DESC:FIELD OF INVENTION
The present invention relates to a system that enables uploading audio as well as video recordings without background noise. More particularly, it relates to a system which facilitates audio recording by supressing background noise and enhancing specific sound as well as capturing a face of the user while video recording irrespective of background ambience and noise.
BACKGROUND OF INVENTION
Thanks to the emergence of high-speed Internet and reduced prices of high-quality web cameras! Wide-spread instant messaging software supports voice/video chatting, where people can view each other while talking. Due to the advent of social media, there is a massive surge in digital content which people, businesses or governments are sharing with each other. Particularly in this new normal, it has become imperative to have audio as well as video communication without any disturbances. E-learning platforms are mandating the teaching fraternity to conduct/post/record their content in the form of virtual modules.
Most of the time it happens that content creators or normal people create video content or record audio in a noisy place. That noise in the videos and audio destroys their quality and also irritates the viewers or listeners. It may also lose the audience if the content is uploaded on any type of social media by some content creator. Additionally, content creation becomes challenging as people don't want to share their location, background scenario and face difficulty in clarity of voice recording due to noisy place, etc. Technically speaking, noise in audio and video recordings is defined based on audio frequency and audio decibel, which is loud, disruptive and out of the comfort area to human hearing. Also, all kinds of unwanted sounds in video recordings are noises. It could be wind sound, man's vocal cord, motor noises, etc. For example, when a song is recorded, all sounds except for human voice are noises; when a person mainly wants to collect ocean wave sounds, then all the others are noises.
It is to worth noting that extremely loud noises cannot only harm hearing but also speaking abilities. Inability to speak and understand each other may lead to miscommunication and affect productivity.
Secondly, there are privacy concerns with video conferencing as Social Etiquettes in real life are ingrained into our social life. Also, people from rural area who are not exposed to the social media much yet have skill sets which can be showcased to be useful to the world. In such cases there may be unwanted fear, embarrassment while appearing in front of such virtual platforms which obstructs the presentation of their skills to outside world. Such people are remaining deprived of the due credit and remuneration they deserve just because they find it difficult and uncomfortable in communicating with the world with the help of available digital platforms. In such cases the usage of social media more frequently increases FOMO and feelings of inadequacy, dissatisfaction, and isolation.
In case of virtual communication platforms available at present, such as ZOOM, Google Meet, etc. offer options like blurring of the background or applying virtual background so that the surrounding of the attendant is avoided from facing any awkward situation yet there is no provision for reducing or eliminating the background noise.
Disadvantages of the existing platforms:
? The prime requirement is to have perfect lighting conditions either natural or studio based. This is because it also takes into consideration the background of the end user.
? Production time and cost is more. An experienced visual effects supervisor for perfect video shooting needs to be hired which involves time as well as cost factor. These platforms have their set standards which need to be complied to get high quality video recordings which is not in the purview of all the common end users.
? Spills: The presently available platforms pose a risk of leaving coloured spill on the edges of character and prop if optimum distance is not maintained between the camera and the end user.
? Some platforms offer background and have a risk of the user’s cloth colour matching with the background colour.
The above-mentioned points reveal that in case of video recordings, the existing platforms need to emphasise on the exterior factors such as presence of adequate light, have limitation on the cloth colour of the user, need of hiring expert professionals, etc.
Thus, in order to contribute as a social impact by encouraging all segments of people to open up, express themselves for boosting their confidence and protecting their privacy requirement, it is evident to have a universal system. Hence, a need exists for a noise reduction and face isolation system and method that offers audio and video recordings with enhanced quality and least noise with face catching feature.
The proposed invention takes care of awkwardness of the user being afraid/ concerned about the location, distraction, attire, etc. Moreover, this invention will help people from rural places to express themselves without hesitation and also to sell/ highlight the product, services or the skill set, etc.
OBJECT OF THE INVENTION
• Primary object of the present invention is to offer a noise reduction and face isolation system with distinct features.
• Further object of the present invention is to provide a method to eliminate the background noise during audio as well as video recordings.
• Yet further object of the present invention is to develop a noise reduction and face isolation system and method to enable the user to upload a video irrespective of user’s extrinsic features arresting the facial part.
• Another object of the present invention is to provide a noise reduction and face isolation system and method to upload the audio recordings irrespective of the location by enhancing the user’s voice and suppressing the surrounding noise.
• Yet another object of the present invention is to provide a noise reduction and face isolation system to offer the end users the ease of recording and uploading the video as well as audio from any place to showcase the strength, skills as well as emergency situations to the wide group of people.
• Yet another object of the present invention is to apply a noise reduction and face isolation system and method thereof to generate plurality of business opportunities for outreaching business personnel by end users.
• Further another object of the present invention is to provide a noise reduction and face isolation system to bring a massive social impact by focusing on “Learning with Positivity”.
• Further another object of the present invention is to provide a noise reduction and face isolation system to demonstrate a clear message of equality regardless of gender, socioeconomic background, or otherwise and to reflect that all the users are same and come from the same starting point.
• Further another object of the present invention is to offer a noise reduction and face isolation system to enable the user to remain secluded if desired due to the face catching feature of the digital platform.
SUMMARY
A noise reduction and face isolation system is comprised of an acoustic noise elimination module and an optical noise elimination module. The acoustic noise elimination module further comprises communicatively connected means for receiving an audio signal, means for recording and saving an audio signal, means for identifying noise, means for cancellation of noise and means of posting the audio with prime voice. Whereas the optical noise elimination module further consists of communicatively interconnected means for capturing real image, means of selecting background, means of detecting visage and recognizing pattern, means of performing computational analysis for background of said video and means for posting the corrected video.
For effective use of noise reduction and face isolation system, first audio signal from the user is received with the help of audio receivers which is further recorded and saved as prime voice to an audio engine. The acoustic noise elimination module receives audio signal from the user, records and saves the received audio signal, identifies acoustic noise, compares it with the prime voice and eliminates the acoustic noise by artificial neural networks to enable the user to create and post an audio recording without noise by enhancing the voice quality of the user.
Creation of a video by isolating face of the user is accomplished by using the optical noise elimination module which comprises of the steps such as capturing the real image, selecting the background, detecting foreground, performing computational analysis for correcting the background and eliminating optical noise by using artificial neural network to enhance the visage. The user can correct the background as per his choice by changing, blurring or eliminating the background completely. Also, the user can highlight his facial parts by hiding reminder of the body as well as maintain his identity anonymous by selecting a facial cover. The user can combine said audio recording by the acoustic noise elimination module and said video recording by the optical noise elimination module to create an audiovisual with recorded prime voice and isolated face of the user.
The proposed invention using noise reduction and face isolation system allows the user to record audio and video from any location either by isolating and displaying specifically facial features or by maintaining his/her identity being anonymous. It is also helpful to reveal only the face of the end user thereby removing any preconceived socioeconomic barriers.
BRIEF DESCRIPTION OF DRAWINGS
FIG.1 is a realistic drawing of an acoustic noise elimination module (100) of noise reduction and face isolation system of the present invention depicting the interconnectivity of different means of said module (100).
FIG.2 is a realistic drawing of an optical noise elimination module (200) of noise reduction and face isolation system of the present invention depicting the interconnectivity of different means of said module (200).
FIG.3 is a flow chart illustrating stage wise acoustic noise elimination and optical noise elimination of the present invention.

DETAILED DESCRIPTION OF THE INVENTION
Before the present invention is described, it is to be understood that this invention is not limited to particular methodologies described, as these may vary as per the person skilled in the art. It is also to be understood that the terminology used in the description is for the purpose of describing the particular embodiments only and is not intended to limit the scope of the present invention. Throughout this specification, the word “comprises”, or variations such as “comprises” or “comprising”, will be understood to imply the inclusion of a stated element, integer or step, or group of elements, integers or steps, but not the exclusion of any other element, integer or step, or group of elements, integers or steps. The use of the expression “at least” or “at least one” suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the invention to achieve one or more of the desired objects or results.
This will be readily apparent to those skilled in the art, the present invention may easily be produced in other specific forms without departing from its essential characteristics. The present embodiments are, therefore, to be considered as merely illustrative and not restrictive, the scope of the invention being indicated by the claims rather than the foregoing description, and it will be appreciated that many variations in detail are possible without departing from the scope and spirit of the invention and all such variations therefore intended to be embraced therein.
In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address any of the problems discussed above or might address only one of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein. Example embodiments of the present disclosure are described below, as illustrated in various drawings in which like reference numerals refer to the same parts throughout the different drawings.
Reference will now be made in detail to embodiments of the invention, one or more examples of which are illustrated in the description. Each example is provided by the way of explanation of the invention and not meant as limitation of the invention. features illustrated or described as part of one embodiment to yield still third embodiment. It is intended that the present invention includes these and other modifications and variations. The variation and inclusion of technological features and their applications in different circumstances applied to enhance the audio and video quality shall not limit the scope of the invention.
To get high quality video recordings, the presently available systems have their set standards, and they also require perfect distance and lighting conditions either natural or studio which otherwise pose a risk of leaving colour spills on edges of the image. This further increases the production cost and time. Various virtual communication available platforms such as Zoom, Google Meet don’t offer options for eliminating the background, noise and provision for maintaining anonymity by the user. The user needs to consider various socioeconomic factors such as clothes, gender, race, colour, etc while recording the video. The content creator shall not be deprived of showcasing his creativity due to the above limiting factors. Hence, a need exists for a system and method that offers audio and video recordings with enhanced quality and least noise with face catching feature by eliminating the background.
Present invention describes a noise reduction and face isolation system with distinct features and a method to improve the quality of audio and video recordings by supressing the background noise.
This invention involves various aspects since the noise reduction and face isolation system aims at multi-pronged approach to tackle and improve recording and uploading audio and videos by noise reduction/suppression.
Firstly, the invention aims towards suppressing the surrounding noise wherein the said noise reduction and face isolation system carries out multiple processing in the background. The sample of prime voice is collected for the first time and the system stores and identifies this sample for future purpose. When the end user records the audio, the stored prime voice is matched with the main voice and the surrounding voices are considered as noise.
Secondly, the invention takes care of quality video recordings by identification of the key elements such as facial organs (i.e., eyes, nose and mouth). On the basis of these elements the dimensions are defined and optimization of the distance between the face of the user and recording device is achieved.
Thirdly, the invention aims to remove/alter the background on the basis of additional feature offered by said noise reduction and face isolation system.
Fourthly, proposed invention allows the user to be anonymous by selecting face cover/mask virtually during video recordings.
All features such as the combination of audio with processing, video with face isolation, background noise removal and with other related options of being identified or anonymous during the overall process make the proposed invention unique and distinctive.
The different components of said system are as described in the table given below:
Table 1
Sr. No. Name of the Component Reference Numeral
1.
2.
3.
4. Prime voice
Acoustic Noise
Audio signal
Audio recording without noise 1a
b
1b
1
5. Acoustic Noise Elimination Module 100
i. means of receiving an audio signal
ii. means of recording and saving an audio signal
iii. means of identifying noise
iv. means of cancellation of noise
v. means of posting the audio with prime voice 101
102
103
104
105
6. Optical Noise Elimination Module 200
i. means for capturing real image
ii. means of selecting background
iii. means of detecting foreground and recognizing pattern for face isolation
iv. means of performing computational analysis for background of said video
v. means of posting the corrected video 201
202
203

204

205

DETAILED DESCRIPTION OF DRAWINGS
FIG.1 is a realistic drawing of an acoustic noise elimination module (100) of noise reduction and face isolation system of the present invention depicting the interconnectivity of different components in a sequential manner to generate an audio recording without noise. The audio signal (1b) received which is a mixture of the voice of the recorder and surrounding acoustic noise (b) is compared with the prime voice (1a) and the surrounding noise is eliminated.
FIG.2a is a realistic drawing of an optical noise elimination module (200) of noise reduction and face isolation system of the present invention depicting the interconnectivity of different components in a sequential manner to enable the user to select background along with face isolation. The module allows the user to select different background The computational analysis of the background is carried out using artificial neural network to produce a video without background noise.
FIG.2b is a realistic drawing of an optical noise elimination module (200) of noise reduction and face isolation system of the present invention depicting the interconnectivity of different components in a sequential manner to enable the user to select background along with appropriate face cover to be anonymous. The module allows the user to select different background The computational analysis of the background is carried out using artificial neural network to produce a video without background noise.
FIG.3 is a flow diagram illustrating stage wise a method of operation of acoustic noise elimination (100) and optical noise elimination (200) of the present invention.
Process Flow A1- A2- A3- A4- A5- A6- B1- B2- B3- B4- B5- C1- C2- C3
The noise reduction and face isolation system of the present invention for improvement in quality of audio and video recording is comprised of said acoustic noise elimination module (100) and said optical noise elimination module (200).
The acoustic noise elimination module (100) is comprised of communicatively connected means for receiving an audio signal (101), means for recording and saving an audio signal (102), means for identifying noise (103), means for cancellation of noise (104) and means of posting the audio with prime voice (105).
Further, the optical noise elimination module (200) consists of communicatively connected means for capturing real image (201), means of selecting the background (202), means of detecting visage and recognizing pattern for face isolation (203), means of performing computational analysis for background of said video (204) and means for posting the corrected video (205).
To use the noise reduction and face isolation system of the present invention, the user needs to register and create a profile using one time password alternatively a link provided in Email can be used. The user needs to record his or her audio signal with the help of audio receivers. This audio signal is further saved as prime voice (1a) to an audio engine. To create an audio recording with enhanced voice quality without noise (1),the acoustic noise elimination module (100) receives audio signal (1b) from the user by using means of receiving audio signal (101), records and saves the received signal by using means of recording and saving an audio signal (102) ,identifies the acoustic noise by using means of identifying noise (103), compares it with the prime voice (1a) by using artificial neural networks and eliminates the acoustic noise (b) by means of cancellation of noise (104).
The method of operation of optical noise elimination module (200) comprises the steps such capturing the real image by using means of capturing real image (201), selecting the background by using means for selecting the background (202), detecting foreground by using means of detecting visage and recognizing pattern for face isolation (203), performing computational analysis of the background by using means of performing computational analysis for background of said video (204) and eliminating optical noise by artificial neural networks to enhance visage and enabling the user to create a video by isolating face of the user.
The user can combine said audio recording by the acoustic noise elimination module (100) and said video recording by the optical noise elimination module (200) to create an audiovisual with recorded prime voice (1a) and isolated face of the user.
EXAMPLE 1:
Said noise reduction and face isolation system of the present invention, offers the user capturing the real image, detecting foreground, selection of alternate face cover to maintain the identity of the user anonymous.
EXAMPLE 2:
Said noise reduction and face isolation system of the present invention, offers the user capturing the real image face, detecting foreground, conducting computational analysis of the background to isolate the face of the user irrespective of the ambience.
EXAMPLE 3:
Said noise reduction and face isolation system of the present invention, offers the user capturing the real image, detecting foreground, correcting the background as per his choice by changing or blurring the background completely.
BEST MODE OF CARRYING OUT THE INVENTION
The present invention in the form of noise reduction and face isolation system involves various aspects since said system aims at multi-pronged approach to tackle and improve the quality of audio and video recordings by noise reduction/suppression and isolating the real image of the user. To create an audiovisual with isolated face of the user eliminating acoustic noise, the user needs to register and create a profile. Creation of profile through one time password alternatively a link provided in Email can be used. First the audio signal from the user is received, recorded and further saved as prime voice (1a). The acoustic noise elimination module (100) and an optical noise elimination module (200) of noise reduction and face isolation system is used to record audio and video of the user wherein acoustic noise elimination module (100) receives audio signal (1b) from the user and compares it to the prime voice (1a), identifies and eliminates acoustic noise (b), enhances the voice quality of the user and simultaneously the optical noise elimination module captures the real image, selects the background and records video, detects foreground, performs computational analysis of the background to eliminate optical noise by using artificial neural networks and isolate the face of the user irrespective of the ambience. Thus, enables the user to create an audiovisual with isolated face and audio without noise.
ADVANTAGES OF THE PRESENT INVENTION
The present invention provides many advantages, few are listed out below:
1. A noise reduction and face isolation system allows the users to record audio from any location be it home/ office/ bus/ train/flight, etc.
2. A noise reduction and face isolation system allows the users to record video from any location be it home/ office/ bus/ train/flight, etc.
3. A noise reduction and face isolation system offers the benefit to reveal the identity or maintain anonymity based on the user’s choice.
4. A noise reduction and face isolation system demonstrates a clear message of equality since it catches only the face of the end user thereby removing any preconceived ideas about what to wear, allowing for greater group cohesion and commonality regardless of gender, socioeconomic background, or otherwise.
5. A noise reduction and face isolation system by allowing the end user to remain in seclusion and enriching with a feeling that reflects that all the users are same and come from the same starting point.
6. A noise reduction and face isolation system motivates users to bring the strength as well as real stories to the wide group of people.
7. A noise reduction and face isolation system generates various new market and opportunities like Customer(s) to Business(es) and Customer(s) to Customer(s).
8. A noise reduction and face isolation system is a new revolution in terms of social impact by placing all users on same platform.
INVENTIVE CONCEPT
The novelty and key inventive features for present invention would fall under multi-pronged approach:
1. An acoustic noise elimination module of the present invention reduces the surrounding noise from the recorded audio by comparing it with the pre-recorded prime voice.
2. An Optical Moise Elimination module of the present invention removes all background and isolates only the face of the end user.
3. A noise reduction and face isolation system described in the present invention enhances overall quality of the recorded video employing artificial neural network.
While considerable emphasis has been placed herein on the disclosed embodiments, it will be appreciated that many embodiments can be made and that many changes can be made to the embodiments without departing from the principles of the present disclosure. These and other changes in the embodiments of the present disclosure will be apparent to those skilled in the art, whereby it is to be understood that the foregoing descriptive matter to be implemented is illustrative and non-limiting.
,CLAIMS:We Claim:
1. A noise reduction and face isolation system comprising:
a) acoustic noise elimination module (100) comprises communicatively connected;
i. means for receiving an audio signal (101),
ii. means for recording and saving an audio signal (102),
iii. means for identifying noise (103),
iv. means for cancellation of noise (104) and
v. means of posting the audio with prime voice (105);
b) optical noise elimination module (200) comprises communicatively connected;
i. means for capturing real image (201),
ii. means of selecting the background (202),
iii. means of detecting visage and recognizing pattern for face isolation (203),
iv. means of performing computational analysis for background of said video (204) and
v. means for posting the corrected video (205).
2. The noise reduction and face isolation system as claimed in Claim 1 wherein, said means of receiving audio signal (101) are selected from but not limited to microphone.
3. The noise reduction and face isolation system as claimed in Claim 1 wherein, said means of recording an audio signal (102) are selected from but not limited to an audio engine.
4. The noise reduction and face isolation system as claimed in Claim 1 wherein, said means of identification of noise and means for cancelation of noise are selected from and not limited to artificial neural networks.
5. The noise reduction and face isolation system as claimed in Claim 1 wherein, said means for performing computational analysis of the background and means for correcting the background are selected from but not limited to artificial neural networks.
6. A method using the noise reduction and face isolation system comprising the steps of:
I. receiving first audio signal from the user with the help of audio receivers;
II. recording said audio signal and saving it as prime voice (1a) to said audio engine;
III. at said acoustic noise elimination module (100):
a) receiving audio signal (1b) from the user by using means of receiving an audio signal (101),
b) recording and saving an audio signal by using means of recording and saving an audio signal (102),
c) identifying acoustic noise (b) by artificial neural networks and using means of identifying noise (103),
d) comparing the received audio signal (1b) to the prime voice (1a) and eliminating the acoustic noise by using means of cancellation of noise (104) to enhance the voice quality of the user and
e) enabling the user to create and post an audio recording without noise (1) by using means of posting the audio with prime voice (105);
IV. at optical noise elimination module (200):
a) capturing the real image by using means of capturing real image (201) and recording video,
b) selecting the background by using means for selecting the background (202),
c) detecting foreground by using means of detecting visage and recognizing pattern for face isolation (203),
d) performing computational analysis of the background by using means of performing computational analysis for background of said video (204) and eliminating optical noise by artificial neural networks to enhance visage and
e) enabling the user to create a video by isolating face of the user;
V. combining said audio recording from step III(e) and said video recording in step IV(d) to create an audiovisual with recorded prime voice (1a) and isolated face of the user.

7. The method using noise reduction and face isolation system as claimed in Claim 6 step IV(b) wherein, said correction of the background is accomplished by provisions selected from but not limited to changing, blurring, eliminating completely the background as per user’s choice.

8. The method using noise reduction and face isolation system as claimed in Claim 6 wherein, said creation of audiovisual without noise is accomplished by isolating facial parts of the user and hiding reminder of the body.

9. The method using noise reduction and face isolation system for improvement in quality of audio and video recording as claimed in Claim 6 wherein, said creation of audiovisual without noise is accomplished by hiding identity of the user by selecting appropriate face cover.

10. The method using noise reduction and face isolation system for improvement in quality of audio and video recording as claimed in Claim 9 wherein, said hiding identity of the user is achieved by selecting facial cover