I am trying to write something that scans an audio file and tells when and what kind of Anuran is present (from a set of 6 diff species). I am having trouble understanding what would be the workflow of this whole process.
What I am doing so far:
>scanning several sound samples from frog databases in the time domain and segmenting that audio around where the calls might be (pic related)
>using the frequency information from those time slices to train a supervised model

Most articles I am reading use Mel-frequency cepstrum to "just do it" and a whole lot of dark magics.

Where can I read more on MFCCs? How would you recommend to preprocess the data? I basically need to remove sections without calls from several recordings, and possibly reduce the noise a bit. (I already downsample them to 16k Hz and filter them).

Pic related is my shitty segmentation algorithm, I just look for areas that cross the mean+-std*factor, it doesn't section them cleanly and works meh.

>t. /pol/ free energy demon

Ignored math through all of high school, only realized my love for learning shortly after. I've been doing math on my own and enjoying it, but be real, what are my chances that after a year I'm still an autist vegetable? Is there any shot at redemption? Do any of you anons have your own comeback stories? How hard would it be to catch up to at least high school math if I basically quit halfway through freshman year?

This is not a post asking for motivation, but just made out of curiosity.

Gogo Tomago from big hero 6 (my favorite movie) created a bike with "electro-mag[netic] suspension" which she says creates "zero resistance" for a faster bike. Is this physically possible and/or plausible to build with current technology? Would it offer any meaningful advantage over a normal bike? What does the cutting edge of bike technology look like?

Physicists, engineers, and others with knowledge, please answer! Thanks in advance.

https://dictionary.cambridge.org/dictionary/english/relativity
https://dictionary.cambridge.org/dictionary/english/reflexive

We live in a reflexive universe, not a relativistic one. The calculations can work when done from a relativistic perspective, but ultimately they're merely an abstraction of the truth that you are a reflexive and non-relative observer. Relativity is reflexive to the observers, and in that sense, if you have multiple observers, you can have reflexivity relative to these observation points, but they aren't all unique points. They're reflexive to entropic maps, which are chaotic in nature. As such, the chaotic map is always drawing the same worldlines for any observable point, and one need not have any special observers considered.

Einstein is dumb. Science is dumb, you guys are dumb clowns.

What the fuck is Havana Syndrome?

Anyone here suffer from imposter-syndrome? I'm currently in the last couple of weeks of my master thesis in food/analytical chemistry and the doubts have never been so bad before. I'm feeling super stressed out because I feel like I'm just making things up while interpreting my data. I've always had very good grades without ever slipping, and rationally I know that it will be the same for the thesis. Still, I feel like everyday I'm gonna get busted for being a fraud.

Anyone else feel like this?

I'm a stupid 26 yo man with poor memory and reasoning, despite my genetic father being a physician, is there any hope for me scientifically or should I just rope?

Thoughts on this program?

I don't get it