Audio Phonic ( An Audiovisual Auto corrector) / Capt Muhammed Bilal Sadiq, Capt Danish Zarif, Capt Arslan Waqar, Capt Shehryar Ali Ahmad

By: Sadiq, Muhammed BilalContributor(s): Supervisor AP Mobeena ShahzadMaterial type: TextTextMCS, NUST Rawalpindi 2023Description: 67 pSubject(s): UG BESE | BESE-25DDC classification: 005.1,SAD
Contents:
Media industry, especially after the rise of the internet as it is readily available to all households, there is a lot of increase in the internet users both as well as consumer and content creators. Now the ultimate problem of proof-editing the videos and audio created by the creators and voice-over artists respectively. According to the statistics, more than 40% of the pupils living in Ireland, find it cumbersome in preparing videos and sounds for the internet. This leads us to the utmost problem editors and voice-over artists face, which is proofreading, changing the audio/video again and again to match perfection which takes a lot of time, Secondly, the problem is with the audiobook creators, one small mistake in the voice generation and you’ll have to start all over again from the Last sentence and often from the last paragraph to avoid any feelings of unmatched voices. This system i.e., “AudioPhonic – an audiovisual auto corrector” aims to automate the process of making changing in the audio as well as video files . System will provide many features such as, upload your audio as well video files, get editable transcript (change the audio transcript) and changings will be added as the original voice on the audio. Finally, you can download the final version of the audio/video files from the system. The system will be easy to use and provide a great user experience throughout the process. It will help the content creators as well as the voice-over artists to minimize their time of editing the voice/video due to the process of automation using deep neural networks. There will be a lot of improvements and future work that can be done as well as cater in this project, such as shifting all the learning practices to online has left us with a need for a solution to provide quality content despite the internet connectivity issues. This project also has the branch to solve this internet connectivity issue by using the technology of deepfake and TTS (Text-to-speech) solutions. We can work for online transfer of text and generation of audio on the other end. According to a report, more than 1.2 million Californian students are reported to have internet or computer issues for learning online. And the others are also getting either a very low bandwidth or a constant connectivity issue for their network. Hence, we can solve this problem too by providing them a solution like free Facebook for their online lectures and meetings. Moreover, we make the edits in the audio file on the face (in case of video) more realistic and accurate.
Tags from this library: No tags from this library for this title. Log in to add tags.
Item type Current location Home library Shelving location Call number Status Date due Barcode Item holds
Project Report Project Report Military College of Signals (MCS)
Military College of Signals (MCS)
General Stacks 005.1,SAD (Browse shelf) Available MCSPCS-454
Total holds: 0

Media industry, especially after the rise of the internet as it is readily available to all households, there is a lot of increase in the internet users both as well as consumer and content creators. Now the ultimate problem of proof-editing the videos and audio created by the creators and voice-over artists respectively. According to the statistics, more than 40% of the pupils living in Ireland, find it cumbersome in preparing videos and sounds for the internet. This leads us to the utmost problem editors and voice-over artists face, which is proofreading, changing the audio/video again and again to match perfection which takes a lot of time, Secondly, the problem is with the audiobook creators, one small mistake in the voice generation and you’ll have to start all over again from the Last sentence and often from the last paragraph to avoid any feelings of unmatched voices. This system i.e., “AudioPhonic – an audiovisual auto corrector” aims to automate the process of making changing in the audio as well as video files . System will provide many features such as, upload your audio as well video files, get editable transcript (change the audio transcript) and changings will be added as the original voice on the audio. Finally, you can download the final version of the audio/video files from the system.
The system will be easy to use and provide a great user experience throughout the process. It will help the content creators as well as the voice-over artists to minimize their time of editing the voice/video due to the process of automation using deep neural networks.
There will be a lot of improvements and future work that can be done as well as cater in this project, such as shifting all the learning practices to online has left us with a need for a solution to provide quality content despite the internet connectivity issues. This project also has the branch to solve this internet connectivity issue by using the technology of deepfake and TTS (Text-to-speech) solutions. We can work for online transfer of text and generation of audio on the other end. According to a report, more than 1.2 million Californian students are reported to have internet or computer issues for learning online. And the others are also getting either a very low bandwidth or a constant connectivity issue for their network. Hence, we can solve this problem too by providing them a solution like free Facebook for their online lectures and meetings. Moreover, we make the edits in the audio file on the face (in case of video) more realistic and accurate.

There are no comments on this title.

to post a comment.
© 2023 Central Library, National University of Sciences and Technology. All Rights Reserved.