I would like to know what is/are the purpose of voice detection other than synchronizing with some types of subtitles. I almost exclusively use the subtitles that comes with the DVD/Blu-ray, and I think these don’t work with the feature.
Does voice detection served any other purpose? If not are there any planned upcoming features that could benefit from it?
Finally, cans someone explain to me once and for all which audio track (tracks?) is being analyzed; the very first one only? What about subtitle tracks? Which track gets synchronized?
Maybe it’s all explained on docs, but I could find it.
(Used the android-mobile tag because voice boost or something similar would be neat…It be even better if such boost could be applied on any track…)
Using these on a mobile device is a pain, IMHO.
Since these are pictures, they cannot be adapted to the specific needs of smaller screens. You cannot change their colors, or adapt the line wrapping to compensate for larger text sizes.
It might be bearable, if all you need is some occasional “forced” subtitle line. But if you watch foreign movies with subtitle translations, you want to be able to read them without straining your eyes all the time.
So, there are good reasons to fetch “text” (i.e. SRT) versions of the subtitles. And unless you are converting them yourself from the picture subs you already have, downloaded subs are often not matching your specific version of the video.
That’s where the voice analysis comes into play.
