WO2023048680A1 - A baby voice translation system - Google Patents

A baby voice translation system Download PDF

Info

Publication number
WO2023048680A1
WO2023048680A1 PCT/TR2022/050979 TR2022050979W WO2023048680A1 WO 2023048680 A1 WO2023048680 A1 WO 2023048680A1 TR 2022050979 W TR2022050979 W TR 2022050979W WO 2023048680 A1 WO2023048680 A1 WO 2023048680A1
Authority
WO
WIPO (PCT)
Prior art keywords
baby
voice
crying
sounds
smartphone
Prior art date
Application number
PCT/TR2022/050979
Other languages
French (fr)
Inventor
Numan YANIKLAR
Original Assignee
Yaniklar Numan
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yaniklar Numan filed Critical Yaniklar Numan
Publication of WO2023048680A1 publication Critical patent/WO2023048680A1/en

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state

Definitions

  • the invention relates to a baby voice translation system that converts the crying sounds of babies into text and/or form and/or voice speech and/or voice message that other people, especially mothers and fathers, can understand.
  • the invention eliminates the disadvantages described above.
  • the baby voice translation system developed in the invention the sounds made by the baby are taken and compared with the five different crying sounds explaining the needs of the baby that were previously installed on it thanks to a software.
  • the crying sounds made by the baby are taken and sent to the cloud system, where the crying sounds are analyzed with artificial intelligence-supported software.
  • the comparison (analysis) made by the software if the sound received from the baby is not one of the five different crying sounds that describe the baby's needs, no action is taken.
  • I’m uncomfortable It is a picture or a sound, such as a text in the form of a text and/or a photo of a baby eating.
  • the mother and/or father who see a text and/or picture and/or hear the voice message, ensures that the need expressed in the message is met. For example, if the message is "I'm hungry", they feed the baby.
  • FIG. 1 The schematic view of the baby voice translation system developed in the invention
  • Figure 2 It is the schematic view of the wifi module.
  • FIG. 3 Schematic view of the speaker module.
  • Figure 4 Schematic view of the microphone module.
  • Figure 5 It is the schematic view of the micro controller and the led display.
  • the invention is a baby voice translation system (1), a microphone module (1.1.2) that allows to receive the baby (1.5) voice, a wifi module (1.1.3),
  • a microcontroller (1.1.1) that enables the baby (1.5) sounds received over the microphone module (1.1.2) to be sent to the cloud system (1.2) via a wifi module (1.1.3), a cloud system (1.2) and information about five different types of crying sounds and what the equivalent of these crying sounds are; comparing the baby (1.5) sound coming from the microphone module (1.1.2) with the five different crying sounds loaded on it; If the sound coming from the baby (1.5) is one of the five different crying sounds, the text corresponding to the crying sound detected on the mother's smartphone (1.3) and/or the father's smartphone (1.4) and/or the LED display (1.1.1.1) and/or an artificial intelligence supported software located in the cloud system (1.2) that sends the shape and/or voice speech and/or voice message
  • Baby voice translator (1.1), a microcontroller (1.1.1) with an led display (1.1.1.1) on it, microphone module (1.1.2),
  • the Baby Voice Translator (1.1) developed in the invention is placed next to the baby (1.5).
  • the baby voice translator (1.1) which receives the sounds of the baby (1.5) with the microphone module (1.1.2), sends the sounds received by the microcontroller (1.1.1) via the wifi module (1.1.3) to the cloud system (1.2).
  • the information corresponding to this recorded crying sound can only be sent to the mother's smartphone (1.3) or only to the father's smartphone (1.4) or to both the mother's smartphone (1.3) and it sends it to the fathers smart phone (1.4) or only on the led screen (1.1.1.1) or to the mother's smart phone (1.3), to the father's smart phone (1.4) and over the led screen (1.1.1.1).
  • Messages such as "I'm hungry”, “I'm sleepy”, "I have gas” are sent to the mother's smartphone (1.3) and/or father's smartphone (1.4) and/or the LED screen (1.1.1.1). The mother and / or father who see this message do what is necessary.
  • the baby (1.5) is fed. If he sees the message “I'm sleepy”, he puts the baby (1.5) to bed.
  • the LED display (1.1.1.1) the message can also be sent to a computer.
  • Messages may be in the form of "I am hungry” and similar expressions and/or in the form of a picture of a baby (1.5) eating and similar pictures and/or the words "I am hungry” and similar words spoken aloud and/or in the form of voice messages.
  • five different pictures can be seen on the mother's smartphone (1.3) and/or the father's smartphone (1.4) and/or the LED screen (1.1.1.1).
  • the software in the cloud system (1.2) detects the sound coming from the baby (1.5) corresponding to the "I am sleepy” message, it ensures that the music previously loaded on it is output from the speaker module (1.1.4). In this way, the baby (1.5) can fall asleep in a short time with lullabies and similar pleasant sounds.
  • the invention is a method of converting baby (1.5) voice into text and/or shape and/or voice speech and/or voice message with baby voice translation system (1). placing the baby voice translator (1.1) next to the baby (1.5),
  • the baby's (1.5) voice is received by the microphone module (1.1.2), sending the baby (1.5) sounds received by the microphone module (1.1.2) to the cloud system (1.2) via a Wi-Fi module (1.1.3) controlled and commanded by a microcontroller (1.1.1),

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Psychiatry (AREA)
  • Hospice & Palliative Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Child & Adolescent Psychology (AREA)
  • Machine Translation (AREA)
  • Telephone Function (AREA)

Abstract

Invention, the crying sounds produced by babies are written and / or shaped and/or audible speech and / or audible speech that other people, especially mom and dad, will understand it is about a baby voice translation system that converts it into a message.

Description

A BABY VOICE TRANSLATION SYSTEM
Technical Field:
The invention relates to a baby voice translation system that converts the crying sounds of babies into text and/or form and/or voice speech and/or voice message that other people, especially mothers and fathers, can understand.
State of the Art:
Babies express all their needs with the sounds they make. When the baby who makes a sound does not get what he wants, he starts to cry and transmits his request predominantly in the form of crying.
Studies have shown that babies cry in five different types. The language that consists of these five different types of crying is called "dunstan baby language".
Baby with five different types of crying;
- Hungry
- that his sleep came
- there is gas in the stomach area,
- that there is gas in the intestinal area, and
- uncomfortability
Today, it is very difficult for other people, especially mothers and fathers, to understand the messages that babies convey by crying. This situation both causes babies to be very battered to express their wishes and causes other people, especially mothers and fathers, to take longer to understand babies, or even not to understand them at all. Inability to understand or difficult to understand the sounds babies make by crying reduces the quality of life of the mother, father and baby.
Description of the Invention:
The invention eliminates the disadvantages described above.
Thanks to the baby voice translation system developed in the invention; the sounds made by the baby are taken and compared with the five different crying sounds explaining the needs of the baby that were previously installed on it thanks to a software. (The crying sounds made by the baby are taken and sent to the cloud system, where the crying sounds are analyzed with artificial intelligence-supported software.) As a result of the comparison (analysis) made by the software, if the sound received from the baby is not one of the five different crying sounds that describe the baby's needs, no action is taken. Babies sound, from one of five different cries that have been installed on it before, this is the article for sound and/or shape and/or voice and/or audio message mother's mobile phone and/or your father's mobile phone and/or sends the LED screen.
Sent message;
"I’m sleepy"
Or
"I’m hungry"
Or
"I have gas in the stomach area"
Or
"I have gas in the intestinal area"
Or
I’m uncomfortable It is a picture or a sound, such as a text in the form of a text and/or a photo of a baby eating. In this way, the mother and/or father, who see a text and/or picture and/or hear the voice message, ensures that the need expressed in the message is met. For example, if the message is "I'm hungry", they feed the baby.
Thanks to the baby voice translation system developed in the invention, all mothers and/or fathers will understand what their babies want at that moment and will meet their needs immediately. In this way, mother, father and baby communication will be at the highest level and the quality of life will increase.
Description of References:
1. Baby Voice Translation System
1.1.Baby Voice Translator
1.1.1. Microcontroller
1.1.1.1. Led Display
1.1.2. Microphone Module
1.1.3. Wifi Module
1.1.4. Speaker Module
1.2. Cloud System
1.3. Mother's Smartphone
1.4.Father's Smartphone
1.5. Baby
Description of the Figures:
Figure 1 The schematic view of the baby voice translation system developed in the invention
Figure 2 It is the schematic view of the wifi module.
Figure 3 Schematic view of the speaker module.
Figure 4 Schematic view of the microphone module. Figure 5 It is the schematic view of the micro controller and the led display.
Detailed Description of The Invention:
The invention is a baby voice translation system (1), a microphone module (1.1.2) that allows to receive the baby (1.5) voice, a wifi module (1.1.3),
A microcontroller (1.1.1) that enables the baby (1.5) sounds received over the microphone module (1.1.2) to be sent to the cloud system (1.2) via a wifi module (1.1.3), a cloud system (1.2) and information about five different types of crying sounds and what the equivalent of these crying sounds are; comparing the baby (1.5) sound coming from the microphone module (1.1.2) with the five different crying sounds loaded on it; If the sound coming from the baby (1.5) is one of the five different crying sounds, the text corresponding to the crying sound detected on the mother's smartphone (1.3) and/or the father's smartphone (1.4) and/or the LED display (1.1.1.1) and/or an artificial intelligence supported software located in the cloud system (1.2) that sends the shape and/or voice speech and/or voice message
Baby voice translator (1.1), a microcontroller (1.1.1) with an led display (1.1.1.1) on it, microphone module (1.1.2),
- wifi module (1.1.3) and preferably a speaker module (1.1.4) The baby (1.5) cries in five different sounds;
- Hungry
- that his sleep came
- there is gas in the stomach area,
- that there is gas in the intestinal area, and
- uncomfortability
The Baby Voice Translator (1.1) developed in the invention is placed next to the baby (1.5). The baby voice translator (1.1), which receives the sounds of the baby (1.5) with the microphone module (1.1.2), sends the sounds received by the microcontroller (1.1.1) via the wifi module (1.1.3) to the cloud system (1.2). There is an artificial intelligence supported software in the cloud system (1.2). The software that compares the sounds received from the baby (1.5) with the five different crying sounds pre-loaded on it; If the sounds taken from the baby (1.5) are any other sound other than five different crying sounds, no action is taken. If the sounds taken from the baby (1.5) are one of the five different crying sounds, the information corresponding to this recorded crying sound can only be sent to the mother's smartphone (1.3) or only to the father's smartphone (1.4) or to both the mother's smartphone (1.3) and it sends it to the fathers smart phone (1.4) or only on the led screen (1.1.1.1) or to the mother's smart phone (1.3), to the father's smart phone (1.4) and over the led screen (1.1.1.1). Messages such as "I'm hungry", "I'm sleepy", "I have gas" are sent to the mother's smartphone (1.3) and/or father's smartphone (1.4) and/or the LED screen (1.1.1.1). The mother and / or father who see this message do what is necessary. For example, if the message "I am hungry" is seen, the baby (1.5) is fed. If he sees the message "I'm sleepy", he puts the baby (1.5) to bed. In addition to the smart mobile phone, the LED display (1.1.1.1), the message can also be sent to a computer.
Messages may be in the form of "I am hungry" and similar expressions and/or in the form of a picture of a baby (1.5) eating and similar pictures and/or the words "I am hungry" and similar words spoken aloud and/or in the form of voice messages. In other words, in response to five crying sounds, five different pictures can be seen on the mother's smartphone (1.3) and/or the father's smartphone (1.4) and/or the LED screen (1.1.1.1).
When the software in the cloud system (1.2) detects the sound coming from the baby (1.5) corresponding to the "I am sleepy" message, it ensures that the music previously loaded on it is output from the speaker module (1.1.4). In this way, the baby (1.5) can fall asleep in a short time with lullabies and similar pleasant sounds.
The invention is a method of converting baby (1.5) voice into text and/or shape and/or voice speech and/or voice message with baby voice translation system (1). placing the baby voice translator (1.1) next to the baby (1.5),
- the baby's (1.5) voice is received by the microphone module (1.1.2), sending the baby (1.5) sounds received by the microphone module (1.1.2) to the cloud system (1.2) via a Wi-Fi module (1.1.3) controlled and commanded by a microcontroller (1.1.1),
Comparison of the five different crying sounds from the microphone module (1.1.2) with the baby (1.5) voice loaded on it by the artificial intelligence supported software in the cloud system (1.2) in which the five different types of crying sounds and the information about the equivalent of these crying sounds are loaded, If the sound coming from the baby (1.5) is one of the five different crying sounds, the text corresponding to the crying sound detected on the mother's smartphone (1.3) and/or the father's smartphone (1.4) and/or the LED screen (1.1.1.1) and/or sending the form and/or voice speech and/or voice message by an artificial intelligence supported software located in the cloud system (1.2).

Claims

CLAIMS - The invention is a baby voice translation system (1), the feature of which is; a microphone module (1.1.2) that allows to receive the voice of the baby (1 -5), a wifi module (1.1.3), a microcontroller (1.1.1) that allows baby (1.5) voices received via the microphone module (1.1.2) to be sent to the cloud system (1.2) via a wifi module (1.1.3), a cloud system (1.2) and information about five different types of crying sounds and what the equivalent of these crying sounds are; comparing the baby sound coming from the microphone module (1.1.2) with the five different crying sounds loaded on it; If the sound coming from the baby (1.5) is one of the five different crying sounds, the text corresponding to the crying sound detected on the mother's smartphone (1.3) and/or the father's smartphone (1.4) and/or the LED screen (1.1.1.1) and/or an artificial intelligence supported software located in the cloud system (1.2) that sends the shape and/or voice speech and/or voice message. - It is the baby voice translation system (1) mentioned in Claim 1, and its feature is; a microcontroller (1.1.1) with an led display (1.1.1.1) on it, microphone module (1.1.2), wifi module (1.1.3) and preferably from a speaker module (1.1.4) the resulting baby voice translation device (1.1). - It is the baby voice translation system (1) mentioned in Claim 1, and its feature is; The message sent to the mother's smartphone (1.3) and/or the father's smartphone (1.4) and/or the LED screen (1.1.1.1) may be in the form of "I am hungry" and similar expressions, as well as "a picture of a baby eating (1.5)" or It includes artificial intelligence supported software in the cloud system (1.2), which can be in the form of pictures and/or voice conversation and/or voice message as desired. - It is the baby voice translation system (1) mentioned in Claim 1, and its feature is; when the artificial intelligence supported software in the cloud system (1.2) detects the sound coming from the baby (1.5) corresponding to the "I am sleepy" message; It contains the speaker module (1.1.4) that allows the music loaded on it to come to the baby. - The invention is a method of translating the baby's voice (1.5) into writing and/or shape and/or voice speech and/or voice message with the baby voice translation system (1), and its feature is; placing the baby voice translation device (1.1) next to the baby (1.5), the baby's (1.5) voice is received by the microphone module (1.1.2),
9 sending the baby (1.5) sounds received by the microphone module (1.1.2) to the cloud system (1.2) via a wifi module (1.1.3) controlled and commanded by a microcontroller (1.1.1),
Comparison of the five different crying sounds from the microphone module
(1.1.2) with the baby (1.5) voice loaded on it by the artificial intelligence supported software in the cloud system (1.2) in which the five different types of crying sounds and the information about the equivalent of these crying sounds are loaded,
If the sound coming from the baby (1.5) is one of the five different crying sounds, the text corresponding to the crying sound detected on the mother's smartphone (1.3) and/or the father's smartphone (1.4) and/or the LED screen (1.1.1.1) and/or sending the form and/or voice speech and/or voice message by an artificial intelligence supported software located in the cloud system
(1.2) consists of process steps.
10
PCT/TR2022/050979 2021-09-21 2022-09-13 A baby voice translation system WO2023048680A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
TR2021/014791 2021-09-21
TR2021/014791A TR2021014791A2 (en) 2021-09-21 2021-09-21 A BABY SOUND TRANSLATION SYSTEM

Publications (1)

Publication Number Publication Date
WO2023048680A1 true WO2023048680A1 (en) 2023-03-30

Family

ID=84046118

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/TR2022/050979 WO2023048680A1 (en) 2021-09-21 2022-09-13 A baby voice translation system

Country Status (2)

Country Link
TR (1) TR2021014791A2 (en)
WO (1) WO2023048680A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107657965A (en) * 2017-09-22 2018-02-02 许灿丽 Vagitus identifier and knowledge method for distinguishing
CN107886953A (en) * 2017-11-27 2018-04-06 四川长虹电器股份有限公司 A kind of vagitus translation system based on expression and speech recognition
CN109697991A (en) * 2019-02-20 2019-04-30 厦门点圈科技有限公司 A kind of vagitus translation system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107657965A (en) * 2017-09-22 2018-02-02 许灿丽 Vagitus identifier and knowledge method for distinguishing
CN107886953A (en) * 2017-11-27 2018-04-06 四川长虹电器股份有限公司 A kind of vagitus translation system based on expression and speech recognition
CN109697991A (en) * 2019-02-20 2019-04-30 厦门点圈科技有限公司 A kind of vagitus translation system

Also Published As

Publication number Publication date
TR2021014791A2 (en) 2021-10-21

Similar Documents

Publication Publication Date Title
Bruderer et al. Sensorimotor influences on speech perception in infancy
Lam et al. Mommy, speak clearly: Induced hearing loss shapes vowel hyperarticulation
US20200365136A1 (en) Speech synthesizing devices and methods for mimicking voices of public figures
US11115539B2 (en) Smart voice system, method of adjusting output voice and computer readable memory medium
US10791404B1 (en) Assisted hearing aid with synthetic substitution
US20180213396A1 (en) Privacy control in a connected environment based on speech characteristics
JP6945130B2 (en) Voice presentation method, voice presentation program, voice presentation system and terminal device
EP1703492B1 (en) System and method for personalised text-to-voice synthesis
Keitel et al. The use of intonation for turn anticipation in observed conversations without visual signals as source of information
WO2019240035A1 (en) Conversation assistance device, conversation assistance method, and program
Kalashnikova et al. Infant‐directed speech to infants at risk for dyslexia: A novel cross‐dyad design
JP7095684B2 (en) Information processing equipment, information processing method, program
WO2023048680A1 (en) A baby voice translation system
Kersken et al. Listeners can extract meaning from non-linguistic infant vocalisations cross-culturally
KR102346158B1 (en) Emotional Intelligence Education AI Speaker System
KR20160142079A (en) Language interpreter, speech synthesis server, speech recognition server, alarm device, lecture local server, and voice call support application for deaf auxiliaries based on the local area wireless communication network
KR20190007129A (en) Camera Apparatus and Method for Calling Protector of Infant
KR20160144104A (en) Educational terminal based voice recognition, education system based voice recognition
Olaosun et al. Assistive technology for hearing and speech disorders
KR102179220B1 (en) Electronic Bible system using speech recognition
CN105791713A (en) Intelligent device for playing voices and captions synchronously
Newman et al. Communication development in infancy
CN109346058B (en) Voice acoustic feature expansion system
JP2019018336A (en) Device, method, program, and robot
KR20240108146A (en) Customized artificial intelligence output system

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: 22873313

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE