CN107094196A - A kind of method and mobile terminal of de-noising of conversing - Google Patents
A kind of method and mobile terminal of de-noising of conversing Download PDFInfo
- Publication number
- CN107094196A CN107094196A CN201710266250.3A CN201710266250A CN107094196A CN 107094196 A CN107094196 A CN 107094196A CN 201710266250 A CN201710266250 A CN 201710266250A CN 107094196 A CN107094196 A CN 107094196A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- mobile terminal
- voiceprint
- signal
- default
- 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 abstract description 58
- 230000006854 communication Effects 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 46
- 230000008569 process Effects 0.000 claims abstract description 26
- 239000000284 extract Substances 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims description 14
- 230000001755 vocal effect Effects 0.000 claims description 12
- 230000005236 sound signal Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 238000004549 pulsed laser deposition Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 210000000867 larynx Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 210000003928 nasal cavity Anatomy 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 210000002105 tongue Anatomy 0.000 description 1
- 210000000515 tooth Anatomy 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/02—Constructional features of telephone sets
- H04M1/19—Arrangements of transmitters, receivers, or complete sets to prevent eavesdropping, to attenuate local noise or to prevent undesired transmission; Mouthpieces or receivers specially adapted therefor
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
- G10L21/028—Voice signal separating using properties of sound source
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present invention provides a kind of method and mobile terminal of de-noising of conversing, and this method includes：In the communication process of the mobile terminal, the first voice signal is obtained；Extract the voiceprint of first voice signal；Judge to whether there is default voiceprint in the voiceprint of first voice signal；If there is default voiceprint in the voiceprint of first voice signal, according to the default voiceprint, treat process signal and carry out denoising Processing, wherein, during the pending signal is first voice signal, the signal in addition to the corresponding signal of the default voiceprint.The method for the call de-noising that the present invention is provided, in the communication process of mobile terminal, denoising Processing can be carried out to the signal outside the corresponding signal of default voiceprint in voice signal, denoising Processing is carried out to noise signal and other people voice signal etc. so as to realize, improve speech quality.
Description
Technical field
The present invention relates to communication technical field, more particularly to a kind of method and mobile terminal of de-noising of conversing.
Background technology
With the development of mobile communication technology, the mobile terminal such as mobile phone and tablet personal computer is becoming increasingly popular, and user can be with
Pass through CS (Circuit Switched, the circuit switching) calls of mobile terminal, VoIP (Voice over Internet
Protocol, ip voice), VoLTE (Voice over LTE, LTE voice), ViLTE (Video over LTE, LTE video)
And the communication mode such as the networking telephone, conversed with other people.In user is conversed using mobile terminal and peer user,
It may produce call due to the noise of oneself or peer user surrounding environment and be interfered.
At present, in order to improve speech quality, mobile terminal is handled voice signal usually using denoising algorithm.But
Because existing denoising algorithm is when handling noise, the voice signal of user or peer user may be mistaken for noise letter
Number, and voice signal is subjected to denoising Processing, cause to exist in communication process sound discontinuously or interrupt, so as to reduce call
Quality.It can be seen that, it is current in the communication process of mobile terminal, there is the problem of speech quality is low.
The content of the invention
The embodiment of the present invention provides a kind of method and mobile terminal of de-noising of conversing, current in mobile terminal to solve
In communication process, there is the problem of speech quality is low.
In a first aspect, the embodiments of the invention provide a kind of method for de-noising of conversing, applied to mobile terminal, including：
In the communication process of the mobile terminal, the first voice signal is obtained；
Extract the voiceprint of first voice signal；
Judge to whether there is default voiceprint in the voiceprint of first voice signal；
If there is the default voiceprint in the voiceprint of first voice signal, according to the default sound
Line information, treat process signal carry out denoising Processing, wherein, the pending signal be first voice signal in, except institute
State the signal outside the corresponding signal of default voiceprint.
Second aspect, the embodiment of the present invention also provides mobile terminal, including：
First acquisition module, in the communication process of the mobile terminal, obtaining the first voice signal；
First extraction module, the voiceprint for extracting first voice signal；
It whether there is default voiceprint in judge module, the voiceprint for judging first voice signal；
Processing module, if there is default voiceprint in voiceprint for first voice signal, according to institute
Default voiceprint is stated, process signal is treated and carries out denoising Processing, wherein, the pending signal is believed for first sound
In number, the signal in addition to the corresponding signal of the default voiceprint.
In the embodiment of the present invention, in the communication process of the mobile terminal, the first voice signal is obtained；Extract described
The voiceprint of one voice signal；Judge to whether there is default voiceprint in the voiceprint of first voice signal；
If there is the default voiceprint in the voiceprint of first voice signal, according to the default voiceprint,
Treat process signal carry out denoising Processing, wherein, the pending signal be first voice signal in, except described default
Signal outside the corresponding signal of voiceprint.So, can be to being preset in voice signal in the communication process of mobile terminal
The corresponding signal of voiceprint outside signal carry out denoising Processing, so as to realize to noise signal and other people voice
Signal etc. carries out denoising Processing, improves speech quality.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed for description of the embodiment of the present invention
The accompanying drawing to be used is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention,
For those of ordinary skill in the art, without having to pay creative labor, it can also be obtained according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of the method for de-noising of conversing provided in an embodiment of the present invention；
Fig. 2 is the schematic flow sheet of the method for another call de-noising provided in an embodiment of the present invention；
Fig. 3 is a kind of structural representation of mobile terminal provided in an embodiment of the present invention；
Fig. 4 is the structural representation of another mobile terminal provided in an embodiment of the present invention；
Fig. 5 is the structural representation of another mobile terminal provided in an embodiment of the present invention；
Fig. 6 is a kind of structural representation of the 3rd extraction module of mobile terminal provided in an embodiment of the present invention；
Fig. 7 is the structural representation of another mobile terminal provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is a part of embodiment of the invention, rather than whole embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
Referring to Fig. 1, Fig. 1 is a kind of schematic flow sheet of the method for de-noising of conversing provided in an embodiment of the present invention, such as Fig. 1 institutes
Show, this method comprises the following steps：
Step 101, in the communication process of mobile terminal, obtain the first voice signal.
In the embodiment of the present invention, above-mentioned first voice signal is the sound that mobile terminal is obtained in current communication process
Signal.Wherein, the first voice signal can include the voice signal and voice letter that the speech reception module of mobile terminal is received
Noise signal beyond number, or the voice letter that terminal corresponding with mobile terminal reception target contact number is sent can be included
Number and the voice signal beyond noise signal, or can also simultaneously including mobile terminal speech reception module receive
Voice signal, mobile terminal receive voice signal and mobile terminal side and the target that the corresponding terminal of target contact number is sent
The noise signal of the corresponding end side of contact number.
It should be noted that above-mentioned speech reception module can be disposed in mobile terminal, user's input can be received
Voice or other sound any structure, for example：It can be microphone, herein and be not construed as limiting.
Step 102, the voiceprint for extracting the first voice signal.
In the embodiment of the present invention, mobile terminal can be to extracting voiceprint from the first voice signal, first sound
The voiceprint of signal includes the voiceprint in the voice signal that the dynamic terminal of at least one people's sounding time shift is received.
For example：First voice signal includes voice signal, other people voice signal and the week of the user of the mobile terminal
During the noise signal in collarette border, mobile terminal can parse each voice signal, so that by the voice signal of user with other people
The voiceprint extracted in voice signal as the first voice signal voiceprint.
Wherein, vocal print is the sound wave spectrum for the carrying verbal information that electricity consumption acoustic instrument is shown.The generation of human language is
A complicated physiology physical process between Body Languages maincenter and vocal organs, the phonatory organ that people uses in speech-
Tongue, tooth, larynx, lung, nasal cavity everyone widely different in terms of size and form, so everyone has oneself unique
Voiceprint.
Step 103, judge to whether there is default voiceprint in the voiceprint of the first voice signal.
In the embodiment of the present invention, above-mentioned default voiceprint can be the vocal print letter being pre-set in mobile terminal
Breath or the voiceprint that is determined by mobile terminal, and its be only a people voice signal voiceprint.For example：
Default voiceprint can be the sound that mobile terminal is extracted from the voice signal for obtaining user or terminal user first in advance
Line information.
Wherein, due to above-mentioned first voice signal voiceprint be at least one people's sounding when voice signal extract
Arrive, mobile terminal, which may determine that in the voiceprint of the first voice signal, whether there is default voiceprint, so that it is determined that being
No progress next step 104.
If there is default voiceprint in step 104, the voiceprint of the first voice signal, believed according to default vocal print
Breath, treat process signal carry out denoising Processing, wherein, pending signal be the first voice signal in, except the default vocal print
Signal outside the corresponding signal of information.
In the embodiment of the present invention, the corresponding signal of above-mentioned default voiceprint can be understood as using in the first voice signal
Family or the voice signal of terminal user；Above-mentioned pending signal can be understood as user or terminal in the first voice signal and use
Signal outside the voice signal at family, including the noise of surrounding environment and user or the corresponding end side of target contact number
User beyond other people voice signal etc..
Wherein, above-mentioned according to default voiceprint, it can treat process signal to enter to treat process signal and carry out de-noising
Row decay；It can also be that the pending signal in the first voice signal is completely eliminated, only retain the default voiceprint
Corresponding voice signal.
For example：First voice signal is made up of voice signal and environmental noise signal, and voice signal is by the voice of user
Signal and other people voice signal composition, and the corresponding voice signal of default voiceprint is the voice signal of user,
The signal that then pending signal constitutes for other people voice signal and environmental noise signal, mobile terminal can will be pending
In signal attenuation to preset range.
In addition, it is necessary to explanation, if default voiceprint is not present in the voiceprint of above-mentioned first voice signal,
Mobile terminal, can be without any processing for the first voice signal.
In the embodiment of the present invention, above-mentioned mobile terminal can any can carry out the mobile terminal of voice call, example
Such as：Mobile phone, tablet personal computer (Tablet Personal Computer), laptop computer (Laptop Computer), individual number
Word assistant (personal digital assistant, abbreviation PDA), mobile Internet access device (Mobile Internet
Device, MID) or wearable device (Wearable Device) etc..
The method of the call de-noising of the embodiment of the present invention, in the communication process of mobile terminal, obtains the first voice signal；
Extract the voiceprint of the first voice signal of the first voice signal；It whether there is in the voiceprint for judging the first voice signal
Default voiceprint；If there is default voiceprint in the voiceprint of the first voice signal, believed according to default vocal print
Breath, treat process signal carry out denoising Processing, wherein, pending signal be the first voice signal in, except default voiceprint
Signal outside corresponding signal.So, in the communication process of mobile terminal, default vocal print in voice signal can be believed
Cease the signal outside corresponding signal and carry out denoising Processing, noise signal and other people voice signal etc. are entered so as to realize
Row denoising Processing, improves speech quality.
Referring to Fig. 2, Fig. 2 is a kind of schematic flow sheet of the method for de-noising of conversing provided in an embodiment of the present invention, such as Fig. 2 institutes
Show, the present embodiment and the main distinction of embodiment in Fig. 1 are：The step of process signal carries out denoising Processing is treated, including：It is right
Pending signal carries out attenuation processing.This method comprises the following steps：
Step 201, in the communication process of mobile terminal, obtain the first voice signal.
In the embodiment of the present invention, above-mentioned first voice signal is the sound that mobile terminal is obtained in current communication process
Signal, the voice signal can be that the voice signal or mobile terminal of acquisition for mobile terminal mobile terminal side receive mesh
Mark the voice signal for the end side that the corresponding terminal of contact number is sent.
Optionally, it is above-mentioned in the communication process of the mobile terminal, before the step of obtaining the first voice signal, may be used also
With including：
Obtain the second sound signal that the speech reception module of mobile terminal is received；
It regard the voiceprint in second sound signal as default voiceprint；
It is above-mentioned in the communication process of the mobile terminal, obtain the first voice signal the step of, including：
In the communication process of the mobile terminal, the speech reception module of the mobile terminal is received into voice signal
It is used as first voice signal.
In the embodiment, mobile terminal is opened in its user after de-noising function, and its user can be guided to pass through voice
Receiving module typing voice, for example：Can be that user reads aloud passage or sings song etc.；Mobile terminal can be obtained
Voice signal during its user's typing voice, and the voiceprint of the voice signal is extracted, it is used as the default vocal print of the user
Information.
Wherein, when the user is conversed using mobile terminal, the of the input of acquisition for mobile terminal speech reception module
One voice signal, first voice signal can include voice signal, other people voice signal and the surrounding environment of its user
Middle noise signal etc..If there is the voice signal of default voiceprint, i.e. user in the first voice signal, mobile terminal can be with
Signal of first voice signal in addition to the voice signal of the user is subjected to attenuation processing, i.e., by other people voice signal and
Noise signal etc. carries out attenuation processing, so that mobile terminal sends into terminal voice signal and is relatively enhanced, can avoid
The voice signal of the user of mobile terminal is interfered, and improves speech quality.
Optionally, it is above-mentioned in the communication process of the mobile terminal, before the step of obtaining the first voice signal, may be used also
With including：
In the user of memory mobile terminal and target contact number history communication process, the 3rd voice signal received,
Wherein, the 3rd voice signal is the voice signal that the corresponding terminal of target contact number is sent；
Determine reference voice signal, and extract the voiceprint of reference voice signal as default voiceprint, wherein,
Reference voice signal is one the 3rd voice signal that stores in mobile terminal；
In the communication process of mobile terminal, the step of obtaining the first voice signal, including：
In the communication process of mobile terminal, what the corresponding terminal of target contact number that mobile terminal is received was sent
Voice signal, is used as the first voice signal.
In the embodiment, above-mentioned target contact number can be a preassigned contact number, example in mobile terminal
Such as：Talk times are more than a contact number of certain threshold value during mobile terminal will can be conversed with its history, are contacted as target
Number.
Wherein, in the history call of mobile terminal and the target contact number, when mobile terminal can be by conversing every time
The voice signal sent by the corresponding terminal of the target contact number is that the 3rd voice signal is stored, and according to preset rules
The 3rd voice signal is selected from the 3rd voice signal of storage as reference voice signal, so as to extract reference voice letter
Voiceprint in number is used as default voiceprint.For example：Mobile terminal will can be conversed with the target contact number last time
When the 3rd voice signal be used as reference voice signal；Or mobile terminal selects one from the 3rd voice signal of storage at random
Secondary 3rd voice signal is used as reference voice signal.
In addition, doing in order to avoid other people voice signal in addition to the corresponding contact person of the target contact number
Disturb, the 3rd voice signal during mobile terminal can be conversed history is parsed, will only include the 3rd of a voice signal
Voice signal is stored；Or mobile terminal is parsed to reference voice signal, if having in reference voice signal multiple
Voice signal, mobile terminal extracts the voiceprint of the voice signal in multiple voice signals with peak swing as default
Voiceprint, so as to avoid the corresponding voice signal of default voiceprint from there is other people voice signal, it is ensured that move
The speech quality of dynamic terminal.
Mobile terminal can will receive the sound letter that the corresponding terminal of target contact number is sent in this communication process
Number as the first voice signal, so that with the presence or absence of target contact number correspondence in comparing the voiceprint of the first voice signal
Default voiceprint, if in the first voice signal exist the default voiceprint, carry out denoising Processing, so as to reality
Denoising Processing now is carried out to the voice signal that the corresponding terminal of target contact number is sent, the call of mobile terminal is further improved
Quality.
It is further alternative, above-mentioned determination reference voice signal, and extract the voiceprint of the reference voice signal and be
The step of default voiceprint, it can include：
The short-time average energy of voice signal in the 3rd voice signal respectively stored；
Determine that voice signal has the 3rd voice signal of maximum short-time average energy as reference voice signal；
The voiceprint of the reference voice signal is extracted as default voiceprint.
Wherein, mobile terminal can carry out feature extraction to the voice signal parsed from the 3rd voice signal, extract
Go out the short-time average energy of voice signal in the 3rd voice signal, and voice signal in the 3rd voice signal respectively stored
Short-time average energy, wherein one time voice signal of selection has the 3rd voice signal of maximum short-time average energy as referring to sound
Message number, and extract the voiceprint of reference voice signal as default voiceprint, so as to that voice signal is strong
The voiceprint of 3rd voice signal further improves the speech quality of mobile terminal as with reference to default.
Step 202, the voiceprint for extracting the first voice signal.
Step 203, judge to whether there is default voiceprint in the voiceprint of the first voice signal.
In the embodiment of the present invention, if the speech reception module that the first voice signal is mobile terminal in this communication process connects
Voice signal is received, the default voiceprint that mobile terminal selects above-mentioned second sound signal to extract is compared；If this
In secondary communication process, mobile terminal is received in the voice signal that the corresponding terminal of target contact number is sent, mobile terminal selection
The default voiceprint for stating the extraction of the 3rd voice signal is compared, and is no longer repeated herein.
If there is default voiceprint in step 204, the voiceprint of the first voice signal, believed according to default vocal print
Breath, treat process signal carry out attenuation processing, wherein, pending signal be the first voice signal in, except default voiceprint
Signal outside corresponding signal.
The method of the call de-noising of the embodiment of the present invention, to removing the corresponding letter of default voiceprint in the first voice signal
Other signals outside number are decayed, and can extremely close the noise signal in voice signal and other people voice signal de-noising
In suitable scope, so that it is guaranteed that the sound of mobile terminal output is undistorted, the call in mobile terminal calling process is further improved
Quality.
Referring to Fig. 3, Fig. 3 a kind of structural representations of mobile terminal provided in an embodiment of the present invention, as shown in figure 3, above-mentioned
Mobile terminal 300 includes：
First acquisition module 301, in the communication process of mobile terminal, obtaining the first voice signal；
First extraction module 302, the voiceprint for extracting the first voice signal；
It whether there is default voiceprint in judge module 303, the voiceprint for judging the first voice signal；
Processing module 304, if there is default voiceprint in voiceprint for the first voice signal, according to default
Voiceprint, treat process signal carry out denoising Processing, wherein, pending signal be the first voice signal in, except default
Signal outside the corresponding signal of voiceprint.
Optionally, above-mentioned processing module 304 can be also used for treating process signal progress attenuation processing.
Optionally, as shown in figure 4, above-mentioned mobile terminal 300 can also include：
Second acquisition module 305, for obtaining the second sound signal that the speech reception module of mobile terminal is received；
Second extraction module 306, for extracting the voiceprint in second sound signal as default voiceprint；
First acquisition module 301 is additionally operable in the communication process of mobile terminal, by the speech reception module of mobile terminal
Voice signal is received as the first voice signal.
Optionally, as shown in figure 5, above-mentioned mobile terminal 300 can also include：
Memory module 307, the user for memory mobile terminal is with target contact number history communication process, receiving
The 3rd voice signal, wherein, the 3rd voice signal is the voice signal that the corresponding terminal of target contact number is sent；
3rd extraction module 308, for determining reference voice signal, and extracts the voiceprint conduct of reference voice signal
Default voiceprint, wherein, reference voice signal is one the 3rd voice signal that stores in mobile terminal；
First acquisition module 301 is additionally operable in the communication process of mobile terminal, and the target that mobile terminal is received joins
It is the voice signal that the corresponding terminal of number is sent, is used as the first voice signal.
Optionally, as shown in fig. 6, above-mentioned 3rd extraction module 308 can include：
Comparing unit 3081, the short-time average energy for voice signal in the 3rd voice signal that respectively stores；
Determining unit 3082, for determining that voice signal has the 3rd voice signal conduct of maximum short-time average energy
Reference voice signal；
Extraction unit 3083, for extracting the voiceprint of reference voice signal as default voiceprint.
Mobile terminal 300 can realize each process that mobile terminal is realized in Fig. 1 and Fig. 2 embodiment, to avoid weight
It is multiple, repeat no more here.
Mobile terminal 300 provided in an embodiment of the present invention, in the communication process of mobile terminal, obtains the first sound letter
Number；Extract the voiceprint of the first voice signal；Judge to whether there is default vocal print in the voiceprint of the first voice signal
Information；If there is default voiceprint in the voiceprint of the first voice signal, according to default voiceprint, to pending
Signal carry out denoising Processing, wherein, pending signal be the first voice signal in, except the corresponding signal of default voiceprint it
Outer signal.So, can be to the corresponding signal of default voiceprint in voice signal in the communication process of mobile terminal
Outside signal carry out denoising Processing, so as to realize to noise signal and other people voice signal etc. carry out denoising Processing,
Improve speech quality.
Referring to Fig. 7, Fig. 7 is a kind of structural representation for mobile terminal that the present invention implements offer, as shown in fig. 7, mobile
Terminal 700 includes：At least one processor 701, memory 702, at least one network interface 704 and user interface 703.It is mobile
Each component in terminal 700 is coupled by bus system 705.It is understood that bus system 705 is used to realize these groups
Connection communication between part.Bus system 705 is in addition to including data/address bus, in addition to power bus, controlling bus and state
Signal bus.But for the sake of clear explanation, various buses are all designated as bus system 705 in the figure 7.
Wherein, user interface 703 can include display, keyboard or pointing device (for example, mouse, trace ball
(trackball), touch-sensitive plate or touch-screen etc..
It is appreciated that the memory 702 in the embodiment of the present invention can be volatile memory or nonvolatile memory,
Or may include both volatibility and nonvolatile memory.Wherein, nonvolatile memory can be read-only storage (Read-
Only Memory, ROM), programmable read only memory (Programmable ROM, PROM), the read-only storage of erasable programmable
Device (Erasable PROM, EPROM), Electrically Erasable Read Only Memory (Electrically EPROM, EEPROM) or
Flash memory.Volatile memory can be random access memory (Random Access Memory, RAM), and it is used as outside high
Speed caching.By exemplary but be not restricted explanation, the RAM of many forms can use, such as static RAM
(Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), Synchronous Dynamic Random Access Memory
(Synchronous DRAM, SDRAM), double data speed synchronous dynamic RAM (Double Data Rate
SDRAM, DDRSDRAM), enhanced Synchronous Dynamic Random Access Memory (Enhanced SDRAM, ESDRAM), synchronized links
Dynamic random access memory (Synch Link DRAM, SLDRAM) and direct rambus random access memory (Direct
Rambus RAM, DRRAM).The memory 702 of system and method described herein be intended to including but not limited to these and it is any its
It is adapted to the memory of type.
In some embodiments, memory 702 stores following display content, can perform module or data knot
Structure, either their subset or their superset：Operating system 7021 and application program 7022.
Wherein, operating system 7021, comprising various system programs, such as ccf layer, core library layer, driving layer, are used for
Realize various basic businesses and handle hardware based task.Application program 7022, includes various application programs, such as media
Player (Media Player), browser (Browser) etc., for realizing various applied business.Realize the embodiment of the present invention
The program of method may be embodied in application program 7022.
In embodiments of the present invention, by calling program or the instruction of the storage of memory 702, specifically, can be application
The program stored in program 7022 or instruction, processor 701 are used for：In the communication process of mobile terminal, the first sound is obtained
Signal；Extract the voiceprint of the first voice signal；Judge to whether there is default sound in the voiceprint of the first voice signal
Line information；If there is default voiceprint in the voiceprint of the first voice signal, according to default voiceprint, place is treated
Manage signal carry out denoising Processing, wherein, pending signal be the first voice signal in, except the corresponding signal of default voiceprint
Outside signal.
The method that the embodiments of the present invention are disclosed can apply in processor 701, or be realized by processor 701.
Processor 701 is probably a kind of IC chip, the disposal ability with signal.In implementation process, the above method it is each
Step can be completed by the integrated logic circuit of the hardware in processor 701 or the instruction of software form.Above-mentioned processing
Device 701 can be general processor, digital signal processor (Digital Signal Processor, DSP), special integrated electricity
Road (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field
Programmable Gate Array, FPGA) or other PLDs, discrete gate or transistor logic,
Discrete hardware components.It can realize or perform disclosed each method, step and the logic diagram in the embodiment of the present invention.It is general
Processor can be microprocessor or the processor can also be any conventional processor etc..With reference to institute of the embodiment of the present invention
The step of disclosed method, can be embodied directly in hardware decoding processor and perform completion, or with the hardware in decoding processor
And software module combination performs completion.Software module can be located at random access memory, and flash memory, read-only storage may be programmed read-only
In the ripe storage medium in this area such as memory or electrically erasable programmable memory, register.The storage medium is located at
Memory 702, processor 701 reads the information in memory 702, the step of completing the above method with reference to its hardware.
It is understood that embodiments described herein can with hardware, software, firmware, middleware, microcode or its
Combine to realize.Realized for hardware, processing unit can be realized in one or more application specific integrated circuit (Application
Specific Integrated Circuits, ASIC), digital signal processor (Digital Signal Processing,
DSP), digital signal processing appts (DSP Device, DSPD), programmable logic device (Programmable Logic
Device, PLD), field programmable gate array (Field-Programmable Gate Array, FPGA), general processor,
In controller, microcontroller, microprocessor, other electronic units for performing herein described function or its combination.
Realize, can be realized by performing the module (such as process, function) of function described herein herein for software
Described technology.Software code is storable in memory and by computing device.Memory can within a processor or
Realized outside processor.
Optionally, processor 701 perform it is above-mentioned treat process signal carry out denoising Processing the step of, including：
Treat process signal and carry out attenuation processing.
Optionally, processor 701 performs above-mentioned in the communication process of the mobile terminal, obtains the first voice signal
Before step, in addition to：
Obtain the second sound signal that the speech reception module of mobile terminal is received；
The voiceprint extracted in second sound signal is used as default voiceprint；
It is above-mentioned in the communication process of mobile terminal, obtain the first voice signal the step of, including：
In the communication process of mobile terminal, the speech reception module of mobile terminal is received into voice signal as first
Voice signal.
Optionally, processor 701 performs above-mentioned in the communication process of the mobile terminal, obtains the first voice signal
Before step, in addition to：
In the user of memory mobile terminal and target contact number history communication process, the 3rd voice signal received,
Wherein, the 3rd voice signal is the voice signal that the corresponding terminal of target contact number is sent；
Determine reference voice signal, and extract the voiceprint of reference voice signal as default voiceprint, wherein,
Reference voice signal is one the 3rd voice signal that stores in mobile terminal；
It is above-mentioned in the communication process of mobile terminal, obtain the first voice signal the step of, including：
In the communication process of mobile terminal, what the corresponding terminal of target contact number that mobile terminal is received was sent
Voice signal, is used as the first voice signal.
Optionally, processor 701 performs above-mentioned determination reference voice signal, and extracts the voiceprint of reference voice signal
The step of for default voiceprint, including：
The short-time average energy of voice signal in the 3rd voice signal respectively stored；
Determine that voice signal has the 3rd voice signal of maximum short-time average energy as reference voice signal；
The voiceprint for extracting reference voice signal is used as default voiceprint.
Mobile terminal 700 can realize each process that mobile terminal is realized in previous embodiment, to avoid repeating, here
Repeat no more.
The mobile terminal 700 of the embodiment of the present invention, in the communication process of mobile terminal, obtains the first voice signal；Carry
Take the voiceprint of the first voice signal；Judge to whether there is default voiceprint in the voiceprint of the first voice signal；
If there is default voiceprint in the voiceprint of the first voice signal, according to default voiceprint, process signal is treated
Carry out denoising Processing, wherein, pending signal be the first voice signal in, in addition to the corresponding signal of default voiceprint
Signal.So, in the communication process of mobile terminal, can be to the corresponding signal of default voiceprint in voice signal outside
Signal carry out denoising Processing, so as to realize to noise signal and other people voice signal etc. carry out denoising Processing, improve
Speech quality.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, depending on the application-specific and design constraint of technical scheme.Professional and technical personnel
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the present invention.
It is apparent to those skilled in the art that, for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In embodiment provided herein, it should be understood that disclosed apparatus and method, others can be passed through
Mode is realized.For example, device embodiment described above is only schematical, for example, the division of the unit, is only
A kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored, or does not perform.Another, shown or discussed is mutual
Between coupling or direct-coupling or communication connection can be the INDIRECT COUPLING or communication link of device or unit by some interfaces
Connect, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize scheme of the embodiment of the present invention according to the actual needs
Purpose.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.
If the function is realized using in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Understood based on such, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are to cause a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each of the invention embodiment methods described.
And foregoing storage medium includes：USB flash disk, mobile hard disk, ROM, RAM, magnetic disc or CD etc. are various can be with store program codes
Medium.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be defined by scope of the claims.
Claims (10)
1. a kind of method for de-noising of conversing, applied to mobile terminal, it is characterised in that including：
In the communication process of the mobile terminal, the first voice signal is obtained；
Extract the voiceprint of first voice signal；
Judge to whether there is default voiceprint in the voiceprint of first voice signal；
If there is the default voiceprint in the voiceprint of first voice signal, believed according to the default vocal print
Breath, treat process signal carry out denoising Processing, wherein, the pending signal be first voice signal in, except described pre-
If the corresponding signal of voiceprint outside signal.
2. the method for call de-noising according to claim 1, it is characterised in that the process signal for the treatment of is carried out at de-noising
The step of reason, including：
Attenuation processing is carried out to the pending signal.
3. the method for call de-noising according to claim 1 or 2, it is characterised in that described in the logical of the mobile terminal
During words, before the step of obtaining the first voice signal, in addition to：
Obtain the second sound signal that the speech reception module of the mobile terminal is received；
The voiceprint in the second sound signal is extracted as the default voiceprint；
It is described in the communication process of the mobile terminal, obtain the first voice signal the step of, including：
In the communication process of the mobile terminal, the speech reception module of the mobile terminal is received voice signal as
First voice signal.
4. the method for call de-noising according to claim 1 or 2, it is characterised in that described in the logical of the mobile terminal
During words, before the step of obtaining the first voice signal, in addition to：
Store in the mobile terminal and target contact number history communication process, the 3rd voice signal received, wherein, institute
State the voice signal that the 3rd voice signal sends for the corresponding terminal of the target contact number；
Determine reference voice signal, and extract the voiceprint of the reference voice signal as the default voiceprint,
Wherein, the reference voice signal be the mobile terminal in store one described in the 3rd voice signal；
It is described in the communication process of the mobile terminal, obtain the first voice signal the step of, including：
In the communication process of the mobile terminal, the target contact number corresponding end that the mobile terminal is received
The voice signal sent is held, first voice signal is used as.
5. the method for call de-noising according to claim 4, it is characterised in that the determination reference voice signal, and carry
The step of voiceprint for taking the reference voice signal is the default voiceprint, including：
The short-time average energy of voice signal in the 3rd voice signal respectively stored；
Determine that voice signal has the 3rd voice signal of maximum short-time average energy as the reference voice signal；
The voiceprint of the reference voice signal is extracted as the default voiceprint.
6. a kind of mobile terminal, it is characterised in that including：
First acquisition module, in the communication process of the mobile terminal, obtaining the first voice signal；
First extraction module, the voiceprint for extracting first voice signal；
It whether there is default voiceprint in judge module, the voiceprint for judging first voice signal；
Processing module, if there is the default voiceprint in voiceprint for first voice signal, according to institute
Default voiceprint is stated, process signal is treated and carries out denoising Processing, wherein, the pending signal is believed for first sound
In number, the signal in addition to the corresponding signal of the default voiceprint.
7. mobile terminal according to claim 6, it is characterised in that the processing module is additionally operable to the pending letter
Number carry out attenuation processing.
8. the mobile terminal according to claim 6 or 7, it is characterised in that the mobile terminal also includes：
Second acquisition module, for obtaining the second sound signal that the speech reception module of the mobile terminal is received；
Second extraction module, for extracting the voiceprint in the second sound signal as the default voiceprint；
First acquisition module is additionally operable in the communication process of the mobile terminal, by the speech reception module of the mobile terminal
Voice signal is received as first voice signal.
9. the mobile terminal according to claim 6 or 7, it is characterised in that the mobile terminal also includes：
Memory module, for storing the user of the mobile terminal with target contact number history communication process, receiving
3rd voice signal, wherein, the 3rd voice signal is the voice signal that the corresponding terminal of the target contact number is sent；
3rd extraction module, for determining reference voice signal, and extracts the voiceprint of the reference voice signal as institute
State default voiceprint, wherein, the reference voice signal be the mobile terminal in store one described in the 3rd sound letter
Number；
First acquisition module is additionally operable in the communication process of the mobile terminal, the mesh that the mobile terminal is received
The voice signal that the corresponding terminal of contact number is sent is marked, first voice signal is used as.
10. mobile terminal according to claim 9, it is characterised in that the 3rd extraction module includes：
Comparing unit, the short-time average energy for voice signal in the 3rd voice signal that respectively stores；
Determining unit, for determining that voice signal has the 3rd voice signal of maximum short-time average energy as the reference
Voice signal；
Extraction unit, for extracting the voiceprint of the reference voice signal as the default voiceprint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710266250.3A CN107094196A (en) | 2017-04-21 | 2017-04-21 | A kind of method and mobile terminal of de-noising of conversing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710266250.3A CN107094196A (en) | 2017-04-21 | 2017-04-21 | A kind of method and mobile terminal of de-noising of conversing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107094196A true CN107094196A (en) | 2017-08-25 |
Family
ID=59637058
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710266250.3A Pending CN107094196A (en) | 2017-04-21 | 2017-04-21 | A kind of method and mobile terminal of de-noising of conversing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107094196A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107566658A (en) * | 2017-10-13 | 2018-01-09 | 广东欧珀移动通信有限公司 | Call method, device, storage medium and mobile terminal |
| CN107979790A (en) * | 2017-11-28 | 2018-05-01 | 上海与德科技有限公司 | One kind call noise-reduction method, device, equipment and medium |
| CN108882073A (en) * | 2018-06-19 | 2018-11-23 | 倬韵科技（深圳）有限公司 | A kind of method, apparatus, earphone and mobile terminal that the wind inhibiting microphone is made an uproar |
| CN109272996A (en) * | 2018-11-09 | 2019-01-25 | 广州长嘉电子有限公司 | A kind of noise-reduction method and system |
| CN110097872A (en) * | 2019-04-30 | 2019-08-06 | 维沃移动通信有限公司 | A kind of audio-frequency processing method and electronic equipment |
| CN110225195A (en) * | 2019-05-30 | 2019-09-10 | 维沃移动通信有限公司 | A kind of audio communication method and terminal |
| CN111565295A (en) * | 2020-04-28 | 2020-08-21 | 北京飞马拓新电子设备有限公司 | Large monitoring center console system with alarm function and control method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514884A (en) * | 2012-06-26 | 2014-01-15 | 华为终端有限公司 | Communication voice denoising method and terminal |
| CN103514876A (en) * | 2012-06-28 | 2014-01-15 | 腾讯科技（深圳）有限公司 | Method and device for eliminating noise and mobile terminal |
-
2017
- 2017-04-21 CN CN201710266250.3A patent/CN107094196A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514884A (en) * | 2012-06-26 | 2014-01-15 | 华为终端有限公司 | Communication voice denoising method and terminal |
| CN103514876A (en) * | 2012-06-28 | 2014-01-15 | 腾讯科技（深圳）有限公司 | Method and device for eliminating noise and mobile terminal |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107566658A (en) * | 2017-10-13 | 2018-01-09 | 广东欧珀移动通信有限公司 | Call method, device, storage medium and mobile terminal |
| CN107979790A (en) * | 2017-11-28 | 2018-05-01 | 上海与德科技有限公司 | One kind call noise-reduction method, device, equipment and medium |
| CN108882073A (en) * | 2018-06-19 | 2018-11-23 | 倬韵科技（深圳）有限公司 | A kind of method, apparatus, earphone and mobile terminal that the wind inhibiting microphone is made an uproar |
| CN108882073B (en) * | 2018-06-19 | 2020-08-21 | 倬韵科技（深圳）有限公司 | Method and device for inhibiting wind noise of microphone, earphone and mobile terminal |
| CN109272996A (en) * | 2018-11-09 | 2019-01-25 | 广州长嘉电子有限公司 | A kind of noise-reduction method and system |
| CN109272996B (en) * | 2018-11-09 | 2021-11-30 | 广州长嘉电子有限公司 | Noise reduction method and system |
| CN110097872A (en) * | 2019-04-30 | 2019-08-06 | 维沃移动通信有限公司 | A kind of audio-frequency processing method and electronic equipment |
| CN110225195A (en) * | 2019-05-30 | 2019-09-10 | 维沃移动通信有限公司 | A kind of audio communication method and terminal |
| CN111565295A (en) * | 2020-04-28 | 2020-08-21 | 北京飞马拓新电子设备有限公司 | Large monitoring center console system with alarm function and control method |
| CN111565295B (en) * | 2020-04-28 | 2021-06-29 | 北京飞马拓新电子设备有限公司 | Large monitoring center console system with alarm function and control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107094196A (en) | A kind of method and mobile terminal of de-noising of conversing | |
| CN110085251B (en) | Human voice extraction method, human voice extraction device and related products | |
| AU2004201992B2 (en) | Semantic object synchronous understanding implemented with speech application language tags | |
| CN109326289A (en) | Exempt to wake up voice interactive method, device, equipment and storage medium | |
| CN107910014A (en) | Test method, device and the test equipment of echo cancellor | |
| WO2024077878A1 (en) | Voice outbound call processing method and related apparatus | |
| CN111653265B (en) | Speech synthesis method, device, storage medium and electronic equipment | |
| CN107492382A (en) | Voiceprint extracting method and device based on neutral net | |
| CN110675854A (en) | Chinese and English mixed speech recognition method and device | |
| CN107393544A (en) | A kind of voice signal restoration method and mobile terminal | |
| CN109543200A (en) | A kind of text interpretation method and device | |
| CN110379414B (en) | Acoustic model enhancement training method and device, readable storage medium and computing equipment | |
| CN109147930A (en) | Divide and examines dialogue method, divides and examine conversational device and system | |
| CN114333912B (en) | Voice activation detection method, device, electronic equipment and storage medium | |
| CN106791244A (en) | Echo cancel method, device and verbal system | |
| CN107564532A (en) | Awakening method, device, equipment and the computer-readable recording medium of electronic equipment | |
| CN106782529A (en) | The wake-up selected ci poem selection method and device of speech recognition | |
| CN108595412A (en) | Correction processing method and device, computer equipment and readable medium | |
| CN107301030A (en) | A kind of method for controlling volume, device and a kind of terminal | |
| CN107622769A (en) | Number modification method and device, storage medium and electronic equipment | |
| CN112447168A (en) | Voice recognition system and method, sound box, display device and interaction platform | |
| CN110020429A (en) | Method for recognizing semantics and equipment | |
| CN204117590U (en) | Voice collecting denoising device and voice quality assessment system | |
| Han et al. | PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models | |
| CA3097683C (en) | Speech analysis system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170825 |