Let's face it -- even with the latest advances in voice recognition, dictating actual messages can be a lengthy, error prone process, especially when you're driving.

Yet music recognition works surprisingly well, often needing just a second or so of audio to recognize a tune. Said tune, of course, has lyrics.

The idea then is to create use music recognition in aiding voice recognition. To create a message, one would sing a verse or even a few words from a song on an appropriate subject with a suitable subset of lyrics.
-- theircompetitor, Dec 04 2011

I experimented with a voice recognition program to see if it could distinguish two differently toned whistles. It could not. I conclude that voice recognition programs are all about rhythm.
-- bungston, Dec 04 2011


[Bung], the voice recognition program didn't recognize the difference because you were whistling, not vocalizing. It simply disregarded the sounds.
-- Alterother, Dec 05 2011


This would work well towards morphing English into a tonal language.
-- RayfordSteele, Dec 05 2011


If this takes off in a big way, there would presumably be a drive to make popular songs more relevant to the dictation needs of the busy executive.

Not, of course, that I would condone Halfbakers listing song titles adapted to such needs.
-- MaxwellBuchanan, Dec 11 2011


That's three more points on your poetic license, [MB]. Any more of this and you'll have to take a remedial course in paralepsis parking.
-- mouseposture, Dec 11 2011



random, halfbakery