Does anyone know of a piece of software to split multiple voices from a single audio file?
I know of things like lalal.ai to split vocals from music, and I can find a bunch of research papers about voice separation from Google and Facebook, but I'm struggling to find actual software I can run myself on my own audio files.
Learn to segment your images with the Segment Anything Model (SAM) by Meta AI in just a few lines of #Python code! Check out my YouTube tutorial: https://youtu.be/fVeW9a6wItM
#imageSegmentation #MetaAI #segmentanything #microscopy
Extending the sensitivity, consistency and depth of single-cell proteomics | https://www.nature.com/articles/s41592-023-01786-2 #proteomics
Teaching students to interpret data and write their first scientific paper can be hard!
Our new publication provides all the materials you need to teach these skills in graduate or upper-level undergraduate courses. 1/
https://doi.org/10.24918/cs.2023.14
After a long hiatus (because, life...) I have updated my blog!
I have been meaning to write about neural networks for a while, so here it is! Part 1 of ... a certain number😜
In this first episode, I will guide you through what is a neural network, with a bit of history on the topic!
https://www.nicolaromano.net/data-thoughts/intro-neural-networks-pt1/
Stay tuned because other posts will be showing up in the upcoming weeks... we'll see a bit more of the theory of how these networks are trained, and then we'll code our own network in #python!
#ai #machinelearning #neuralnetworks #statistics #artificialintelligence
“‘It’s always done like this, whether getting women to champion other women’s oppression or Jews who supported Hitler, it’s absolutely essential to get a token member of the targeted group to promote the extremist agenda’” #MAGAFascism https://buckscountybeacon.com/2023/04/the-truth-about-maga-activist-scott-presler/
At one in six, it is more likely than not that you know someone who has had issues with fertility. However, given the taboo nature of the topic, it is much less likely that you know about it. Normalising talking about issues is a big step towards improving the lives and mental health of those you meet in this world. #infertility #MentalHealth
🇫🇷 French newspapers published a large investigation on delivery workers in mid-sized towns.
Lots of interesting tidbits there, like the fact that they earn roughly 1500€/month for 10 hours of work, with no days off. That's half the minimum wage.
See here e.g. in Lorraine: https://www.republicain-lorrain.fr/societe/societe/livreurs-les-forcats-de-l-uberisation
@nicolaromano two of my favourite topics!
(see e.g. https://tomstafford.github.io/psy-checklist/ and https://tomstafford.github.io/psy6422/)
We have a research assistant position to work on a study surveying how experimental study design and analysis are taught at the undergraduate level in the UK (position based at the University of Edinburgh, Scotland). The post is for four months full-time or equivalent part-time (e.g. eight. months 50%).
If you are interested or know someone who is, you can find more details here:
https://elxw.fa.em3.oraclecloud.com/hcmUI/CandidateExperience/en/sites/CX_1001/job/7014
#job #research #experimentalDesign #dataAnalysis #survey #statistics
“Help,” cries the journalist, “I’m being held captive by Elon Musk!”
He calls out from the unlocked cage, door wide open, to which he holds the key in his own hands.
“Quickly,” he begs now, “I can’t bear the thought that someone might think I’m paying for this.”
He gestures to the searing blue legacy checkmark, a brand affixed not to his skin, but the cage.
Concerned passerby leave treats at the door, in the hopes he might free himself. But alas, he shall surely starve.
I was under the impression (will look later for corroboration) that poor grammar in phishing serves as a filter: phishers don't want to waste their time on people who won't get duped, so in an attempt to filter those people out early they send initial e-mails that will look suspicious to those people. If that's true, then the most obvious way to interpret the reason from that article doesn't apply. However, there might be some more involved reasons: e.g. if text generators make interaction with the potential victim cheaper, the reason for the filter's existence might disappear.
As I was privately babbling out my own diatribe on the FLI letter yesterday, I was honored to be pinged by @emilymbender and @timnitGebru about joining forces to put out coherent thoughts. Excited to be able to share it today.
There are clearly foreseeable long-term AI harms. To address them, regulatory efforts should focus on transparency, accountability and preventing exploitative labor practices.
https://www.dair-institute.org/blog/letter-statement-March2023
Current pocket rock - wee piece of carboniferous limestone full of crinoids and bryozoans 🖤 #ScottishFossils
Wondering if anyone has access to this paper:
Onwuegbuzie, A. J. (in press). Prevalence of statistics anxiety among graduate students. Journal of Research in Education
It is one of the main papers in #StatisticsAnxiety research in undergraduate samples and from around 2004 but I am having trouble finding and accessing it. If anyone had a copy that they could share that would be much appreciated.
I am still disappointed every time I see (what seems like) an in-person conference only.
We learned to do better, and now many are choosing to unlearn it…
https://openbiblio.social/@openaccessnetwork/110105672763644418
Oh shit now the "hey transpeople are evil cause one just shot some kids" morons are creeping in on my timeline... its almost like being a member of one of the most abused, ridiculed, attacked, and tortured groups in existance (trans people) might lead to a very very small portion of them snapping and becoming violent... the level of stupdity of these people to think it infers trans people are just bad people, instead of recognizing it might be a symptom of extreme abuse, is mind boggling.
@nicolaromano You can try StringTie2 (https://ccb.jhu.edu/software/stringtie/index.shtml?t=manual) and FLAIR (https://flair.readthedocs.io/en/latest/) to discover transcript isoforms from all samples and quantify them with packages like featureCounts (https://subread.sourceforge.net/) and Salmon (https://salmon.readthedocs.io/en/latest/salmon.html)
Senior lecturer at ZJE and Edinburgh university.
I teach #imageanalysis & #dataanalysis with #RStats & #python. I study #heterogeneity in #pituitary (and other) cells.