home
products
contribute
download
documentation
forum
Home
Forums
New posts
Search forums
What's new
New posts
All posts
Latest activity
Members
Registered members
Current visitors
Donate
Log in
Register
What's new
Search
Search
Search titles only
By:
New posts
Search forums
Search titles only
By:
Menu
Log in
Register
Navigation
Install the app
Install
More options
Contact us
Close Menu
Forums
MediaPortal 1
Development
Improvement Suggestions
Auto sync subtitle to video
Contact us
RSS
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Reply to thread
Message
<blockquote data-quote="mm1352000" data-source="post: 1137735" data-attributes="member: 82144"><p>Hello Marcel</p><p></p><p>Interesting idea. I guess it <em>might</em> be possible... but very, <em>very, <strong>very </strong></em>challenging. So hard that it would take years of work, and still maybe not work reliably.</p><p>...but still, interesting. <img src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7" class="smilie smilie--sprite smilie--sprite1" alt=":)" title="Smile :)" loading="lazy" data-shortname=":)" /></p><p></p><p>Identifying voice in an audio track would be the first challenge. For this I guess you'd need a codec that could "parse"/process uncompressed audio to separate the voices from the other sounds. This could be hard. Especially for language-independent speech (different languages sound different => require different recognition techniques?)... and if more than one person is talking at once.</p><p></p><p>Second would be recognising that somebody in the video is talking. This would require a code that could "parse"/processed uncompressed video to find the talker. Honestly, this is most likely to be impossible. The person who is talking may not even be shown in the video... or the quality/resolution may be too poor to identify lips moving properly.</p><p></p><p>This seems too hard from a technical perspective. Perhaps there's another easier way to do it?</p></blockquote><p></p>
[QUOTE="mm1352000, post: 1137735, member: 82144"] Hello Marcel Interesting idea. I guess it [I]might[/I] be possible... but very, [I]very, [B]very [/B][/I]challenging. So hard that it would take years of work, and still maybe not work reliably. ...but still, interesting. :) Identifying voice in an audio track would be the first challenge. For this I guess you'd need a codec that could "parse"/process uncompressed audio to separate the voices from the other sounds. This could be hard. Especially for language-independent speech (different languages sound different => require different recognition techniques?)... and if more than one person is talking at once. Second would be recognising that somebody in the video is talking. This would require a code that could "parse"/processed uncompressed video to find the talker. Honestly, this is most likely to be impossible. The person who is talking may not even be shown in the video... or the quality/resolution may be too poor to identify lips moving properly. This seems too hard from a technical perspective. Perhaps there's another easier way to do it? [/QUOTE]
Insert quotes…
Verification
Post reply
Forums
MediaPortal 1
Development
Improvement Suggestions
Auto sync subtitle to video
Contact us
RSS
Top
Bottom