I think the next revolution will be voice input

It was recently thought here - why neither I, nor my relatives, do not use a computer in everyday life, for example, to write down where they put another thing in the process, for example, annually getting summer things and removing winter things? This is despite the fact that when you need something, you have to painfully recall “where did you put it”, fantasize on the theme “where it could be now” and search through all possible shelves and drawers in order of decreasing hopes for a satisfactory result.

Strict accounting in a warehouse of a large trading or industrial company - it is clear that business is not only conducted on a computer, but for a long time it has been issued with pieces of paper with signatures and seals. But at home, no one will be engaged, and I first. To equip all things with rfid-tags and all cabinets with readers, as they do in some advanced warehouses - I probably wouldn't be able to either. This would not be enough not only money, but also pedantry when connecting readers and attaching tags.

But I thought that removing the next thing in the next place - I would almost without straining would comment on it out loud. To process this, a computer needs a microphone and (this is the thing that is not enough yet!) A speech recognizer that would put the recognized text into the database that provides the search. I need that when I say that I put “something” “somewhere”, I could then ask the computer (this is already possible in writing, although if it recognizes, then for some reason and not verbally) - where did I put the “something” I needed, and he could find all the cases when I informed him about the shifting of this “something”.
')
Oral filling in notes, assignments, reminders, questionnaires, forms, search requests and many such things would open up the widest spaces for using computers where use now rests on having to type the text with your hands while looking at the screen.

This technology would turn the world of home use of computers! That's what you need to spend their power.

PS For good, it is necessary to store the recorded speech along with the text. About the same as DJVU and PDF can store a text layer for scanned images, and videos sometimes store subtitles for the audio track. In fact, you need an automatic subtitle generation engine for audio recordings.

And just like for OCR, we need tools to read and edit the text recognized from the sound. With histograms for clarity and orientation. For reliability, re-checking, and ease of perception, it would be useful to store such audio recordings with a text layer as the values ​​of text fields.

It is also necessary that the means of recording and saving to the database with the same voice be controlled. Itself cut heard on words and sentences, and some of the words not only recorded, but also fulfilled.