Browse Prior Art Database

Video Content Navigation based on Voice input provided by user

IP.com Disclosure Number: IPCOM000249159D
Publication Date: 2017-Feb-08
Document File: 2 page(s) / 50K

Publishing Venue

The IP.com Prior Art Database

Abstract

Video Content Navigation based on Voice input provided by user

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

1

Video Content Navigation based on Voice input provided by user

Most software's gain recognition when the user’s need is tapped and a new service package is marketed. While watching long videos, we have trouble in picking the correct point we wish to watch and end up fast forwarding and rewinding, in search for a particular scene. This is very frustrating for user and we want to tap this need and develop a software, which the users would love.

Let us consider the movie Gladiator. We want to go back to the scene, where the hero says “My Name is Maximus Decimus Meridius…” Based on a voice input, we would use available audio streaming and match the voice input . Then based on that, it would take us to that particular point in the video. This way, the user need not use the cumbersome means of fast forwarding/ rewinding and re checking

We can navigate the video based on voice input and recognition from user. We don't need to use navigation buttons, need not remember the timing where we wanted to see again the video. It’s just a voice based content search for video using voice input from user

With the growing network speeds, it is becoming easier to browse content on the net and stream videos online without much lag. The video can be viewed with less buffering and great quality.

But while watching a video we usually keep navigating from one point to another and this can be done by clicking on the video navigator. We also have text based searching tools for video content where in we provide some text in search box, it would navigate to that text in the video. Such tools can navigate only for recordings and not all videos. The tools create tags for each video block and compare it with the search string.

Our idea is to navigate the video based on the voice input from the user. We use a tool that plays the video available in it. We can add videos to the tool or access...