message wherein the sound frequency of the voice response information and is listened force parameter and is adjusted according to above-mentioned.In this implementation
In example, voice response module 30A includes question unit 34A, replies receiving unit 35A and frequency adjustment unit 33A.Question unit
34A is, by the first wireless communication module 92A, to be sent to voice service server 80A for the speech message received.Voice
After the second wireless communication module 81A of service server 80A receives the speech message, the language can then be analyzed by replying module 84A
The meaning of one's words of sound message, and the answer text information for being suitable for replying the speech message is found out according to analysis result, and by the answer
Text extraction becomes an original answer speech message.Finally, the original answer speech message can pass through the second channel radio again
Letter module 81A is back to electronic device 90A.Receiving unit 35A is replied to receive from voice service server 80A passback
Original answer speech message.Frequency adjustment unit 33A is then according to force parameter is listened, to adjust the original sound for replying speech message
Voice frequency, to generate answer speech message.
In the second embodiment of the present invention, speech message output module 40A replies speech message to audio to export
Chip 94A is handled, which, can be by loudspeaker 95A output (i.e. broadcasting language after the conversion process of digital-to-analog
Sound).
Then, the step flow chart of the first embodiment for the method that Fig. 5 is adjusted about voice output of the present invention is please referred to, and
Please also refer to Fig. 1.
In the first embodiment of the present invention, the method for voice output of the invention adjustment is suitable for for example shown in FIG. 1
Voice service server 80, it includes each step be to be carried out by intelligent voice system 1.Voice service server 80 and electronics
Device 90 is online.
As shown in Figures 1 and 5, firstly, executing step S501：The hearing evaluation data about a user are received, with root
Force parameter is just listened according to hearing evaluation data acquirement.
In the first embodiment of the present invention, user U can via input interface 91 (such as：Touch Screen) input about
The hearing evaluation data H of itself, may include such as age data and gender data.Hearing evaluation data H can be wireless by first
Communication module 92 is sent to voice service server 80, is received by the second wireless communication module 81.Again by the second wireless communication
Module 81 transmits the hearing evaluation data H to intelligent voice system 1, is received by data reception module 10.Data reception module 10
It, further can be according to hearing evaluation data H, by searching for for example scheming after receiving about the hearing evaluation data H of user U
The mode of mapping table shown in 3, come obtain it is corresponding listen force parameter, this listen force parameter be the user for different frequency
The audible minimal volume data of sound.
Execute step S502：Receive the speech message that user issues.
After the intelligent sound service function of user U starting electronic device 90, once it speaks against electronic device 90
(i.e. sending speech message), the speech message V issued can be received by microphone 93.Then, speech message V can quilt
It is sent to voice service server 80, is received by the second wireless communication module 81.It again should by the transmission of the second wireless communication module 81
Speech message V is received to intelligent voice system 1 by speech message receiving module 20.
Execute step S503：The speech message is analyzed, and finds out be suitable for replying the speech message based on the analysis results
Reply text information.
After speech message receiving module 20 receives speech message V, the then lexical analysis unit of voice response module 30
31 can analyze the meaning of one's words of speech message V, and find out the answer text letter for being suitable for replying speech message V based on the analysis results
Breath.
Execute step S504：Text extraction, which will be replied, becomes original answer speech message.
After the completion of step S503, the speech message of voice response module 30, which generates unit 32, will reply Text extraction
As original answer speech message.
Execute step S505：According to force parameter is listened, the original sound frequency for replying speech message is adjusted, is replied with generating
Speech message.
Once replying text information is processed to be original answer speech message, then the frequency tune of voice response module 30
Whole unit 33 can listen force parameter according to what data reception module 10 obtained, adjust the original sound frequency for replying speech message,
Speech message is replied to generate.
It must be noted that in other embodiments, above-mentioned speech message generates unit 32 can also direct basis hearing
Parameter and will reply Text extraction become voice response information, i.e., during executing text-to-speech, i.e., foundation listen
The frequency of force parameter adjustment output sound in other words also can single step：According to force parameter is listened, Text extraction will be replied
As voice response information, come step of replacing S504 and S505.
Finally, executing step S506：Output replies speech message.
After the completion of step S505, finally, speech message output module 40 exports the answer speech message to the second channel radio
Believe module 81, and is sent to electronic device 90 by the second wireless communication module 81.The answer speech message is via audio
After the digital-to-analog conversion process for handling chip 94, (i.e. broadcasting voice) can be exported by loudspeaker 95.
Finally, the step flow chart of the second embodiment for the method that Fig. 6 is adjusted about voice output of the present invention is please referred to, and
Please also refer to Fig. 2, Fig. 3 and Fig. 4.
As shown in Fig. 2, the method for voice output adjustment of the invention is suitable for for example in the second embodiment of the present invention
Electronic device 90A shown in Fig. 2, it includes each step be to be carried out by intelligent voice system 1.Electronic device 90A and voice
Service server 80A is online.
As shown in fig. 6, firstly, executing step S601：The hearing evaluation data H about a user is received, it should with basis
Hearing evaluation data H acquirement just listens force parameter.
In the second embodiment of the present invention, similarly, user can input listening about itself by input interface 91A
Force estimation data H.Data reception module 10A will be commented from after input interface 91A reception hearing evaluation data H according to the hearing
Estimate data H, by searching for the mode of mapping table for example shown in Fig. 3, corresponding listens force parameter to obtain.
Execute step S602：Receive the speech message that user issues.
Similarly, in the second embodiment of the present invention, user U starts the intelligent sound service function of electronic device 90
Afterwards, the speech message V issued to electronic device 90 can be transmitted to audio processing chip 94A after by microphone 93A, and
After audio processing chip 94A is the conversion process of analog/digital, it is transmitted to intelligent voice system 1, mould is received by speech message
Block 20 receives.
Execute step S603：The speech message is sent to voice service server.
Speech message receiving module 20A is after receiving speech message V, then, the question unit of voice response module 30A
Speech message V can be sent to voice service server 80A by the first wireless communication module 92A by 34A.
After the second wireless communication module 81A of voice service server 80A receives speech message V, replies module 84A and connect
Can analyze the meaning of one's words of speech message V, and find out the answer text for being suitable for replying speech message V according to analysis result and believe
Breath.Then, the answer Text extraction can be become one original answer speech message by replying module 84A, and pass through the second nothing
The original answer speech message that processing generates is back to electronic device 90A by line communication module 81A.
Execute step S604：Receive the original answer speech message from voice service server.
It, can be by answer mould after original answer speech message sends back electronic device 90A via the second wireless communication module 81A
The answer receiving unit 35A of block 30A is received.
Execute step S605：According to force parameter is listened, the original sound frequency for replying speech message is adjusted, is replied with generating
Speech message.
After receiving from the original answer speech message of voice service server 80A, then voice response module 30A
Frequency adjustment unit 33A can listen force parameter according to what data reception module 10 obtained, adjust this and original reply speech message
Sound frequency, to generate answer speech message.
Finally, executing step S606：Output replies speech message.
After the completion of step S605, finally, speech message output module 40 exports the answer speech message to audio processing core
Piece 94A, the answer speech message can be exported after the digital-to-analog conversion process of audio processing chip 94A by loudspeaker 95A
(i.e. sending voice).
Illustrate via preceding taking off it is found that the method for the voice output adjustment that the present invention discloses can be according to the hearing shape of user
State adjusts the intelligent sound service function of electronic device when responding user's problem, the frequency of sound is exported, even if therefore electronics
The user of device has the obstacle in hearing, can also experience brought by the intelligent sound service function of electronic device offer just
Benefit.
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 illustrated only for the purposes of explanation, the interest field of the invention advocated
Apply described in claim from that should be subject to, not just the above examples.
Claims (12)
1. a kind of intelligent voice system, which is characterized in that including：
One data reception module, to receive about one of user hearing evaluation data, according to the hearing evaluation data
Acquirement just listens force parameter, and it is the user minimal volume number audible for the sound of different frequency that wherein this, which listens force parameter,
According to；
One speech message receiving module, to receive a speech message of user sending；
One voice response module is suitable for replying the one of the speech message and replies speech message, the wherein voice response to obtain
The sound frequency of information is simultaneously listened force parameter according to this and is adjusted；And
One speech message output module, to export the answer speech message.
2. intelligent voice system as described in claim 1, which is characterized in that voice response module includes：
One lexical analysis unit to analyze the speech message, and finds out be suitable for replying the speech message based on the analysis results
One reply text information；
One speech message generates unit, and to listen force parameter according to this, which is become the voice response
Information.
3. intelligent voice system as described in claim 1, which is characterized in that voice response module includes：
One lexical analysis unit to analyze the speech message, and finds out be suitable for replying the speech message based on the analysis results
One reply text information；
One speech message generates unit, the answer Text extraction is become an original answer speech message；And
One frequency adjustment unit adjusts the original sound frequency for replying speech message, to listen force parameter according to this to generate
The answer speech message.
4. intelligent voice system as described in claim 1, which is characterized in that voice response module includes：
One question unit, the speech message is sent to a voice service server, so that the voice service server point
An original answer speech message is generated after analysing the speech message；
One replies receiving unit, to receive the original answer speech message from the voice service server；And
One frequency adjustment unit adjusts the original sound frequency for replying speech message, to listen force parameter according to this to generate
The answer speech message.
5. intelligent voice system as described in claim 1, which is characterized in that user's hearing evaluation data include an age
Data and/or a gender data.
6. a kind of method of voice output adjustment, is suitable for a voice service server, one electricity of voice service server online
Sub-device, which is characterized in that the voice output method of adjustment includes the following steps：
The hearing evaluation data about a user are received, to just listen force parameter according to hearing evaluation data acquirement,
In this to listen force parameter be user minimal volume data audible for the sound of different frequency；
Receive a speech message of user sending；
The speech message is analyzed, and finds out the answer text information for being suitable for replying the speech message based on the analysis results；
According to the answer text information to generate a voice response information, the wherein sound frequency of the voice response information and foundation
This is listened force parameter and is adjusted；And
Export the answer speech message.
7. method as claimed in claim 6, which is characterized in that generate the voice response information according to the answer text information
Step includes：
Force parameter is listened according to this, which is become into the voice response information.
8. method as claimed in claim 6, which is characterized in that generate the voice response information according to the answer text information
Step includes：
The answer Text extraction is become into an original answer speech message；And
Force parameter is listened according to this, the original sound frequency for replying speech message is adjusted, to generate the answer speech message.
9. method as claimed in claim 6, which is characterized in that user's hearing evaluation data include an age data or/
An and gender data.
10. a kind of method of voice output adjustment, is suitable for an electronic device, the online voice service service of the electronic device
Device, which is characterized in that this method includes the following steps：
The hearing evaluation data about a user are received, to just listen force parameter according to hearing evaluation data acquirement, wherein
It is the user minimal volume data audible for the sound of different frequency that this, which listens force parameter,；
Receive a speech message of user sending；
The speech message is sent to a voice service server；
The original answer speech message from the voice service server is received, wherein the original answer speech message is the language
Sound service server searches acquirement according to the speech message；
Force parameter is listened according to this, adjusts the original sound frequency for replying speech message, replies speech message to generate one；And
Export the answer speech message.
11. method as claimed in claim 10, which is characterized in that user's hearing evaluation data include an age data
An and/or gender data.
12. a kind of computer-readable memory media of internally stored program, which is characterized in that, can after computer loads the program
Complete such as the described in any item methods of claim 7 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710320114.8A CN108877822A (en) | 2017-05-09 | 2017-05-09 | Intelligent voice system, the method for voice output adjustment and computer-readable memory media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710320114.8A CN108877822A (en) | 2017-05-09 | 2017-05-09 | Intelligent voice system, the method for voice output adjustment and computer-readable memory media |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108877822A true CN108877822A (en) | 2018-11-23 |
Family
ID=64287210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710320114.8A Pending CN108877822A (en) | 2017-05-09 | 2017-05-09 | Intelligent voice system, the method for voice output adjustment and computer-readable memory media |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108877822A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459212A (en) * | 2019-06-05 | 2019-11-15 | 西安易朴通讯技术有限公司 | Method for controlling volume and equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008008730A2 (en) * | 2006-07-08 | 2008-01-17 | Personics Holdings Inc. | Personal audio assistant device and method |
| CN103177750A (en) * | 2011-12-20 | 2013-06-26 | 富泰华工业（深圳）有限公司 | Audio playing device and control method thereof |
| CN103516854A (en) * | 2012-06-15 | 2014-01-15 | 三星电子株式会社 | Terminal apparatus and control method thereof |
| CN104104780A (en) * | 2013-04-08 | 2014-10-15 | 杨国屏 | Telephone voice output method, and computer program product and electronic device using same |
| CN104160443A (en) * | 2012-11-20 | 2014-11-19 | 统一有限责任两合公司 | Method, device, and system for audio data processing |
| CN106228978A (en) * | 2016-08-04 | 2016-12-14 | 成都佳荣科技有限公司 | A kind of audio recognition method |
| CN106598535A (en) * | 2016-11-01 | 2017-04-26 | 乐视控股（北京）有限公司 | Volume adjustment method and apparatus |
-
2017
- 2017-05-09 CN CN201710320114.8A patent/CN108877822A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008008730A2 (en) * | 2006-07-08 | 2008-01-17 | Personics Holdings Inc. | Personal audio assistant device and method |
| CN103177750A (en) * | 2011-12-20 | 2013-06-26 | 富泰华工业（深圳）有限公司 | Audio playing device and control method thereof |
| CN103516854A (en) * | 2012-06-15 | 2014-01-15 | 三星电子株式会社 | Terminal apparatus and control method thereof |
| CN104160443A (en) * | 2012-11-20 | 2014-11-19 | 统一有限责任两合公司 | Method, device, and system for audio data processing |
| CN104104780A (en) * | 2013-04-08 | 2014-10-15 | 杨国屏 | Telephone voice output method, and computer program product and electronic device using same |
| CN106228978A (en) * | 2016-08-04 | 2016-12-14 | 成都佳荣科技有限公司 | A kind of audio recognition method |
| CN106598535A (en) * | 2016-11-01 | 2017-04-26 | 乐视控股（北京）有限公司 | Volume adjustment method and apparatus |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459212A (en) * | 2019-06-05 | 2019-11-15 | 西安易朴通讯技术有限公司 | Method for controlling volume and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1168297B1 (en) | Speech synthesis | |
| TWI689865B (en) | Smart voice system, method of adjusting output voice and computre readable memory medium | |
| CN103546503B (en) | Voice-based cloud social intercourse system, method and cloud analysis server | |
| CN109903773B (en) | Audio processing method, device and storage medium | |
| CN108028044A (en) | The speech recognition system of delay is reduced using multiple identifiers | |
| CN108922528B (en) | Method and apparatus for processing speech | |
| CN107705782B (en) | Method and device for determining phoneme pronunciation duration | |
| WO2016101571A1 (en) | Voice translation method, communication method and related device | |
| CN106415541A (en) | Techniques for real-time translation of a media feed from a speaker computing device and distribution to multiple listener computing devices in multiple different languages | |
| CN109587657A (en) | A kind of method of speech processing and device based on bluetooth interpreting equipment | |
| CN106534484A (en) | Method and apparatus for adjusting the volume of mobile equipment | |
| CN102257566A (en) | Method and system for adapting communications | |
| CN106297839A (en) | A kind of audio-frequence player device | |
| CN109002274A (en) | The method of the electronic device and adjustment output sound of adjustable output sound | |
| CN106708741B (en) | The test method and system of voice application | |
| CN112349266B (en) | Voice editing method and related equipment | |
| CN115098633A (en) | Intelligent customer service emotion analysis method and system, electronic equipment and storage medium | |
| CN108877822A (en) | Intelligent voice system, the method for voice output adjustment and computer-readable memory media | |
| CN107331399A (en) | Learning effect detection method and system and terminal equipment | |
| CN104317404A (en) | Voice-print-control audio playing equipment, control system and method | |
| CN113299309A (en) | Voice translation method and device, computer readable medium and electronic equipment | |
| CN115004297A (en) | Traffic management device and method | |
| US10841713B2 (en) | Integration of audiogram data into a device | |
| CN104348436B (en) | A kind of parameter regulation means and electronic equipment | |
| CN113808566B (en) | Vibration noise processing method and device, electronic equipment and storage medium |
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: 20201028 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: 20181123 |
|
| WD01 | Invention patent application deemed withdrawn after publication |