Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tuomas Virtanen

Tuomas Virtanen

Tampere University

Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags


Oct 27, 2020
Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra

* 5 pages, 1 figure 

  Access Paper or Ask Questions

Robust Audio-Based Vehicle Counting in Low-to-Moderate Traffic Flow


Oct 22, 2020
Slobodan Djukanović, Jiři Matas, Tuomas Virtanen

* The paper has been accepted for the IV2020 conference 

  Access Paper or Ask Questions

Neural Network-based Acoustic Vehicle Counting


Oct 22, 2020
Slobodan Djukanović, Yash Patel, Jiři Matas, Tuomas Virtanen


  Access Paper or Ask Questions

WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information


Oct 21, 2020
An Tran, Konstantinos Drossos, Tuomas Virtanen

* Submitted for review at ICASSP2021 

  Access Paper or Ask Questions

Conditioned Time-Dilated Convolutions for Sound Event Detection


Jul 10, 2020
Konstantinos Drossos, Stylianos I. Mimilakis, Tuomas Virtanen


  Access Paper or Ask Questions

Multi-task Regularization Based on Infrequent Classes for Audio Captioning


Jul 09, 2020
Emre Çakır, Konstantinos Drossos, Tuomas Virtanen


  Access Paper or Ask Questions

COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations


Jul 08, 2020
Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra

* 8 pages, 1 figure, workshop on Self-supervision in Audio and Speech at the 37th International Conference on Machine Learning (ICML), 2020, Vienna, Austria 

  Access Paper or Ask Questions

Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation


Jul 06, 2020
Pyry Pyykkönen, Styliannos I. Mimilakis, Konstantinos Drossos, Tuomas Virtanen


  Access Paper or Ask Questions

Temporal Sub-sampling of Audio Feature Sequences for Automated Audio Captioning


Jul 06, 2020
Khoa Nguyen, Konstantinos Drossos, Tuomas Virtanen


  Access Paper or Ask Questions

Active Learning for Sound Event Detection


Feb 12, 2020
Shuyang Zhao, Toni Heittola, Tuomas Virtanen


  Access Paper or Ask Questions

Sound Event Detection with Depthwise Separable and Dilated Convolutions


Feb 02, 2020
Konstantinos Drossos, Stylianos I. Mimilakis, Shayan Gharib, Yanxiong Li, Tuomas Virtanen


  Access Paper or Ask Questions

Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters


Nov 01, 2019
Niccoló Nicodemo, Gaurav Naithani, Konstantinos Drossos, Tuomas Virtanen, Roberto Saletti


  Access Paper or Ask Questions

Clotho: An Audio Captioning Dataset


Oct 21, 2019
Konstantinos Drossos, Samuel Lipping, Tuomas Virtanen


  Access Paper or Ask Questions

Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling


Jul 22, 2019
Konstantinos Drossos, Shayan Gharib, Paul Magron, Tuomas Virtanen

* Fixed the display of URLs at footnote 

  Access Paper or Ask Questions

Deep Learning for Audio Signal Processing


May 25, 2019
Hendrik Purwins, Bo Li, Tuomas Virtanen, Jan Schlüter, Shuo-yiin Chang, Tara Sainath

* Journal of Selected Topics of Signal Processing 14, No. 8 (2019) 
* 15 pages, 2 pdf figures 

  Access Paper or Ask Questions

Zero-Shot Audio Classification Based on Class Label Embeddings


May 06, 2019
Huang Xie, Tuomas Virtanen

* 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 

  Access Paper or Ask Questions

Localization, Detection and Tracking of Multiple Moving Sound Sources with a Convolutional Recurrent Neural Network


Apr 29, 2019
Sharath Adavanne, Archontis Politis, Tuomas Virtanen


  Access Paper or Ask Questions

Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification


Apr 24, 2019
Konstantinos Drossos, Paul Magron, Tuomas Virtanen


  Access Paper or Ask Questions

Unsupervised adversarial domain adaptation for acoustic scene classification


Aug 17, 2018
Shayan Gharib, Konstantinos Drossos, Emre Çakir, Dmitriy Serdyuk, Tuomas Virtanen


  Access Paper or Ask Questions

Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network


Aug 05, 2018
Sharath Adavanne, Archontis Politis, Tuomas Virtanen

* EUSIPCO 2018 

  Access Paper or Ask Questions

Acoustic Scene Classification: A Competition Review


Aug 02, 2018
Shayan Gharib, Honain Derrar, Daisuke Niizumi, Tuukka Senttula, Janne Tommola, Toni Heittola, Tuomas Virtanen, Heikki Huttunen

* This work has been accepted in IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2018). Copyright may be transferred without notice, after which this version may no longer be accessible 

  Access Paper or Ask Questions

End-to-End Polyphonic Sound Event Detection Using Convolutional Recurrent Neural Networks with Learned Time-Frequency Representation Input


May 09, 2018
Emre Çakır, Tuomas Virtanen

* accepted to IJCNN 2018 

  Access Paper or Ask Questions

Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features


Jan 29, 2018
Sharath Adavanne, Archontis Politis, Tuomas Virtanen


  Access Paper or Ask Questions

Automated Audio Captioning with Recurrent Neural Networks


Oct 24, 2017
Konstantinos Drossos, Sharath Adavanne, Tuomas Virtanen

* Presented at the 11th IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2017 

  Access Paper or Ask Questions

Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features


Jun 07, 2017
Sharath Adavanne, Giambattista Parascandolo, Pasi Pertilä, Toni Heittola, Tuomas Virtanen


  Access Paper or Ask Questions

Stacked Convolutional and Recurrent Neural Networks for Music Emotion Recognition


Jun 07, 2017
Miroslav Malik, Sharath Adavanne, Konstantinos Drossos, Tuomas Virtanen, Dasa Ticha, Roman Jarina

* Accepted for Sound and Music Computing (SMC 2017) 

  Access Paper or Ask Questions

Sound Event Detection Using Spatial Features and Convolutional Recurrent Neural Network


Jun 07, 2017
Sharath Adavanne, Pasi Pertilä, Tuomas Virtanen

* Accepted for IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017) 

  Access Paper or Ask Questions

Stacked Convolutional and Recurrent Neural Networks for Bird Audio Detection


Jun 07, 2017
Sharath Adavanne, Konstantinos Drossos, Emre Çakır, Tuomas Virtanen

* Accepted for European Signal Processing Conference 2017 

  Access Paper or Ask Questions