Hacker News new | ask | show | jobs
by chrisseaton 1623 days ago
But why can't that be done automatically from the 5.1 signal on the consumer's device?
2 comments

It could. But it's an artistic and a sound engineering decision that changes based on what you actually want the listener to hear.

The defaults for automatic sound mixing will almost always be wrong. And they will differ in how they are wrong from consumer box to consumer box.

If wonder if instead of a separate mix, 5.1 could be modified to include hints for how to better down-mix a given production.
It can. That's part of the Blu-ray spec. But it's not standardized in streaming video AFAIK (not that Netflix has to care about that, they have their own player) and, even if the feature exists, somebody still has to go do it.
A speech recognition model can give you a reading on how understandable the speech is and use that information to guide the channel volume in the mixing.

OTOH, a lot of the models end up trained on features that are very different from what humans hear.

Exactly and I have no idea, why this is not done - is it a technical reason, or is it lazy consumer device programming?