CN102342858A - Chinese medicine sound diagnosis acquisition and analysis system - Google Patents
Chinese medicine sound diagnosis acquisition and analysis system Download PDFInfo
- Publication number
- CN102342858A CN102342858A CN2010102454937A CN201010245493A CN102342858A CN 102342858 A CN102342858 A CN 102342858A CN 2010102454937 A CN2010102454937 A CN 2010102454937A CN 201010245493 A CN201010245493 A CN 201010245493A CN 102342858 A CN102342858 A CN 102342858A
- Authority
- CN
- China
- Prior art keywords
- voice
- signal
- sound
- analysis
- traditional chinese
- 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
Images
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a Chinese medicine sound diagnosis acquisition and analysis system. The Chinese medicine sound diagnosis acquisition and analysis system is formed by sequentially connecting a pronunciation table, a sound acquisition device and a voice processing system, wherein the pronunciation table is formed by combining vowels, poetry of the Tang Dynasty and Chinese characters corresponding to five tones; the sound acquisition device consists of a microphone and an audio card and is used for acquiring a sound signal; the microphone is connected with the audio card; the audio card converts an analogue signal acquired by the microphone into a digital signal; the voice processing system is arranged on a computer and comprises a voice recording system, a voice signal preprocessing system and a voice signal analysis system; and the voice recording system can prompt a testee to read after the content prompted in the pronunciation table. After the recorded voice signals are preprocessed, the voice signal analysis system distinguishes exterior and interior, cold and heat, and deficiency and excess of medical card type and viscera disease location by analyzing the sound information of the testee.
Description
Technical field
What the present invention relates to is to be used for traditional Chinese medical science sound to examine the armarium technical field that objectifies detection and analyze, and particularly a kind of ability objective detection examined collection and analytical system with the traditional Chinese medical science sound that analysis traditional Chinese medical science sound is examined information.
Background technology
It is through the examination method of listening with the understanding conditions of patients that traditional Chinese medical science sound is examined, and is the important component part of auscultation and olfaction in the traditional Chinese medical science four diagnostic methods.Traditional Chinese medical science sound is examined has long history and abundant theoretical basis, is in the clinical practice of ancient Chinese medicine doctor, to develop to sum up, and very important clinical application value is arranged.The traditional Chinese medical science is thought " lung controlling voice ", sound from lung system root in kidney, i.e. " lung is the door of sound, and kidney is the root of sound ".Lung governing qi, sound is sent out by gas, so the function of the generation of sound and lung is closely related; The kidney pulse hold under the arm tongue this, kidney essense is sufficient, on hold epiglottis, agitate sound channel and speak.If lung qi is sufficient, then sound is loud and clear; Insufficiency of lung-QI, then sound is humble; Wind-cold affecting lung, lung qi is inaccessible, then hoarseness or aphonia etc.Exopathogen is stopped up the lung person, and real noiseless for gold, its disease is true; Lung qi loss or YIN-deficiency of the lung and kidney person are the damaged lung not functioning normally, and its sick genus is empty, so saying of " gold being noiseless actually, and gold is broken also noiseless " arranged.
The research that Chinese medicine is examined sound is of long duration, and Huangdi's Internal Classics has proposed the theory of the five internal organs phase sound the earliest, thinks that the five internal organs respectively have positive sound, to close the five notes of traditional Chinese music.With the five internal organs and the five notes of traditional Chinese music, interrelate for five, illustrate that the inherent basis of the five notes of traditional Chinese music five is the internal organs vital essence.Jing-Yue Complete Works is said: " sound is from visceral-qi, and all dirty sound actually is great, and deficiency of five ZANG-organs then sound is timid "; Golden Mirror of Medicine is said: " good speaker's heat, lazy speaker is cold ".Ancient medicine is thought the abnormal noise that internal organs pathological changes such as a height of listening differential diagnosis of diseases people's words tone breath, power, pure and impure, emergency variation and cough, vomiting are sent, and can judge the cold and heat and asthenia and sthenia character of disease.
But tradition sound is examined restriction and the influence that is subject to doctors experience, academic thought, examination environment etc., and foundation and method that deficiency in objective is estimated have influenced the clinical practice that sound is examined.In recent years, the developing into of computer information technology inherited and developed sound and examine research opportunity is provided, and is that traditional Chinese medical science disease sound is examined information Recognition and injected new vitality like information processing technologies such as voice signal processing, pattern recognition and artificial intelligences.
At present, the research of similar purpose mainly concentrates in the research to 5525 people's cent classes.
Chinese patent CN 1560835A discloses a kind of twenty-five tones analyser on 01 05th, 2005; Comprise standard pronunciation table, sound resolving device, computer, display and printer; With the traditional medical theory is foundation; Utilize modernized high-tech; Solved the error of the resolution sound that possibly cause because of individual variation; Quantizating index for the twenty-five tones of indication in the Huangdi's Internal Classics provides a kind of modernized high-tech to analyze also can be used in other Acoustic detection fields.
Chinese patent CN 1125146A discloses the holographic state of internal organs Coryza Treated by Syndrome Differentiation of a kind of five notes of traditional Chinese music appearance on 06 26th, 1996, disclose a kind of disease therapeutic equipment according to holographic correlation theory design, is the facilities and equipments of five notes of traditional Chinese music dependency treatment method in Chinese medicine meridian and the music.This invention has been adopted the tape radio and has been made up of its preposition driving amplifier, multichannel power amplifier and adjustable power supply of voltage of doing signal source.
The twenty-five tones analyser that Chinese patent CN 1560835A provides adopts modernized high-tech, measures the frequency of pronunciation in good time, and which kind of in the traditional twenty-five tones of China analysis experimenter's sound belong to, to satisfy the clinical classification requirement of traditional traditional Chinese medical science.But the resolution of twenty-five tones is less in clinical practice, and is little to clinical directive significance.Sound resolution method mentioned in this patent is comparatively simple, i.e. and " data base of five or five twenty-five tones of setting up already with computer-internal compares analysis, produces judged result automatically ", its accuracy and practicality remain further to be improved.
Holographic state of internal organs Coryza Treated by Syndrome Differentiation appearance of the five notes of traditional Chinese music that Chinese patent CN 1125146A provides and traditional Chinese medical science sound examine theory and the clinical practice relation is little.
Summary of the invention
Deficiency and defective to prior art; Technical problem to be solved by this invention provides a kind of ability objective detection and analyzes acoustic information, and realizes that with computer analysis the sound of traditional Chinese medical science the exterior and the interior deficiency and excess cold and heat and different internal organs pattern of syndrome is examined the identification of information characteristics and the traditional Chinese medical science sound of judgement is examined collection and analytical system.Relative theory and theory that this system examines based on traditional Chinese medical science sound; In conjunction with the whole bag of tricks such as present information treatment technology, pattern recognitions; Can objective detection and write down measured's acoustical signal; Use multiple signal processing technology; Acoustical signal to detecting is analyzed, and judges experimenter's the sound and the corresponding relation of traditional Chinese medical science the exterior and the interior, deficiency and excess, cold and heat and Zang-Fu syndrome.
The solution of the above-mentioned technical problem of the present invention realizes through following technical scheme: a kind of traditional Chinese medical science sound is examined and is gathered and analytical system, connects voice collection device by the pronunciation table, and voice collection device connects speech processing system and constitutes, and its innovative point is:
The pronunciation table combines by vowel, Tang poetry with corresponding to the Chinese character of the five notes of traditional Chinese music;
Voice collection device is made up of microphone and audio card, is used for collected sound signal; Microphone is connected with audio card, and the analog signal conversion that audio card is collected microphone is a digital signal;
Speech processing system is installed on computers, comprises voice recording system, speech signal pre-processing system and speech signal analysis system, wherein:
The voice recording system voice signal that voice collection device is collected saves as the audio files of WAV form;
Speech signal pre-processing system is carried out pretreatment to the acoustical signal of preserving, and preprocess method comprises end-point detection, preemphasis, windowing and branch frame, for signal analysis and feature extraction are prepared;
The speech signal analysis system will carry out time-domain analysis, frequency-domain analysis and time-frequency combination analysis to acoustical signal; Extract effective characteristic parameter; And the method for using artificial neural networks and support vector machine identification, voice signal is carried out discriminator, draw dialectical conclusion at last.
Among the present invention, voice collection device is connected with voice recording system on the computer, and voice signal pretreatment on the computer and analytical system can be carried out pretreatment and analysis to the voice signal of recording.
Among the present invention, the voice recording system can point out the experimenter to follow the content of being pointed out in the pronunciation table.After the voice signal of being recorded was carried out pretreatment, the exterior and the interior cold and heat and asthenia and sthenia and the cacosplanchnia position of its TCM Syndrome Type distinguished by the speech signal analysis system through the acoustic information of analyzing the measured.
Among the present invention, voice collection device adopts headset integral type microphone, is the influence that lip causes apart from difference apart from microphone in order to reduce the people and to pronounce, and the head that this kind structure is fixed on the people can be so that each recording all be on the identical recording distance.Audio input interface, amplifier interface, headphone monitor output interface, audio output interface are arranged on the audio card.
Among the present invention; Voice recording system on the computer is according to the voice messaging of being accepted; Can demonstrate the sonogram of experimenter's sound, and primary voice data is saved as the audio files of WAV form, comprise the information such as quantization digit, sample frequency and channel number of sound.The pretreatment system of voice signal carries out end-point detection, preemphasis, windowing and branch frame etc. to speech data.Temporal analysis (the basic time domain parameter of voice signal has short-time energy, short-time average magnitude, short-time zero-crossing rate, short-time autocorrelation function and short-time average magnitude difference function etc.), frequency domain analysis (frequency domain character of voice signal comprises the frequency spectrum of voice signal, power spectrum, cepstrum, spectrum envelope analysis etc.) and time-frequency conjoint analysis method (like WAVELET PACKET DECOMPOSITION etc.) etc. are used in the processing section of voice signal, and applying neural network, the recognition methods of support vector machine isotype are carried out distinguishing of syndrome.
The present invention compared with prior art has the following advantages and effect: the whole bag of tricks that present information is handled is used in (1), and the traditional Chinese medical science sound information of examining is carried out analyzing and processing, is the important exploration that traditional Chinese medical science sound is examined the research that objectifies; (2) the whole bag of tricks of first Application pattern recognition carries out Classification and Identification to clinical different syndrome classifications (the exterior and the interior, cold and heat, deficiency and excess and different Zang-Fu syndrome) patient's acoustic information, for clinical syndrome differentiation provides objective basis, improves the clinical value that traditional Chinese medical science sound is examined; (3) all are examined in the relevant invention with sound at present, also do not see the research that the different pattern of syndrome with tcm clinical practice of acoustic information are combined.
Present traditional Chinese medical science sound is examined main dependence doctor's subjective judgment, is subject to many factors such as doctors experience, examination environment, and deficiency in objective property, repeatability have influenced clinical practice and succession popularization that sound is examined.Traditional Chinese medical science sound provided by the invention is examined and is gathered and analytical equipment, and the pronunciation harmony in the exterior voice recording instrument of code requirement has solved shortcomings such as traditional auscultation and olfaction subjectivity is strong, poor repeatability, objective collection of ability and preservation voice signal on the one hand; The correlation theory and the present information treatment technology that combine traditional Chinese medical science sound to examine on the other hand; Voice signal to gathering carries out analyzing and processing; The relevant feature parameters of the voice messaging of different diseases is provided, distinguishes disease, tcm clinical therapeutic evaluation for tcm clinical practice objective basis is provided.
Description of drawings
Fig. 1 is a structured flowchart of the present invention.
The specific embodiment
Below in conjunction with accompanying drawing and specific embodiment, further set forth the present invention.These embodiment are interpreted as only being used to the present invention is described and are not used in restriction protection scope of the present invention.After the content of having read the present invention's record, those skilled in the art can do various changes or modification to the present invention, and these equivalences change and modify and fall into claim of the present invention institute restricted portion equally.
As shown in Figure 1, the traditional Chinese medical science sound that the present invention's one preferred embodiment provides is examined and is gathered and analytical system, connects voice collection device by pronunciation table 1, and voice collection device connects computer and constitutes.Voice collection device is made up of microphone 2, audio card 3.Voice recording system 4 is installed on the computer, and the voice signal that voice collection device is collected saves as wav file.The acoustical signal of 5 pairs of preservations of speech signal pre-processing system carries out pretreatment, and main preprocess method comprises end-point detection, preemphasis, windowing and branch frame etc., for signal analysis and feature extraction are prepared.Speech signal analysis system 6 will carry out various processing such as time-domain analysis, frequency-domain analysis, time-frequency combination analytical method to acoustical signal; Extract effective characteristic parameter; And the method for various pattern recognitions such as applying neural network, support vector machine; Voice signal is carried out discriminator, draw dialectical conclusion at last.
Pronunciation table 1 is vowel, Tang poetry, be formed by combining corresponding to the Chinese character of the five notes of traditional Chinese music.The voice recording system can point out the experimenter to follow the content of being pointed out in the pronunciation table.After the voice signal of being recorded was carried out pretreatment, the exterior and the interior cold and heat and asthenia and sthenia and the cacosplanchnia position of its TCM Syndrome Type distinguished by the speech signal analysis system through the acoustic information of analyzing the measured.
Test Example
Speech signal collection system acquisition clinical patients that provides with the above-mentioned preferred embodiment of the present invention in Shuguang Hospital and healthy subjects sample sound; And analyze, and judge experimenter's the sound and the corresponding relation of traditional Chinese medical science the exterior and the interior, deficiency and excess, cold and heat and Zang-Fu syndrome.At first the voice signal of gathering is carried out pretreatment, comprise end-point detection, preemphasis, windowing and branch frame etc.
1. end-point detection
End-point detection is promptly confirmed the position that voice signal begins and finishes.Use time domain approach in this research and carry out end-point detection.Time domain approach is mainly realized the end-point detection of voice signal through magnitude, can judge through amplitude or energy, and perhaps amplitude is that master, zero-crossing rate are realized for assisting.
2. preemphasis
Preemphasis is through a limited exciter response high pass filter of single order, improves the HFS of signal, makes the frequency spectrum of signal become smooth, remains on low frequency in the whole frequency band of high frequency, can ask frequency spectrum with same signal to noise ratio.
3. windowing and branch frame
According to the smooth performance in short-term of voice, be that unit handles with the frame with voice signal.The frame number of per second is 33～100 frames.Dividing frame is to realize that with the method that wired length window is movably carried out weighting the window function that uses is Hamming window.The windowing of voice signal can reduce the problem of spectral leakage to a certain extent.
After voice signal is carried out pretreatment, carry out feature extraction and Classification and Identification by 6 pairs of voice signals of speech signal analysis system.
Feature extracting method has methods such as time domain, frequency domain and time-frequency conjoint analysis.The time domain parameter of voice signal is promptly analyzed and extracted to temporal analysis, comprises short-time energy, short-time average magnitude, short-time zero-crossing rate, short-time autocorrelation function and short-time average magnitude difference function.Frequency domain analysis is an analyzing speech signal frequency-domain characteristic, comprises frequency spectrum, power spectrum and cepstrum characteristic.What use always in the time-frequency combination analytical method is the WAVELET PACKET DECOMPOSITION method.At first the voice signal of being gathered is carried out 7 layers of WAVELET PACKET DECOMPOSITION; Obtain each node wavelet packet coefficient, extract and to extract energy variation and power variation parameter after the wavelet packet coefficient energy divides frame than, power ratio and shannon entropy than parameter and preceding 14 node wavelet packet coefficients.The diversity of each parameter being carried out between three groups (normal and improper, deficiency syndrome and excess syndrome, the deficiency of vital energy and the deficiency of YIN) detects, and screens the item that there were significant differences.
Artificial neural network is based on a kind of novel information system for handling to the Preliminary study proposition of human brain tissue structure, active mechanism.The establishment of neutral net, training and prediction classification can realize in Matlab software easily.Be that (Error Back Proragation, artificial neural network BP) carries out pattern recognition based on error backpropagation algorithm in application in this research.BP algorithm basic thought is: learning process is made up of the forward-propagating of signal and two processes of back propagation of error.During forward-propagating, the input sample imports into from input layer, after each latent layer is successively handled, passes to output layer.If the actual output of output layer and the output (teacher signal) of expectation are not inconsistent, then change the back-propagation phase of error over to.The error anti-pass is that output error is passed through latent course input layer anti-pass successively with certain form, and error is shared all unit to each layer, thereby obtains the unitary error signal of each layer, and this error signal is promptly as the foundation of revising each unit weights.Each layer weights adjustment process of sort signal forward-propagating and error back propagation is gone round and begun again and is carried out.The weights constantly process of adjustment are exactly the learning training process of network.The error that this process is performed until network output reduces to the acceptable degree, perhaps proceeds to till the preset study number of times.
Support vector machine (Support Vector Machine, SVM) a kind of mode identification method based on Statistical Learning Theory.SVM more in the space of higher-dimension, establishes a largest interval hyperplane with DUAL PROBLEMS OF VECTOR MAPPING in this space.Both sides at the hyperplane that separates data have two hyperplane parallel to each other.Suitable separation hyperplane makes the distance maximization between two parallel with it hyperplane to SVM through setting up direction, thereby reaches the purpose of Classification and Identification.
Be to avoid the randomness of single training and prediction, the method that adopts random sample repeatedly to train prediction to average, promptly each computing is randomly drawed 65% sample and is used for training, remains 35% sample and is used for prediction and calculates predictablity rate.This process is got its meansigma methods as dialectical accuracy rate through 50 training.The result is as shown in table 1 below:
Can find out through the consensus forecast accuracy rate that (1) in three groups, the predictablity rate of non-health, deficiency syndrome and the deficiency of vital energy is higher, meansigma methods has reached 95.6%, 94.6% and 87.4% respectively; And the prediction rate of health, excess syndrome and the deficiency of YIN is lower, and particularly excess syndrome only has 22.5%.
Can find out through the minimax predictablity rate that (2) fluctuation that healthy, excess syndrome and deficiency of YIN group equal samples are less group is bigger, maximum is more than 3 times of minima.
Can find out through the macro-forecast accuracy rate that (3) three group categories grand mean accuracys rate have reached 88.0%, 84.2% and 76.9% respectively, general effect is in a higher level.
Table 1 is used the accuracy rate that the wavelet packet parameter is carried out different syndrome voice signal identifications
Claims (5)
1. a traditional Chinese medical science sound is examined and is gathered and analytical system, connects voice collection device by pronunciation table (1), and voice collection device connects speech processing system and constitutes, and it is characterized in that:
The pronunciation table combines by vowel, Tang poetry with corresponding to the Chinese character of the five notes of traditional Chinese music;
Voice collection device is made up of microphone (2) and audio card (3), is used for collected sound signal; Microphone (2) is connected with audio card (3), and the analog signal conversion that audio card (3) is collected microphone (2) is a digital signal;
Speech processing system is installed on computers, comprises voice recording system (4), speech signal pre-processing system (5) and speech signal analysis system (6), wherein:
Voice recording system (4) voice signal that voice collection device is collected saves as the audio files of WAV form;
Speech signal pre-processing system (5) is carried out pretreatment to the acoustical signal of preserving, and preprocess method comprises end-point detection, preemphasis, windowing and branch frame, for signal analysis and feature extraction are prepared;
Speech signal analysis system (6) will carry out time-domain analysis, frequency-domain analysis and time-frequency combination analysis to acoustical signal; Extract effective characteristic parameter; And the method for using artificial neural networks and support vector machine identification, voice signal is carried out discriminator, draw dialectical conclusion at last.
2. traditional Chinese medical science sound according to claim 1 is examined and is gathered and analytical system; It is characterized in that: voice recording system prompt experimenter is with the content of being pointed out in the pronunciation table; After the voice signal of being recorded was carried out pretreatment, the exterior and the interior cold and heat and asthenia and sthenia and the cacosplanchnia position of its TCM Syndrome Type distinguished by the speech signal analysis system through the acoustic information of analyzing the measured.
3. traditional Chinese medical science sound according to claim 1 is examined and gathered and analytical system, it is characterized in that: voice collection device adopts headset integral type microphone.
4. traditional Chinese medical science sound according to claim 1 is examined and is gathered and analytical system; It is characterized in that: in the time-domain analysis, the basic time domain parameter of voice signal comprises short-time energy, short-time average magnitude, short-time zero-crossing rate, short-time autocorrelation function and short-time average magnitude difference function.
5. traditional Chinese medical science sound according to claim 1 is examined and is gathered and analytical system, and it is characterized in that: in the frequency-domain analysis, the frequency domain character of voice signal comprises the frequency spectrum of voice signal, power spectrum, cepstrum and spectrum envelope analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102454937A CN102342858A (en) | 2010-08-06 | 2010-08-06 | Chinese medicine sound diagnosis acquisition and analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010102454937A CN102342858A (en) | 2010-08-06 | 2010-08-06 | Chinese medicine sound diagnosis acquisition and analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102342858A true CN102342858A (en) | 2012-02-08 |
Family
ID=45542196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010102454937A Pending CN102342858A (en) | 2010-08-06 | 2010-08-06 | Chinese medicine sound diagnosis acquisition and analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102342858A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103377656A (en) * | 2012-04-16 | 2013-10-30 | 联想(北京)有限公司 | Five-tone analysis method for audio frequency file, player, and electronic equipment |
| CN103730130A (en) * | 2013-12-20 | 2014-04-16 | 中国科学院深圳先进技术研究院 | Detection method and system for pathological voice |
| CN105787262A (en) * | 2016-02-20 | 2016-07-20 | 成都中医药大学 | Traditional Chinese medicine clinical digital evaluation system and evaluation method thereof on basis of big data analysis |
| CN107242857A (en) * | 2017-06-12 | 2017-10-13 | 南开大学 | The intelligent traditional Chinese medical science based on deep learning integrates diagnosis and therapy system |
| CN107833582A (en) * | 2017-11-20 | 2018-03-23 | 南京财经大学 | The Method of Speech Endpoint Detection based on arc length |
| CN107910019A (en) * | 2017-11-30 | 2018-04-13 | 中国科学院微电子研究所 | A kind of human acoustical signal's processing and analysis method |
| CN108053841A (en) * | 2017-10-23 | 2018-05-18 | 平安科技（深圳）有限公司 | The method and application server of disease forecasting are carried out using voice |
| CN108806720A (en) * | 2017-05-05 | 2018-11-13 | 京东方科技集团股份有限公司 | Microphone, data processor, monitoring system and monitoring method |
| CN109300473A (en) * | 2018-10-23 | 2019-02-01 | 慈中华 | Voice messaging acquisition methods and device |
| CN109495636A (en) * | 2018-10-23 | 2019-03-19 | 慈中华 | Information interacting method and device |
| CN109599102A (en) * | 2018-10-24 | 2019-04-09 | 慈中华 | Identify the method and device of channels and collaterals state |
| CN110772235A (en) * | 2019-08-22 | 2020-02-11 | 天津森宇科技股份有限公司 | Traditional Chinese medicine intelligent health analysis system based on cloud computing and mobile platform |
| CN111133468A (en) * | 2017-09-21 | 2020-05-08 | 李东奂 | Service providing method and device for electronic engineering harmonic algorithm for comparing, distinguishing and interpreting sound of animal disease infected individual including avian influenza by utilizing PFD technology |
| CN111543947A (en) * | 2020-05-11 | 2020-08-18 | 中北大学 | Traditional Chinese medicine sound diagnosis method and system |
| CN111870525A (en) * | 2020-08-31 | 2020-11-03 | 深圳百川艾科技有限公司 | AI voice constitution recognition moxibustion instrument and AI voice constitution recognition method |
| CN112017695A (en) * | 2020-03-04 | 2020-12-01 | 上海交通大学医学院附属上海儿童医学中心 | System and method for automatically identifying physiological sound |
| CN112587092A (en) * | 2020-12-02 | 2021-04-02 | 上海工程技术大学 | Liver phase voice traditional Chinese medicine accurate auscultation system with force and touch excitation |
| CN115691537A (en) * | 2022-12-28 | 2023-02-03 | 江苏米笛声学科技有限公司 | Analysis and processing system of earphone audio signal |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1241167C (en) * | 2004-03-11 | 2006-02-08 | 高也陶 | 25-voice analyser |
-
2010
- 2010-08-06 CN CN2010102454937A patent/CN102342858A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1241167C (en) * | 2004-03-11 | 2006-02-08 | 高也陶 | 25-voice analyser |
Non-Patent Citations (4)
| Title |
|---|
| 《中华中医药学会中医诊断学分会第十次学术研究论文集》 20090719 沈小静等 "中医声诊研究及基于小波包的客观化研究" 第316-319页 1-5 , * |
| 《中华中医药学会中医诊断学分会第十次学术研究论文集》 20090719 马天才等 "基于小波包声音信号分析技术的中医虚实证声诊特征分析" 第310-315页 1-5 , * |
| 沈小静等: ""中医声诊研究及基于小波包的客观化研究"", 《中华中医药学会中医诊断学分会第十次学术研究论文集》 * |
| 马天才等: ""基于小波包声音信号分析技术的中医虚实证声诊特征分析"", 《中华中医药学会中医诊断学分会第十次学术研究论文集》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103377656B (en) * | 2012-04-16 | 2016-08-10 | 联想(北京)有限公司 | The five notes of traditional Chinese music of a kind of audio file analyze method, player and electronic equipment |
| CN103377656A (en) * | 2012-04-16 | 2013-10-30 | 联想(北京)有限公司 | Five-tone analysis method for audio frequency file, player, and electronic equipment |
| CN103730130A (en) * | 2013-12-20 | 2014-04-16 | 中国科学院深圳先进技术研究院 | Detection method and system for pathological voice |
| CN103730130B (en) * | 2013-12-20 | 2019-03-01 | 中国科学院深圳先进技术研究院 | A kind of detection system of pathological voice |
| CN105787262A (en) * | 2016-02-20 | 2016-07-20 | 成都中医药大学 | Traditional Chinese medicine clinical digital evaluation system and evaluation method thereof on basis of big data analysis |
| CN105787262B (en) * | 2016-02-20 | 2018-04-10 | 成都中医药大学 | Tcm clinical practice Digital evaluation system and its evaluation method based on big data analysis |
| US10499149B2 (en) | 2017-05-05 | 2019-12-03 | Boe Technology Group Co., Ltd. | Microphone, vocal training apparatus comprising microphone and vocal analyzer, vocal training method, and non-transitory tangible computer-readable storage medium |
| CN108806720B (en) * | 2017-05-05 | 2019-12-06 | 京东方科技集团股份有限公司 | Microphone, data processor, monitoring system and monitoring method |
| CN108806720A (en) * | 2017-05-05 | 2018-11-13 | 京东方科技集团股份有限公司 | Microphone, data processor, monitoring system and monitoring method |
| CN107242857A (en) * | 2017-06-12 | 2017-10-13 | 南开大学 | The intelligent traditional Chinese medical science based on deep learning integrates diagnosis and therapy system |
| CN111133468A (en) * | 2017-09-21 | 2020-05-08 | 李东奂 | Service providing method and device for electronic engineering harmonic algorithm for comparing, distinguishing and interpreting sound of animal disease infected individual including avian influenza by utilizing PFD technology |
| CN111133468B (en) * | 2017-09-21 | 2023-12-19 | 李东奂 | Service providing method and device for comparing, distinguishing and interpreting sound of individual infected with animal diseases including avian influenza by using PFD technology |
| CN108053841A (en) * | 2017-10-23 | 2018-05-18 | 平安科技（深圳）有限公司 | The method and application server of disease forecasting are carried out using voice |
| WO2019080502A1 (en) * | 2017-10-23 | 2019-05-02 | 平安科技（深圳）有限公司 | Voice-based disease prediction method, application server, and computer readable storage medium |
| CN107833582B (en) * | 2017-11-20 | 2021-02-09 | 南京财经大学 | Arc length-based voice signal endpoint detection method |
| CN107833582A (en) * | 2017-11-20 | 2018-03-23 | 南京财经大学 | The Method of Speech Endpoint Detection based on arc length |
| CN107910019A (en) * | 2017-11-30 | 2018-04-13 | 中国科学院微电子研究所 | A kind of human acoustical signal's processing and analysis method |
| CN109495636A (en) * | 2018-10-23 | 2019-03-19 | 慈中华 | Information interacting method and device |
| US11315562B2 (en) | 2018-10-23 | 2022-04-26 | Zhonghua Ci | Method and device for information interaction |
| CN109300473A (en) * | 2018-10-23 | 2019-02-01 | 慈中华 | Voice messaging acquisition methods and device |
| CN109599102A (en) * | 2018-10-24 | 2019-04-09 | 慈中华 | Identify the method and device of channels and collaterals state |
| CN110772235A (en) * | 2019-08-22 | 2020-02-11 | 天津森宇科技股份有限公司 | Traditional Chinese medicine intelligent health analysis system based on cloud computing and mobile platform |
| CN112017695A (en) * | 2020-03-04 | 2020-12-01 | 上海交通大学医学院附属上海儿童医学中心 | System and method for automatically identifying physiological sound |
| CN111543947A (en) * | 2020-05-11 | 2020-08-18 | 中北大学 | Traditional Chinese medicine sound diagnosis method and system |
| CN111543947B (en) * | 2020-05-11 | 2023-03-14 | 中北大学 | Traditional Chinese medicine sound diagnosis method and system |
| CN111870525A (en) * | 2020-08-31 | 2020-11-03 | 深圳百川艾科技有限公司 | AI voice constitution recognition moxibustion instrument and AI voice constitution recognition method |
| CN112587092A (en) * | 2020-12-02 | 2021-04-02 | 上海工程技术大学 | Liver phase voice traditional Chinese medicine accurate auscultation system with force and touch excitation |
| CN112587092B (en) * | 2020-12-02 | 2022-04-05 | 上海工程技术大学 | Liver phase voice traditional Chinese medicine accurate auscultation system with force and touch excitation |
| CN115691537A (en) * | 2022-12-28 | 2023-02-03 | 江苏米笛声学科技有限公司 | Analysis and processing system of earphone audio signal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102342858A (en) | Chinese medicine sound diagnosis acquisition and analysis system | |
| Ma et al. | Lungbrn: A smart digital stethoscope for detecting respiratory disease using bi-resnet deep learning algorithm | |
| Alsabek et al. | Studying the Similarity of COVID-19 Sounds based on Correlation Analysis of MFCC | |
| US7479115B2 (en) | Computer aided diagnosis of lung disease | |
| Matos et al. | Detection of cough signals in continuous audio recordings using hidden Markov models | |
| Cheng et al. | Research on heart sound identification technology | |
| Bugdol et al. | Multimodal biometric system combining ECG and sound signals | |
| Hartelius et al. | Long-term phonatory instability in individuals with multiple sclerosis | |
| Patil et al. | The physiological microphone (PMIC): A competitive alternative for speaker assessment in stress detection and speaker verification | |
| Tran et al. | Stethoscope-sensed speech and breath-sounds for person identification with sparse training data | |
| CN112754502A (en) | Automatic music switching method based on electroencephalogram signals | |
| Pham et al. | Inception-based network and multi-spectrogram ensemble applied to predict respiratory anomalies and lung diseases | |
| Patel et al. | Lung Respiratory Audio Prediction using Transfer Learning Models | |
| Chien et al. | Wheeze detection using cepstral analysis in gaussian mixture models | |
| CN113974607A (en) | Sleep snore detecting system based on impulse neural network | |
| Porieva et al. | Investigation of lung sounds features for detection of bronchitis and COPD using machine learning methods | |
| Phua et al. | Human identification using heart sound | |
| US20220409063A1 (en) | Diagnosis of medical conditions using voice recordings and auscultation | |
| Kaur et al. | Extraction of heart rate parameters using speech analysis | |
| Dam et al. | e-Breath: breath detection and monitoring using frequency cepstral feature fusion | |
| CN108154888A (en) | A kind of wearable device monitoring mental health method based on phonetic feature | |
| Nathan et al. | Utilizing deep learning on limited mobile speech recordings for detection of obstructive pulmonary disease | |
| Qiao et al. | A bowel sound detection method based on a novel non-speech body sound sensing device | |
| CN110211566A (en) | A kind of classification method of compressed sensing based hepatolenticular degeneration disfluency | |
| Wiśniewski et al. | Tonal Index in digital recognition of lung auscultation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120208 |