CN108899034A - It is a kind of with the intellectual nursing bed of voice control function - Google Patents
It is a kind of with the intellectual nursing bed of voice control function Download PDFInfo
- Publication number
- CN108899034A CN108899034A CN201810726303.XA CN201810726303A CN108899034A CN 108899034 A CN108899034 A CN 108899034A CN 201810726303 A CN201810726303 A CN 201810726303A CN 108899034 A CN108899034 A CN 108899034A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- nursing bed
- voice
- speaker
- audio
- 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.)
- Withdrawn
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G7/00—Beds specially adapted for nursing; Devices for lifting patients or disabled persons
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/06—Decision making techniques; Pattern matching strategies
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61G—TRANSPORT, PERSONAL CONVEYANCES, OR ACCOMMODATION SPECIALLY ADAPTED FOR PATIENTS OR DISABLED PERSONS; OPERATING TABLES OR CHAIRS; CHAIRS FOR DENTISTRY; FUNERAL DEVICES
- A61G2203/00—General characteristics of devices
- A61G2203/10—General characteristics of devices characterised by specific control means, e.g. for adjustment or steering
- A61G2203/18—General characteristics of devices characterised by specific control means, e.g. for adjustment or steering by patient's head, eyes, facial muscles or voice
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The invention discloses a kind of with the intellectual nursing bed of voice control function, this is intellectual nursing bed including nursing bed ontology and the voice acquisition device being arranged on nursing bed ontology, speech processing system, control instruction generation system, nursing bed control system.Voice acquisition device is used to acquire the voice signal of speaker;Speech processing system obtains the characteristic parameter of the keyword in the identity information and voice signal of speaker for analyzing the voice signal of acquisition;Control instruction generates system and is used for identity information according to the speaker of acquisition, and whether confirmation speaker is possessed of control power limit, and the limit if speaker is possessed of control power generates corresponding control instruction according to the characteristic parameter of the keyword in voice signal;Nursing bed control system controls nursing bed ontology according to control instruction and executes corresponding operation.The present invention controls nursing bed by voice control mode, can bring great convenience to user, user is facilitated easily to control nursing bed.
Description
Technical field
The present invention relates to nursing bed applied technical fields, specially a kind of with the intellectual nursing bed of voice control function.
Background technique
With getting worse for Aging Problem, the parent of especially China's first generation only child have begun successively into
Enter the senescence phase, demand of the elderly to intelligent nursing is continuously increased.The activity of usually old-age group human organism gradually weakens, long-term bed
Or be hospitalized, this not only brings physiology, psychological pain to many patients, but also returns the family members of patient and the body of nursing staff
Central band is come greatly tired out.In addition, cardiovascular and cerebrovascular disease also develops towards rejuvenation, the patient of paralysis is caused because of cerebral infarction
It is more and more, and most of them need to crouch on bed for a long time.The patient's long-term bed for losing ability to act, may cause and detest
The growth of oxygen bacterium generates bedsore, and furthermore the visual field is confined to indoor small corner for a long time, then may result in the psychology such as generation depression and ask
Topic generates very big negative effect to its rehabilitation.Therefore, nursing bed can be easily according to the instruction action of patient, and auxiliary is suffered from
Person, which obtains certain recovery and self-care ability, to be particularly important.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of with the intellectual nursing bed of voice control function.
The purpose of the present invention is realized using following technical scheme:
It is a kind of with the intellectual nursing bed of voice control function, it includes that nursing bed ontology and setting are being protected that this is intellectual nursing bed
It manages the voice acquisition device on bed ontology, speech processing system, control instruction and generates system, nursing bed control system.
Voice acquisition device, for acquiring the voice signal of speaker;Speech processing system, for the voice letter to acquisition
It number is analyzed, obtains the characteristic parameter of the keyword in the identity information and voice signal of speaker;Control instruction generates
System, for the identity information according to the speaker of acquisition, whether confirmation speaker is possessed of control power limit, controls if speaker has
Permission processed generates corresponding control instruction then according to the characteristic parameter of the keyword in voice signal;Nursing bed control system,
Corresponding operation is executed for controlling nursing bed ontology according to control instruction.
Beneficial effect:
(1) the intellectual nursing bed voice signal by acquiring speaker in the present invention, judges speaker's identity, Jin Er
Intellectual nursing bed state is controlled according to the operational order in voice signal, which avoids anyone can be to the nursing bed
It issues order, automatic shield does not have the people of control authority to carry out voice control to the nursing bed.
(2) present invention controls nursing bed by voice control mode, can bring great convenience to user, for suffering from
For person, the self-care ability of itself can be enhanced by voice, their confidence can be reinforced, reduce self-accusation and relied on, weight
Pick up the hope to life.For its nursing, care provider, then labor burden and psychological pressure are greatly reduced, is also saved
Time.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is frame construction drawing of the invention;
Fig. 2 is the frame construction drawing of audio frequency characteristics processing module of the present invention;
Fig. 3 is the frame construction drawing that audio of the present invention pre-processes submodule.
Appended drawing reference:
Nursing bed ontology 1;Voice acquisition device 2;Speech processing system 3;Control instruction generates system 4;Nursing bed control
System 5;Vocal print feature processing module 6;Audio frequency characteristics processing module 7;Audio pre-processes submodule 8;Audio feature extraction submodule
Block 9;Key word information matched sub-block 10;Audio enhancement unit 11;Audio detection unit 12;Pre-processing subelement 13;Inspection
Survey subelement 14;Update subelement 15.
Specific embodiment
In conjunction with following application scenarios, the invention will be further described.
Referring to Fig. 1, a kind of with the intellectual nursing bed of voice control function, it includes nursing bed ontology 1 that this is intellectual nursing bed
System 4 and nursing bed are generated with the voice acquisition device 2, speech processing system 3, control instruction being arranged on nursing bed ontology 1
Control system 5.Voice acquisition device 2 is used to acquire the voice signal of speaker, and speech processing system 3 is used for the voice to acquisition
Signal is analyzed, and the characteristic parameter of the keyword in the identity information and voice signal of speaker is obtained, and control instruction is raw
The identity information according to the speaker of acquisition is used at system 4, and whether confirmation speaker is possessed of control power limit, if speaker has
Control authority generates corresponding control instruction, nursing bed control system then according to the characteristic parameter of the keyword in voice signal
5 execute corresponding operation for controlling nursing bed ontology 1 according to control instruction.
Preferably, voice acquisition device 2 is microphone.
Preferably, speech processing system 3 includes vocal print feature processing module and audio frequency characteristics processing module;
Vocal print feature processing module 6, for the sound for extracting characterization speaker's identity information from the voice signal of acquisition
Line feature;
Audio frequency characteristics processing module 7, for the spy from the keyword extracted in the voice signal of acquisition in speaker's language
Levy parameter.
Preferably, it further includes a memory module that control instruction, which generates system 4, and the memory module possesses control for storing
The vocal print feature of the people of permission.
Preferably, control instruction generates the identity information for the speaker that system 4 is used for according to acquisition, and whether confirmation speaker
Be possessed of control power limit, specifically, according to the vocal print feature and storage of the speaker's identity information that vocal print feature processing module 6 obtains
The vocal print feature of the people for possessing control authority be compared, if the similarity degree of the two vocal print feature is greater than the threshold value of setting,
Then speaker is possessed of control power limit, and otherwise, then speaker does not have control authority.
Preferably, referring to fig. 2, audio frequency characteristics processing module 7 includes audio pretreatment submodule 8, audio feature extraction
Module 9 and key word information matched sub-block 10.
Audio pre-processes submodule 8, for carrying out speech enhan-cement and filtering to the voice signal of acquisition, obtains the first voice
Signal;Audio feature extraction submodule 9 is used to that keyword in speaker's language can be described from extraction in the first voice signal to believe
The characteristic parameter of breath;Key word information matched sub-block 10 is used for the key that will be prestored in the characteristic parameter and database that extract
The characteristic parameter of word is matched, and characteristic parameter to the control instruction for exporting the corresponding keyword after successful match generates system
4。
Preferably, audio pretreatment submodule 8 includes audio enhancement unit 11 and audio detection unit 12;
Audio enhancement unit 11, for carrying out speech enhan-cement processing to the voice signal of acquisition;Audio detection unit 12 is used
In carrying out denoising to enhancing treated voice signal, the first voice signal is obtained.
Preferably, speech enhan-cement processing is carried out to the voice signal of acquisition, including:
(1) voice signal of acquisition is transformed from the time domain in frequency domain using Fourier transformation;
(2) speech enhan-cement processing is carried out to the voice signal in frequency domain according to customized speech enhan-cement formula, is increased
Voice signal after strong, wherein customized speech enhan-cement formula is:
In formula,Indicate that enhanced treated voice signal, N (t, d) refer to prior weight, X (t, d) table
The voice signal in frequency domain before showing enhancing processing, p (t, d) indicate probability value existing for voice, G at t frame d frequency bandminTable
Show that minimum gain value in the state of non-speech frame, t indicate that frame number, d indicate frequency;
(3) inverse Fourier transform is used from frequency-domain transform to time domain, to obtain enhanced voice signal in time domain
Enhanced voice signal.
Beneficial effect:It is transformed in frequency domain using the voice signal that Fourier transformation will acquire and is believed to voice in frequency domain
Number carry out enhancing processing, wherein in customized speech enhan-cement formula, by introducing p (t, d), so that in non-speech frame
When, it is also considered that estimate the amplitude of clean speech, while introducing GminAlso further reduce voice distortion, while by residual error
Noise transition is white noise, allows people to sound smoother, more comfortably;The algorithm can preferably retain the main letter of voice signal
Breath, removes the ambient noise of low frequency part.
Preferably, further to obtain purer voice signal, using following formula to customized speech enhan-cement formula
In prior weight N (t, d) be modified, and by revised N (t, d) replace speech enhan-cement formula in N (t, d),
In, the calculation formula for correcting prior weight is:
In above formula,Indicate that revised prior weight, θ (t, d) indicate that posteriori SNR, ν are the tune of setting
The factor is saved, for being balanced control to noise.
When carrying out enhancing processing to voice signal, by introducing revised prior weightTo replace priori
Signal-to-noise ratio N (t, d), the way can further decrease error, improve the progress speech enhan-cement processing under low signal-to-noise ratio scene
When reinforcing effect, while to prior weightWhen being modified, noise, which was easy to appear, to be estimated and owes the case where estimating,
By introducing regulatory factor ν (usual ν choose 0.75), it is subsequent noise power spectrum is estimated when, can effectively prevent
The generation for the case where estimating is estimated and owes, so that voice distortion is minimum.
Preferably, audio detection unit 12 includes pre-processing subelement 13, detection sub-unit 14, updates subelement 15.
Enhanced voice signal is multiple sons in Time Domain Decomposition using acoustic filter group by pre-processing subelement 13
The signal of band;Detection sub-unit 14 is used to carry out energy measuring to each subband signal, estimates region existing for effective audio;More
New subelement 15 is used for the testing result according to detection sub-unit 14, is updated to the estimation of noise energy value of present frame, and
Updated estimation of noise energy value is applied in detection sub-unit 14, and then is realized to region existing for effective audio more
Newly.
In one embodiment, described that energy measuring is carried out to each subband signal, including:
(1) sub-frame processing is carried out to the signal of each subband;
(2) using energy balane formula calculate frame signal of each subband signal after sub-frame processing energy estimators and
Initial noisc energy estimators, wherein the energy balane formula of i subband is:
In formula, S (k, i, j)2It is the amplitude of k-th of sampled point in the i-th frame of j subband, LenfrFor the length of a frame signal,
Efr(i, j) is the energy estimators of the i-th frame signal, Enoise(i, j) is the initial noisc energy estimation of the i-th frame signal of j subband
Value;M is the preceding m frame signal of subband j;
(2) according to obtaining energy estimators and initial noisc energy estimators, using determine formula formula to present frame whether
It is that effective audio is determined, wherein determine that formula is:
In formula, η1And η2For threshold value weighting coefficient, for adjusting threshold size, and meet η1< η2;Work as Efr(i, j) < η1Enoise(i, j), Vcross(i, j)=0, the i-th frame is noise frame at this time, works as Efr(i, j) > η2EnoiseWhen (i, j), Vcross(i, j)
=1, the i-th frame is speech frame, in the other cases, V at this timecross(i, j) is consistent with the differentiation result of previous frame;
(3) all frames in all subbands are traversed, region existing for effective audio in each subband is obtained.
(4) union is sought into region existing for obtained effective audio, effective sound of enhanced audio signal can be obtained
Region existing for frequency.
Beneficial effect:This algorithm sets absolute threshold η by using dual threshold discriminant approach2Enoise(i, j) and protection
Threshold value η1Enoise(i, j) two decision thresholds, can be avoided a possibility that judging by accident when determining using single threshold value, the differentiation
The accuracy that mode detects is higher than single threshold value detection algorithm, can better discriminate between speech frame and noise frame.And detection
Unit is detected for each subband, which can ignore that the difference that noise energy itself is distributed in different frequency sections
Property, the noise range used is wider.
In one embodiment, the testing result according to detection sub-unit 14, to the estimation of noise energy of present frame
Value is updated, and updated estimation of noise energy value is applied in the detection sub-unit 14, and then to effective audio
Existing region is updated, and works as satisfaction | Enoise k(i, j)-Enoise k-1(i, j) | when≤σ, then stop the noise energy to the i-th frame
Amount estimated value is updated, and σ is preset constant, and k is the number of iterations, wherein is carried out to the estimation of noise energy value of present frame
Update more new formula be:
In formula, R (i, i-1) indicates the related coefficient of the estimation of noise energy value of the i-th frame and the (i-1)-th frame;R (i, i-2) table
Show the related coefficient of the estimation of noise energy value of the i-th frame and the i-th -2 frame.
Beneficial effect:It is updated by the estimation of noise energy value in real time to present frame, and then by updated noise
Energy estimators are applied among the detection sub-unit, further correct the range of effective audio region, which improves
Adaptability under different occasions, that is, improve robustness.And when the estimation of noise energy value to present frame is updated,
When determining that the i-th frame is noise frame as the result is shown, it is contemplated that the estimation of noise energy value of the (i-1)-th frame and the i-th -2 frame, and with the
The degree of correlation of i frame can more accurately be updated estimation of noise energy value.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as analysis, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of with the intellectual nursing bed of voice control function, which is characterized in that including nursing bed ontology and be arranged described
Voice acquisition device, speech processing system, control instruction on nursing bed ontology generate system, nursing bed control system;
The voice acquisition device, for acquiring the voice signal of speaker;
The speech processing system obtains the identity information and language of speaker for analyzing the voice signal of acquisition
The characteristic parameter of keyword in sound signal;
The control instruction generates system, and for the identity information according to the speaker of acquisition, whether confirmation speaker has control
Permission processed, the limit if speaker is possessed of control power generate corresponding control according to the characteristic parameter of the keyword in voice signal
Instruction;
The nursing bed control system executes corresponding operation for controlling the nursing bed ontology according to the control instruction.
2. according to claim 1 intellectual nursing bed, which is characterized in that the voice acquisition device is microphone.
3. according to claim 1 intellectual nursing bed, which is characterized in that the speech processing system includes at vocal print feature
Manage module and audio frequency characteristics processing module;
The vocal print feature processing module, for the vocal print for extracting characterization speaker's identity information from the voice signal of acquisition
Feature;
The audio frequency characteristics processing module, for the feature from the keyword extracted in the voice signal of acquisition in speaker's language
Parameter.
4. according to claim 3 intellectual nursing bed, which is characterized in that the audio frequency characteristics processing module includes that audio is pre-
Handle submodule, audio feature extraction submodule and key word information matched sub-block;
The audio pre-processes submodule, for carrying out speech enhan-cement and filtering to the voice signal of acquisition, obtains the first voice
Signal;
The audio feature extraction submodule can describe speaker's language for extracting from first voice signal
The characteristic parameter of middle key word information;
The key word information matched sub-block, for by the spy of the characteristic parameter extracted and the keyword prestored in database
Sign parameter is matched, and characteristic parameter to the control instruction for exporting the corresponding keyword after successful match generates system.
5. according to claim 4 intellectual nursing bed, which is characterized in that the audio pretreatment submodule includes that audio increases
Strong unit and audio detection subelement;
The audio enhancement unit, for carrying out speech enhan-cement processing to the voice signal of acquisition;
The audio detection subelement obtains the first voice letter for carrying out denoising to enhancing treated voice signal
Number.
6. according to claim 5 intellectual nursing bed, which is characterized in that the voice signal of described pair of acquisition carries out voice increasing
Strength reason, including:
(1) voice signal of acquisition is transformed from the time domain in frequency domain using Fourier transformation;
(2) speech enhan-cement processing is carried out to the voice signal in frequency domain according to customized speech enhan-cement formula, after obtaining enhancing
Voice signal, wherein customized speech enhan-cement formula is:
In formula,Indicate that enhanced treated voice signal, N (t, d) refer to that prior weight, X (t, d) indicate to increase
The voice signal in frequency domain before the reason of strength, p (t, d) indicate probability value existing for voice, G at t frame d frequency bandminIt indicates
Minimum gain value in the state of non-speech frame, t indicate that frame number, d indicate frequency;
(3) use inverse Fourier transform that enhanced voice signal from frequency-domain transform to time domain, is obtained the enhancing in time domain
Voice signal afterwards.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810726303.XA CN108899034A (en) | 2018-07-04 | 2018-07-04 | It is a kind of with the intellectual nursing bed of voice control function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810726303.XA CN108899034A (en) | 2018-07-04 | 2018-07-04 | It is a kind of with the intellectual nursing bed of voice control function |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108899034A true CN108899034A (en) | 2018-11-27 |
Family
ID=64347943
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810726303.XA Withdrawn CN108899034A (en) | 2018-07-04 | 2018-07-04 | It is a kind of with the intellectual nursing bed of voice control function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108899034A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110047483A (en) * | 2019-04-28 | 2019-07-23 | 东莞市慕思寝室用品有限公司 | The method of voice control beddo and the electronic bed system of voice control |
CN110310645A (en) * | 2019-07-02 | 2019-10-08 | 上海迥灵信息技术有限公司 | Sound control method, device and the storage medium of intelligence control system |
CN111110469A (en) * | 2019-12-13 | 2020-05-08 | 南方医科大学南方医院 | Multifunctional nursing bed |
CN113116654A (en) * | 2021-04-20 | 2021-07-16 | 联仁健康医疗大数据科技股份有限公司 | Bed board control system and method and sickbed |
US11881219B2 (en) | 2020-09-28 | 2024-01-23 | Hill-Rom Services, Inc. | Voice control in a healthcare facility |
-
2018
- 2018-07-04 CN CN201810726303.XA patent/CN108899034A/en not_active Withdrawn
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110047483A (en) * | 2019-04-28 | 2019-07-23 | 东莞市慕思寝室用品有限公司 | The method of voice control beddo and the electronic bed system of voice control |
CN110310645A (en) * | 2019-07-02 | 2019-10-08 | 上海迥灵信息技术有限公司 | Sound control method, device and the storage medium of intelligence control system |
CN111110469A (en) * | 2019-12-13 | 2020-05-08 | 南方医科大学南方医院 | Multifunctional nursing bed |
US11881219B2 (en) | 2020-09-28 | 2024-01-23 | Hill-Rom Services, Inc. | Voice control in a healthcare facility |
CN113116654A (en) * | 2021-04-20 | 2021-07-16 | 联仁健康医疗大数据科技股份有限公司 | Bed board control system and method and sickbed |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108899034A (en) | It is a kind of with the intellectual nursing bed of voice control function | |
WO2020177371A1 (en) | Environment adaptive neural network noise reduction method and system for digital hearing aids, and storage medium | |
CN105741849B (en) | The sound enhancement method of phase estimation and human hearing characteristic is merged in digital deaf-aid | |
CN103778920B (en) | Speech enhan-cement and compensating for frequency response phase fusion method in digital deaf-aid | |
US10614788B2 (en) | Two channel headset-based own voice enhancement | |
CN109410977B (en) | Voice segment detection method based on MFCC similarity of EMD-Wavelet | |
CN108735225A (en) | It is a kind of based on human ear masking effect and Bayesian Estimation improvement spectrum subtract method | |
CN110767244B (en) | Speech enhancement method | |
CN109616139A (en) | Pronunciation signal noise power spectral density estimation method and device | |
Borowicz et al. | Signal subspace approach for psychoacoustically motivated speech enhancement | |
CN104810024A (en) | Double-path microphone speech noise reduction treatment method and system | |
CN113129897A (en) | Voiceprint recognition method based on attention mechanism recurrent neural network | |
CN111489763B (en) | GMM model-based speaker recognition self-adaption method in complex environment | |
CN108877807A (en) | A kind of intelligent robot for telemarketing | |
Soleymani et al. | SEDA: A tunable Q-factor wavelet-based noise reduction algorithm for multi-talker babble | |
WO2020024787A1 (en) | Method and device for suppressing musical noise | |
CN115116446A (en) | Method for constructing speaker recognition model in noise environment | |
CN112185405B (en) | Bone conduction voice enhancement method based on differential operation and combined dictionary learning | |
CN113241089B (en) | Voice signal enhancement method and device and electronic equipment | |
Tian et al. | Smart radar sensor for speech detection and enhancement | |
Badiezadegan et al. | A wavelet-based thresholding approach to reconstructing unreliable spectrogram components | |
CN108922529A (en) | A kind of vehicle-mounted voice control system | |
CN111968627B (en) | Bone conduction voice enhancement method based on joint dictionary learning and sparse representation | |
Fu et al. | A novel speech enhancement system based on wavelet denoising | |
Zhang et al. | Robust Speaker Recognition Using Improved GFCC and Adaptive Feature Selection |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181127 |
|
WW01 | Invention patent application withdrawn after publication |