WO2022191685A1 - Smart device for detecting persons displaying symptoms of covid-19 infection - Google Patents
Smart device for detecting persons displaying symptoms of covid-19 infection Download PDFInfo
- Publication number
- WO2022191685A1 WO2022191685A1 PCT/MA2021/050015 MA2021050015W WO2022191685A1 WO 2022191685 A1 WO2022191685 A1 WO 2022191685A1 MA 2021050015 W MA2021050015 W MA 2021050015W WO 2022191685 A1 WO2022191685 A1 WO 2022191685A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cartridges
- aroma
- covid
- infection
- odor
- Prior art date
Links
- 208000025721 COVID-19 Diseases 0.000 title claims description 5
- 208000024891 symptom Diseases 0.000 title claims description 5
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 230000004044 response Effects 0.000 claims abstract description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 208000015181 infectious disease Diseases 0.000 claims description 4
- 238000000034 method Methods 0.000 claims description 4
- 235000019568 aromas Nutrition 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 230000004913 activation Effects 0.000 claims 1
- 239000000796 flavoring agent Substances 0.000 claims 1
- 235000019634 flavors Nutrition 0.000 claims 1
- 238000010606 normalization Methods 0.000 claims 1
- 238000005070 sampling Methods 0.000 claims 1
- 238000005507 spraying Methods 0.000 claims 1
- 238000009529 body temperature measurement Methods 0.000 abstract description 4
- 238000012795 verification Methods 0.000 abstract description 2
- 235000019645 odor Nutrition 0.000 description 10
- 241000711573 Coronaviridae Species 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 210000001061 forehead Anatomy 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010002653 Anosmia Diseases 0.000 description 1
- 235000011034 Rubus glaucus Nutrition 0.000 description 1
- 244000235659 Rubus idaeus Species 0.000 description 1
- 235000009122 Rubus idaeus Nutrition 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 235000016213 coffee Nutrition 0.000 description 1
- 235000013353 coffee beverage Nutrition 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 235000012736 patent blue V Nutrition 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Definitions
- the present invention belongs to the field of measuring means used to establish a diagnosis capable of identifying the cases of persons showing symptoms of infection by Covid-19. In particular, the loss of smell and the rise in temperature.
- the invention relates to a device combining an automated test of temperature and smell in people passing through an access point of a building for example.
- the device is composed of infrared temperature measurement means and an intelligent rapid smell test module composed of: an odor distributor and diffuser, an automatic odor selection module, an electronic system control card, a voice recognition and answer verification system, indicator lights to indicate the test result and the status of the device.
- the control agent presses the ignition button of the device (14).
- the LED (9.3) flashes red, otherwise it is permanently lit in sky blue. If the cartridges are empty, the indicator (9.4) flashes red, otherwise it is permanently lit brown.
- the control officer places the device near the user's forehead and presses the test trigger button (15).
- the tests consist of a temperature measurement and an automated odor examination.
- the device takes the user's temperature and indicates the result on the screen (12), if the measured temperature is greater than 37.3° the light (9.1) lights up, otherwise the odor test is carried out.
- the first step is the automatic and random selection of an examination odor.
- the motor moves the selected cartridge up, the fogger of the selected cartridge passes through the pipe and exits through the diffuser.
- the fan starts to turn, so the smell is transmitted to the user.
- ASR Automatic Speech Recognition
- MFCC Mel-Frequency Cepstral Coefficients
- MFCCs are commonly used as features in voice recognition systems, such as systems that can automatically recognize numbers spoken into a telephone.
- a deep learning model based on convolutional neural networks is applied to classify the MFCC characteristics of the user's speech and determine whether the pronounced response corresponds to the name of the odor diffused (in multi-language).
- CNN convolutional neural networks
- the temperature is taken initially just after pressing the test trigger button (15) present on the device and by directing the latter towards the forehead of the individual.
- the device randomly selects and sprays one of the three aromas installed in the device (for example: Lemon, Mint, Coffee).
- the individual undergoing the test must pronounce the name of the aroma sprayed by their preferred language (Arabic, French, English).
- the loudspeaker included in the device broadcasts a beep indicating the initiation of listening to the response.
- the microphone included in the device picks up the individual's response and sends it to the processing unit which outputs one of these four classes (Odor1, Odor2, Odor3, Other).
- the system triggers the fan a second time to release the scent from the diffuser.
- the result of the processing unit is compared to the selected odor and displays the result on the appropriate light: the green light (9.1) for temperature below 37.3 and correct response, the red light for temperature above 37.3 or for wrong answer.
- the Deep Learning method is used in the context of the present invention for the vocal recognition of the words pronounced by the individuals undergoing the smell test.
- the model used is based on convolutional neural networks (CNN) and is applied to classify the MFCC characteristics of the user's speech.
- Multi-language acceptance consists of classifying the user's response into ten classes: Odorl_Arabe, Odorl_French, Odorl_English, Odor2_Arabic, Odor2_French, Odor2_English, Odor3_Arabic, Odor3_French, Odor3_English, Other, and to reduce the response domain into four: Odor1, Odor 2, Odor 3, other. Description of the drawings
- FIG 1 shows the combined test device object of the invention, this device is composed of (the references refer to drawings 1):
- Figure 2 shows a Functional Description of the device.
Landscapes
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Fire Alarms (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention relates to a device combining an automated temperature and smell test in persons passing through an access point to a building, for example. The device is composed of infrared temperature measurement means and a smart quick smell test module composed of: an odor dispenser and diffuser, an automatic odor selection module, a system control circuit board, a voice recognition and response verification system, indicator lights for indicating the result of the test and the status of the apparatus.
Description
Dispositif intelligent pour détection de personnes manifestant des symptômes d'infection par Intelligent device for detecting persons showing symptoms of infection by
COVID-19 COVID-19
Domaine de l'invention Field of invention
La présente invention appartient au domaine des moyens de mesure servant à établir un diagnostic susceptible d'identifier les cas de personnes manifestant des symptômes d'infection par Covid-19. Notamment, la perte de l'odorat et l'élévation de la température. The present invention belongs to the field of measuring means used to establish a diagnosis capable of identifying the cases of persons showing symptoms of infection by Covid-19. In particular, the loss of smell and the rise in temperature.
Problème technique Technical problem
Dans un monde parfait, l'entrée de chaque bureau, restaurant et école doit être conditionnée par le passage d'un test de coronavirus avec une précision absolue, et capable de déterminer instantanément les cas positifs affectés par le coronavirus afin d'éviter leurs accès aux milieux publics. In a perfect world, the entrance to every office, restaurant and school must be conditioned by passing a coronavirus test with absolute precision, and able to instantly determine the positive cases affected by the coronavirus in order to avoid their access. to public circles.
Malheureusement, cette approche n'est pas réelle, à cause de l'absence actuellement d'une solution fiable et rapide. Actuellement, le test le plus répondus au niveau des accès au bâtiments est la mesure de température. L'efficacité de cette méthode reste limitée à cause de nombreux cas asymptotiques ainsi que les méthodes de relevé de températures aux accès public qui est faites généralement par des gens mal formés et non spécialistes. Unfortunately, this approach is not real, due to the current lack of a reliable and fast solution. Currently, the most popular test for building access is temperature measurement. The effectiveness of this method remains limited because of many asymptotic cases as well as the methods of recording temperatures at public accesses which are generally carried out by poorly trained and non-specialist people.
Résumé de l'invention Summary of the invention
L'invention porte sur un dispositif combinant un test automatisé de température et de l'odorat chez les personnes passant par un point d'accès d'un bâtiment par exemple. Le dispositif est composé de moyens de mesure de température par infrarouge et un module intelligent de test rapide d'odorat composé de : un distributeur et diffuseur d'odeurs, un module de sélection automatique d'odeur, une carte électronique de commande du système, un système de reconnaissance vocale et de vérification de réponses, des voyants lumineux pour indiquer le résultat du test et l'état de l'appareil. The invention relates to a device combining an automated test of temperature and smell in people passing through an access point of a building for example. The device is composed of infrared temperature measurement means and an intelligent rapid smell test module composed of: an odor distributor and diffuser, an automatic odor selection module, an electronic system control card, a voice recognition and answer verification system, indicator lights to indicate the test result and the status of the device.
Description du mode de réalisation de l'invention Description of the embodiment of the invention
Lors de la présentation d'un utilisateur dans un point d'accès d'une entité, l'agent de control appui sur le bouton d'allumage du dispositif (14). En cas de batterie faible le voyant (9.3) clignote en rouge, sinon il est allumé en permanence en bleu ciel. En cas d'épuisement de cartouches le voyant (9.4) clignote en rouge, sinon il est allumé en permanence en marron.During the presentation of a user in an access point of an entity, the control agent presses the ignition button of the device (14). In the event of a low battery, the LED (9.3) flashes red, otherwise it is permanently lit in sky blue. If the cartridges are empty, the indicator (9.4) flashes red, otherwise it is permanently lit brown.
L'agent de control place le dispositif près du front de l'utilisateur et il appui sur le bouton de déclenchement des tests (15). Les tests consistent en une mesure de température et un examen automatisé d'odeur. The control officer places the device near the user's forehead and presses the test trigger button (15). The tests consist of a temperature measurement and an automated odor examination.
Le dispositif prend la température de l'utilisateur et indique le résultat sur l'écran (12), si la température mesurée est supérieure à 37.3° le voyant (9.1) s'allume, sinon l'examen d'odeur s'exécute. The device takes the user's temperature and indicates the result on the screen (12), if the measured temperature is greater than 37.3° the light (9.1) lights up, otherwise the odor test is carried out.
La première étape c'est la sélection automatique et aléatoire d'une odeur d'examen. Le moteur déplace en haut la cartouche sélectionnée, le brumisateur de la cartouche sélectionné
passe dans la canalisation et sort dans le diffuseur. Le ventilateur se met à tourner, ainsi l'odeur est transmise sur l'utilisateur. The first step is the automatic and random selection of an examination odor. The motor moves the selected cartridge up, the fogger of the selected cartridge passes through the pipe and exits through the diffuser. The fan starts to turn, so the smell is transmitted to the user.
Sur le haut-parleur (10), un bip sonore indiquant le déclenchement de l'écoute. Le microphone (8) se met donc dans l'état de l'écoute pour enregistrer la réponse de l'utilisateur. Nous appliquons un algorithme de Automatic Speech Récognition (ASR), l'algorithme se base sur une extraction de caractéristique Mel-Frequency Cepstral Coefficients (MFCC). On the loudspeaker (10), a beep indicating the start of listening. The microphone (8) therefore goes into the listening state to record the user's response. We apply an Automatic Speech Recognition (ASR) algorithm, the algorithm is based on a Mel-Frequency Cepstral Coefficients (MFCC) feature extraction.
Les MFCC sont couramment utilisés comme caractéristiques dans les systèmes de reconnaissance vocale, tels que les systèmes qui peuvent reconnaître automatiquement les numéros prononcés dans un téléphone. MFCCs are commonly used as features in voice recognition systems, such as systems that can automatically recognize numbers spoken into a telephone.
Ainsi un modèle deep learning à base de réseaux de neurones de convolution (CNN) est appliqué pour classifier les caractéristiques MFCC du speech de l'utilisateur et déterminer si a réponse prononcée corresponde au nom de l'odeur diffusée (en multi-langue). Thus, a deep learning model based on convolutional neural networks (CNN) is applied to classify the MFCC characteristics of the user's speech and determine whether the pronounced response corresponds to the name of the odor diffused (in multi-language).
Déclenchement de l'appareil et prise de température : Triggering the device and taking the temperature:
Pour les individus subissant le test par l'appareil objet de la présente invention, la prise de la température est effectuée dans un premier temps juste après l'appuis sur le bouton de déclenchement du test (15) présent sur l'appareil et en dirigeant ce dernier vers le front de l'individu. For individuals undergoing the test by the device that is the subject of the present invention, the temperature is taken initially just after pressing the test trigger button (15) present on the device and by directing the latter towards the forehead of the individual.
Diffusion des odeurs et test de l'odorat : Diffusion of odors and smell test:
En application dans le contexte de la présente invention, l'appareil sélectionne et pulvérise de façon aléatoire un des trois arômes installés dans l'appareil, (par exemple : Citron, Menthe, Café). L'individu subissant le test doit prononcer le nom de l'arôme pulvérisée par sa langue préférée (Arabe, Français, Anglais). Le haut-parleur inclus dans l'appareil diffuse un bip sonore indiquant le déclenchement de l'écoute de la réponse. Le microphone inclus dans l'appareil capte la réponse de l'individu et l'envoie à l'unité de traitement qui donne en sortie l'une de ces quatre classes (Odeurl, Odeur2, Odeur3, Autre). Le système déclenche le ventilateur une deuxième fois pour dégager l'odeur du diffuseur. In application in the context of the present invention, the device randomly selects and sprays one of the three aromas installed in the device (for example: Lemon, Mint, Coffee). The individual undergoing the test must pronounce the name of the aroma sprayed by their preferred language (Arabic, French, English). The loudspeaker included in the device broadcasts a beep indicating the initiation of listening to the response. The microphone included in the device picks up the individual's response and sends it to the processing unit which outputs one of these four classes (Odor1, Odor2, Odor3, Other). The system triggers the fan a second time to release the scent from the diffuser.
Le résultat de l'unité de traitement est comparé à l'odeur sélectionnée et affiche le résultat sur le voyant adéquat : le voyant vert (9.1) pour température en dessous de 37.3 et réponse correcte, le voyant rouge pour température en dessus de 37.3 ou pour réponse fausse. The result of the processing unit is compared to the selected odor and displays the result on the appropriate light: the green light (9.1) for temperature below 37.3 and correct response, the red light for temperature above 37.3 or for wrong answer.
Application du deep learning : Application of deep learning:
La méthode du Deep Learning est utilisé dans le contexte de la présente invention pour la reconnaissance vocale des mots prononcés par les individus subissant le test d'odorat. Le modèle utilisé est à base de réseaux de neurones de convolution (CNN) est appliqué pour classifier les caractéristiques MFCC du speech de l'utilisateur. L'acceptance de multi-langue consiste à classifier la réponse de l'utilisateur dans dix classes : Odeurl_Arabe, Odeurl_Francais, Odeurl_Anglais, Odeur2_Arabe, Odeur2_Francais, Odeur2_Anglais, Odeur3_Arabe, Odeur3_Francais, Odeur3_Anglais, Autre, et de réduire le domaine de réponse en quatre : Odeurl, Odeur 2, Odeur 3, autre.
Description des dessins The Deep Learning method is used in the context of the present invention for the vocal recognition of the words pronounced by the individuals undergoing the smell test. The model used is based on convolutional neural networks (CNN) and is applied to classify the MFCC characteristics of the user's speech. Multi-language acceptance consists of classifying the user's response into ten classes: Odorl_Arabe, Odorl_French, Odorl_English, Odor2_Arabic, Odor2_French, Odor2_English, Odor3_Arabic, Odor3_French, Odor3_English, Other, and to reduce the response domain into four: Odor1, Odor 2, Odor 3, other. Description of the drawings
La figure 1 représente le dispositif de test combiné objet de l'invention, ce dispositif est composé de (les références se rapportent au dessins 1) : Figure 1 shows the combined test device object of the invention, this device is composed of (the references refer to drawings 1):
1 - carte de gestion Raspberry 1 - Raspberry management card
2 - Batterie 2 - Battery
3 - Moteur pour basculer entre les cartouches 4.1,4.2, 4.3 - Cartouches 3 - Engine to switch between cartridges 4.1,4.2, 4.3 - Cartridges
5 - Canaux 5 - Channels
6 - brumisateur 6 - fogger
7 - ventilateur 7 - fan
8 - Microphone 8 - Microphone
9.1, 9.2 - Voyants d'état de la réponse 9.3, 9.4 - Voyants d'état du dispositif 9.1, 9.2 - Response Status LEDs 9.3, 9.4 - Device Status LEDs
10 - Haut-parleur 10 - Loudspeaker
11 - Capteur thermique infra-rouge 11 - Infrared thermal sensor
12 - Ecran pour lecture de température 12 - Display for temperature reading
13 - Diffuseur 13 - Diffuser
14 - Bouton d'allumage du dispositif 14 - Device ignition button
15 - Bouton de déclenchement du test 15 - Test trigger button
La figure 2 représente une Description fonctionnelle du dispositif.
Figure 2 shows a Functional Description of the device.
Claims
1. Dispositif intelligent pour détection de personnes manifestant des symptômes d'infection par COVID-19 comprenant : 1. Intelligent device for detecting people showing symptoms of infection by COVID-19 comprising:
Un Capteur thermique infra-rouge (11) An infrared thermal sensor (11)
- Au moins trois Cartouches d'arômes (4.1, 4.2, 4.3) - At least three Flavor Cartridges (4.1, 4.2, 4.3)
Un diffuseur d'odeur (13) provenant des arômes stockés au niveau des cartouches (4.1, 4.2, 4.3) An odor diffuser (13) originating from the aromas stored at the level of the cartridges (4.1, 4.2, 4.3)
Un sélecteur de cartouches d'odeurs (3) A selector of odor cartridges (3)
Un brumisateur (6) A fogger (6)
Un ventilateur (7) A fan (7)
- Un Haut-parleur (10) - A loudspeaker (10)
Un microphone (8) A microphone (8)
Des voyants (9) et des boutons d'opérations (14,15) LEDs (9) and operation buttons (14,15)
Un écran d'affichage (12) A display screen (12)
Une carte électronique de commande (1) An electronic control card (1)
2. Dispositif selon la revendication précédente caractérisé en ce que la carte de commande (1) sélectionne aléatoirement un arôme à pulvériser pour le test par le sélecteur (3) 2. Device according to the preceding claim characterized in that the control card (1) randomly selects an aroma to be sprayed for the test by the selector (3)
3. Dispositif selon la revendication précédente caractérisé en ce que la voix humaine est enregistrée et traitée en appliquant un algorithme Automatic Speech Récognition (ASR). 3. Device according to the preceding claim, characterized in that the human voice is recorded and processed by applying an Automatic Speech Recognition (ASR) algorithm.
4. Dispositif selon la revendication précédente caractérisé en ce que les voyants s'allument en fonction de la correspondance du mot prononcée (en multi-langue) par l'individu testé avec l'arôme pulvérisé. 4. Device according to the preceding claim, characterized in that the indicators light up according to the correspondence of the word pronounced (in multi-language) by the individual tested with the sprayed aroma.
5. Méthode de test des symptômes d'infection par COVID-19 comportant les étapes suivantes : o Prélèvement de la température par le dispositif de la revendication 1 affichage de la température. o Sélection aléatoire et pulvérisation d'un arôme parmi les arômes stockés dans les cartouches dudit dispositif, o Enregistrement de la réponse. o Extraction des caractéristiques MFCC à partir de la réponse enregistrée, o Classification des caractéristiques MFCC par un modèle d'apprentissage profond à base de réseaux de neurones de convolution (CNN) o Analyse des réponses depuis trois langues possibles et normalisation une réponse représentative. o Comparaison de résultat de reconnaissance vocale par le modèle CNN avec l'arôme sélectionné à l'étape 2. o Activation des voyants en fonction du résultat obtenu.
5. Method for testing the symptoms of infection by COVID-19 comprising the following steps: o Sampling of the temperature by the device of claim 1 temperature display. o Random selection and spraying of an aroma from among the aromas stored in the cartridges of said device, o Recording of the response. o Extraction of MFCC features from the recorded response, o Classification of MFCC features by a deep learning model based on convolutional neural networks (CNN) o Analysis of responses from three possible languages and normalization of a representative response. o Comparison of voice recognition result by the CNN model with the aroma selected in step 2. o Activation of the lights according to the result obtained.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
MA52683A MA52683B1 (en) | 2021-03-09 | 2021-03-09 | Smart device for detecting people showing symptoms of covid-19 infection |
MA52683 | 2021-03-09 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022191685A1 true WO2022191685A1 (en) | 2022-09-15 |
Family
ID=78463852
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/MA2021/050015 WO2022191685A1 (en) | 2021-03-09 | 2021-10-13 | Smart device for detecting persons displaying symptoms of covid-19 infection |
Country Status (2)
Country | Link |
---|---|
MA (1) | MA52683B1 (en) |
WO (1) | WO2022191685A1 (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190314601A1 (en) * | 2018-04-13 | 2019-10-17 | The Regents Of The University Of California | Cognition and memory enhancement via multiple odorant stimulation |
US10902955B1 (en) * | 2020-05-01 | 2021-01-26 | Georgetown University | Detecting COVID-19 using surrogates |
-
2021
- 2021-03-09 MA MA52683A patent/MA52683B1/en unknown
- 2021-10-13 WO PCT/MA2021/050015 patent/WO2022191685A1/en active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190314601A1 (en) * | 2018-04-13 | 2019-10-17 | The Regents Of The University Of California | Cognition and memory enhancement via multiple odorant stimulation |
US10902955B1 (en) * | 2020-05-01 | 2021-01-26 | Georgetown University | Detecting COVID-19 using surrogates |
Non-Patent Citations (1)
Title |
---|
JOURNALS ESAT ET AL: "ISOLATED WORDS RECOGNITION USING MFCC, LPC AND NEURAL NETWORK Related papers SPECT RAL FEAT URES ANALYSIS FOR HINDI SPEECH RECOGNIT ION SYST EM eSAT Journals MACHINE LEARNING APPROACH FOR VOICED/UNVOICED/SILENCE SPEECH SEGMENT DET ECT ION ISOLATED WORDS RECOGNITION USING MFCC, LPC AND NEURAL NETWORK", ARTIFICIAL NEURAL NETWORK, 1 June 2015 (2015-06-01), pages 146 - 149, XP055880169, Retrieved from the Internet <URL:https://d1wqtxts1xzle7.cloudfront.net/41934130/ISOLATED_WORDS_RECOGNITION_USING_MFCC__LPC_AND_NEURAL_NETWORK-with-cover-page-v2.pdf?Expires=1642442770&Signature=LNCkUH-QTesr3dRuxLk7DQZQbq6zEulz-MXoSk82BE6q0D~qdhKd11jM-~wGH9-U~PhS754it9EMFPyiKmZo0NgAJNump9IeQ3tAZhB6sbVX8zzyl5KOGmhp5bYla03D-fkNy3clF2z> [retrieved on 20220117] * |
Also Published As
Publication number | Publication date |
---|---|
MA52683B1 (en) | 2022-12-30 |
MA52683A1 (en) | 2022-09-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101114606B1 (en) | Music interlocking photo-casting service system and method thereof | |
CN109658923B (en) | Speech quality inspection method, equipment, storage medium and device based on artificial intelligence | |
CN107077796B (en) | Storage medium, network test anti-cheating method, system and equipment | |
US8972266B2 (en) | User intent analysis extent of speaker intent analysis system | |
US8306814B2 (en) | Method for speaker source classification | |
US20040001616A1 (en) | Measurement of content ratings through vision and speech recognition | |
JPH02503976A (en) | remote confinement device | |
US20100278377A1 (en) | Methods for electronically analysing a dialogue and corresponding systems | |
Bell et al. | Irrelevant speech disrupts item-context binding | |
Jones | Danger-Voiceprints Ahead | |
CN109166629A (en) | The method and system of aphasia evaluation and rehabilitation auxiliary | |
WO2022191685A1 (en) | Smart device for detecting persons displaying symptoms of covid-19 infection | |
CA2592994A1 (en) | Method for data search in a database | |
JP2006230548A (en) | Physical condition judging device and its program | |
SE2050930A1 (en) | Method and system for determination and classification of intoxicating substance in a breath sample facilitated by a user interaction scheme | |
CN105225664B (en) | Information verification method and device and sound sample generation method and device | |
Gajšek et al. | Multi-modal emotional database: AvID | |
Wagner et al. | Perceptual recognition of familiar voices using falsetto as a type of voice disguise | |
Malsch et al. | Reporting on police interrogations: Selection effects and bias related to the use of text, video and audiotape. | |
JP2020091609A (en) | Learning support device, learning support method and program | |
Jaimes et al. | Affective meeting video analysis | |
Fredouille et al. | Automatic Detection of Abnormal Zones in Pathological Speech. | |
Mackie et al. | Assessment of evaluation measures for processed speech | |
JP6032584B2 (en) | Hearing ability evaluation method, answer sheet and hearing ability evaluation system used therefor. | |
Burnham et al. | The effect of tonal information on auditory reliance in the McGurk effect |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21801239 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21801239 Country of ref document: EP Kind code of ref document: A1 |