Jordi Pons

Jordi Pons - Audio Engineering Researcher


One goal of transcription is the experience of transcription itself.
Ter Ellingson

Menu

  • About me
  • Publications
  • Demos
  • Ongoing projects
  • Presentations & posters
  • Blog

Month: February 2018

Building our own GPU server for training deep learning models with TensorFlow

By Jordi Pons in Deep learning, Hardware February 8, 2018

This post aims to share our experience setting up our deep learning server – thanks to NVidia for the two Titan X Pascal, but also thanks to the Maria de Maeztu Research Program for the machine ! 🙂 The text is divided in two parts: bringing the pieces together, and install TensorFlow. Let’s start!
Continue reading

Recent Posts

  • What’s up with waveform-based VGGs?
  • Why do spectrogram-based VGGs rock?
  • Why do spectrogram-based VGGs suck?
  • Learning the logarithmic compression of the mel spectrogram
  • arXiv article: Training neural audio classifiers with few data

Archives

  • January 2019 (3)
  • December 2018 (1)
  • November 2018 (2)
  • October 2018 (1)
  • September 2018 (1)
  • August 2018 (1)
  • July 2018 (1)
  • June 2018 (1)
  • May 2018 (2)
  • April 2018 (1)
  • March 2018 (1)
  • February 2018 (1)
  • January 2018 (1)
  • December 2017 (1)
  • November 2017 (1)
  • October 2017 (1)
  • September 2017 (1)
  • August 2017 (1)
  • July 2017 (1)
  • June 2017 (1)
  • May 2017 (1)
  • April 2017 (1)
  • March 2017 (2)
  • February 2017 (1)
  • January 2017 (1)
  • December 2016 (2)
  • November 2016 (1)
  • October 2016 (1)
  • September 2016 (1)

Categories

  • CNNs
  • Conferences
  • Datasets
  • Deep learning
  • Extreme Learning Machine
  • Hardware
  • Negative Result
  • Opinion
  • Paper is out
  • Results
  • Slides
Proudly powered by WordPress. Theme: DW Minion by DesignWall.