I’m new with sound analyzing and editing and want to use Audactity to search for things how I can recognize a certain human sounds (but not words).
I do not know where to start, other then watching random turtorials how to use Audacity what I’m doing at this moment none stop.
For research pruposes I want to know/research how I can distinguish human made sounds like ‘Booh’, ‘Wouw’ or Neh…
(where Volume or speed of such sounds can be variable)
Can anybody help me start?
(Should I look at peek frequencies/patterns of waves…)
how I can recognize a certain human sounds (but not words).
It’s the same technology that recognizes human grunts as recognizes “My Country 'Tis Of Thee.” You still have to take the sound apart into phonemes and then try to match them up to a list. I don’t know that Audacity has any such tools.
However, it is a volunteer organization and if you wanted to write something…
If the “human sounds” are the “needles in the haystack”, what is the “haystack”?
If you are simply search for sounds in an otherwise silent recording, then you can use “Analyze menu > Sound Finder”.
If you are searching for a specific sound (like “Booh” within a speech recording, then it is as Koz wrote.
You might want to look at this recent post: https://forum.audacityteam.org/t/need-pointers-on-adding-feature-to-search-pattern/33729/1
It should return those sounds you are looking for, always depending on the threshold.
It has a constant time resolution though. It is clear that it would otherwise indrease the calculation time exponentially since we had to look in an x * x matrix for the best fitting.
It essentially finds sounds that do rhyme with the sample sound.
It does currently compare the wave form themselves which does naturally emphase voiced sounds. Therefore, drawl, ball, call and so on are regarded as highly related because the consonants do not contribute much energy to the whole sound.
Koz, Steve and Robert many thanks for your information.
You gave me much subjects to search for.
The only thing (and its difficult anough) that I want to do with Audactity is search what part makes a sound ‘Booh’, '‘Wouw’ etc unique.
(with variabel timespan, volume and maybe more)
The matching/comparing part I want to do with code, so that isn’t what I’m searching for in Audacity because that the whoel idea of the application code I’m writing.
(I’m trying to develop some application for ‘Booh’, ‘Wouw’, ‘Ugh’ sounds that people make that can’t speak, I already can extract spectrums, volume etc with the app code but I don’t know where to look/match for)
Now I’m going to reasearch all your information, thanks again!
PS: If anyone has more tips/trics how to search in Audacity for ‘the’ unique key af such sounds, please let me know.