Emre Çakır

Doctoral student
Audio Research Group
Tampere University of Technology, Finland
Email
GoogleScholar


About


I graduated from METU, Turkey with a BSc. with honor degree in Electronics Engineering in 2013. Then I completed my MSc. studies (signal processing major) with distinction in Tampere Univ. of Tech. (TUT), Finland in Jan, 2015. I am currently a PhD student in Audio Research Group in TUT under supervision of Tuomas Virtanen SWE intern at Google under supervision of Dan Ellis. I am mainly working on polyphonic sound event detection in real-life environments with deep convolutional and recurrent neural networks.

Research Interests

  • Polyphonic Sound Event Detection

  • Audio Tagging

  • Machine Listening

  • Deep Learning

  • Demos

    (credit: Toni Heittola)

    Academic Experience

  • Course assistant, Fall 2015, Fall 2016 Audio and Speech Processing

  • Course assistant, Spring 2015, Analysis of Audio, Speech and Music Signals

  • Professional Experience

  • Software Engineering Intern, Google, Inc. New York, NY (Aug 2018 - Oct 2018).

  • Machine Learning Analyst, Yousician, Inc. Helsinki, Finland (January 2016 - June 2016).

  • Talks in international conferences

  • International Joint Conference on Neural Networks (IJCNN). Vancouver, Canada, July 2016.

  • 23rd European Signal Processing Conference (EUSIPCO). Nice, France, September 2015.

  • International Joint Conference on Neural Networks (IJCNN). Killarney, Ireland, July 2015.

  • Grants

  • TUT Graduate School, President's funding (January 2016 - December 2019).

  • Publications (180 citations as the main author as of 05/27/2018)


  • Emre Çakır, and Tuomas Virtanen. End-to-End Polyphonic Sound Event Detection Using Convolutional Recurrent Neural Networks with Learned Time-Frequency Representation Input. International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil, July 2018.

  • Emre Çakır and Tuomas Virtanen. Convolutional Recurrent Neural Networks for Rare Sound Event Detection. DCASE2017 Challenge, September 2017.

  • Emre Çakır, Giambattista Parascandolo, Toni Heittola, Heikki Huttunen and Tuomas Virtanen. Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection. Transactions on Audio, Speech and Language Processing: Special issue on Sound Scene and Event Analysis, 2017.

  • Emre Çakır, Sharath Adavanne, Giambattista Parascandolo, Konstantinos Drossos and Tuomas Virtanen. Convolutional Recurrent Neural Networks for Bird Audio Detection. 25th European Signal Processing Conference (EUSIPCO). Kos, Greece, September 2017.

  • Pasi Pertilä and Emre Çakır. Robust Direction Estimation with Convolutional Neural Networks-based Steered Response Power. In International Conference on Acoustics, Speech and Signal Processing (ICASSP). New Orleans, USA, March 2017.

  • Emre Çakır, Ezgi Ozan, and Tuomas Virtanen. Filterbank Learning for Deep Neural Network Based Polyphonic Sound Event Detection. In International Joint Conference on Neural Networks (IJCNN). Vancouver, Canada, July 2016.

  • Aleksandr Diment, Emre Çakır, Toni Heittola, and Tuomas Virtanen. Automatic Recognition of Environmental Sound Events Using All-pole Group Delay Features. In 23rd European Signal Processing Conference (EUSIPCO). Nice, France, September 2015.

  • Emre Çakır, Toni Heittola, Heikki Huttunen, and Tuomas Virtanen. Multi-label vs. Combined Single-label Sound Event Detection with Deep Neural Networks. In 23rd European Signal Processing Conference (EUSIPCO). Nice, France, September 2015.

  • Emre Çakır, Toni Heittola, Heikki Huttunen, and Tuomas Virtanen. Polyphonic Sound Event Detection Using Multi Label Deep Neural Networks. In International Joint Conference on Neural Networks (IJCNN). Killarney, Ireland, July 2015.

  • Emre Çakır (October 2014). Multilabel Sound Event Classification with Neural Networks. Master's Thesis. Tampere University of Technology, Finland.


  • Contact Me


    Tietotalo TF 307, Korkeakoulunkatu 1, 33720, Tampere, Finland

    Phone: +358 414872879

    Email: emre.cakir@tut.fi