Jordi Pons

@jordiponsdotme

Researcher . Motivated citizen. Building bridges between audio signal processing wisdom and deep learning.

Barcelona
jordipons.me
Vrijeme pridruživanja: veljača 2017.
148 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @jordiponsdotme

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @jordiponsdotme

  1. Prikvačeni tweet
    30. lis 2018.

    End-to-end Music Source Separation: Is it possible in the waveform domain? - Check the answer on arXiv: - Demo: - Code:

    31 proslijeđeni tweet 118 korisnika označava da im se sviđa
    Poništi
  2. 30. sij

    Now happening at : A COMPUTER SCIENTIST EXPLAINING (via formulas) TO SOCIAL SCIENTISTS WHY HYPER-PARAMETER TUNING COULD HELP THEM GET FAIRER MODELS. The considered hyper-parameter: the ɛ of the soft-margin formulation of SVMs.

    14 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    29. sij
    Odgovor korisnicima

    Great news. So happy you can pursue your career in Barcelona. This would be a super-team with & , too. Congrats , this is a really smart move 👍🏻

    1 reply 3 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Poništi
  4. 29. sij

    Welcome, Santi! I'm super happy for the team we built in Barcelona :)

    I am thrilled to announce that I am going to join the Barcelona Audio AI team in February, yyayy! 🎉🎊🎙️🤖🎧🎊🎉
    1 reply 7 korisnika označava da im se sviđa
    Poništi
  5. 27. sij

    I'm now at my first (a conference on fairness, accountability and transparency of socio-technical systems) and I'm surprised by how big, international and business-driven is this community. Let's see what do we learn this week, not sure what to expect!!

    1 reply 8 korisnika označava da im se sviđa
    Poništi
  6. 24. sij

    Two papers accepted to !! "An empirical study of Conv-TasNet", my first paper with . "Tensorflow audio models in Essentia", one of my last papers with the ! This is a nice connection for an ICASSP that is going to be held in Barcelona! :)

    2 proslijeđena tweeta 67 korisnika označava da im se sviđa
    Poništi
  7. 22. sij

    Want to work in our team? We are searching interns for next summer (w/ strong background in deep learning & audio, music or speech). Our positions in Barcelona are already filled up, but we still have positions in San Francisco! Apply online and DM me:

    13 proslijeđenih tweetova 40 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    15. sij

    Freesound ended the year with an amazing total of 441,075 sounds!! Check the review of Freesound activity in 2019

    10 proslijeđenih tweetova 22 korisnika označavaju da im se sviđa
    Poništi
  9. 13. sij

    I prepared this slides for next Thursday – I'll be teaching to the Master in Sound and Music Computing students of the .

    1 proslijeđeni tweet 3 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. 13. sij

    Yet another tutorial on Recurrent Neural Networks! You will learn about the gradient vanishing/explode problem 🤯 and how it relates to LSTMs and GRUs. 📢Slides: 📄Main reference: 📽️Additional reference:

    1 reply 11 proslijeđenih tweetova 41 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    3. sij

    Our team has two internship positions in San Francisco (Barcelona position is already filled up). Topics around audio, generative models, and source separation. If interested please apply or DM me.

    1 reply 18 proslijeđenih tweetova 38 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    22. pro 2019.

    "Erdős–Bacon–Sabbath number" is the sum of the Erdős–Bacon number and the collaborative distance to the band Black Sabbath in terms of singing in public. Stephen Hawking had an Erdős–Bacon–Sabbath number of 8, and actress Natalie Portman has one of 11.

    2 proslijeđena tweeta 2 korisnika označavaju da im se sviđa
    Poništi
  13. 19. pro 2019.

    These days catalan deep learning researchers are meeting to the annual symposium. I'll be there presenting MUSICNN (pronounced as "musician"), our open-source deep learning-based music tagger. 🔗Github: 🎶Demo:

    1 reply 11 proslijeđenih tweetova 35 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    5. pro 2019.

    Now you might know what else we were doing during the summer^^ A quick glimpse of working on the client using emscripten & WebAssembly. ps: ongoing work though!

    16 proslijeđenih tweetova 63 korisnika označavaju da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    3. pro 2019.

    Gone in 4 minutes: all available tickets have been quickly distributed. We have opened a waiting list in case some orders get cancelled. The Telefonica Auditorium will be full with more than 300 attendees. Sign in the waiting list from here:

    7 proslijeđenih tweetova 27 korisnika označava da im se sviđa
    Poništi
  16. 15. stu 2019.

    I'm a doctor!!!

    46 replies 4 proslijeđena tweeta 241 korisnik označava da mu se sviđa
    Poništi
  17. proslijedio/la je Tweet
    15. stu 2019.

    Congrats Dr ! Successful (and crowded) defense of the PhD thesis " neural networks for music and audio tagging". Check manuscript, code and demo

    i
    1 reply 12 proslijeđenih tweetova 39 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    14. stu 2019.

    Tomorrow at the MTG: Deep-learning day! 11h: defens his PhD thesis 15:30h: Three talks on Deep-learning for music processing (, Juhan Nam, Fabian-Robert Stöter)

    6 proslijeđenih tweetova 38 korisnika označava da im se sviđa
    Poništi
  19. 11. stu 2019.

    New post: My favourite papers! Link:

    10 proslijeđenih tweetova 53 korisnika označavaju da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    8. stu 2019.

    Next up in our Meetup with Industry: on waveform-based deep learning research at !

    4 proslijeđena tweeta 9 korisnika označava da im se sviđa
    Poništi
  21. 8. stu 2019.

    Our talk on “Waveform-based deep learning research at Dolby” is about to start at the main stage of the Industry Meetup of . See you there!

    1 reply 1 proslijeđeni tweet 25 korisnika označava da im se sviđa
    Poništi

@jordiponsdotme još nije objavio nijedan Tweet.

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·