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 Lars Maaløe

Hierarchical VAEs Know What They Don't Know


Mar 01, 2021
Jakob D. Havtorn, Jes Frellsen, Søren Hauberg, Lars Maaløe

* 18 pages, source code available at https://github.com/vlievin/biva-pytorch and https://github.com/larsmaaloee/BIVA 

  Access Paper or Ask Questions

Do End-to-End Speech Recognition Models Care About Context?


Feb 17, 2021
Lasse Borgholt, Jakob Drachmann Havtorn, Željko Agić, Anders Søgaard, Lars Maaløe, Christian Igel

* Published in the proceedings of INTERSPEECH 2020, pp. 4352-4356 

  Access Paper or Ask Questions

On Scaling Contrastive Representations for Low-Resource Speech Recognition


Feb 01, 2021
Lasse Borgholt, Tycho Max Sylvester Tax, Jakob Drachmann Havtorn, Lars Maaløe, Christian Igel

* {\copyright} 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 

  Access Paper or Ask Questions

MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech


May 12, 2020
Jakob D. Havtorn, Jan Latko, Joakim Edin, Lasse Borgholt, Lars Maaløe, Lorenzo Belgrano, Nicolai F. Jacobsen, Regitze Sdun, Željko Agić

* Accepted at ACL 2020 

  Access Paper or Ask Questions

BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling


Feb 06, 2019
Lars Maaløe, Marco Fraccaro, Valentin Liévin, Ole Winther


  Access Paper or Ask Questions

On the Inductive Bias of Word-Character-Level Multi-Task Learning for Speech Recognition


Nov 28, 2018
Jan Kremer, Lasse Borgholt, Lars Maaløe

* Accepted at the IRASL workshop at NeurIPS 2018 

  Access Paper or Ask Questions

Utilizing Domain Knowledge in End-to-End Audio Processing


Dec 01, 2017
Tycho Max Sylvester Tax, Jose Luis Diez Antich, Hendrik Purwins, Lars Maaløe

* Accepted at the ML4Audio workshop at the NIPS 2017 

  Access Paper or Ask Questions

Exploiting Nontrivial Connectivity for Automatic Speech Recognition


Nov 28, 2017
Marius Paraschiv, Lasse Borgholt, Tycho Max Sylvester Tax, Marco Singh, Lars Maaløe

* Accepted at the ML4Audio workshop at the NIPS 2017 

  Access Paper or Ask Questions

Semi-Supervised Generation with Cluster-aware Generative Models


Apr 03, 2017
Lars Maaløe, Marco Fraccaro, Ole Winther


  Access Paper or Ask Questions

Auxiliary Deep Generative Models


Jun 16, 2016
Lars Maaløe, Casper Kaae Sønderby, Søren Kaae Sønderby, Ole Winther

* Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA, 2016, JMLR: Workshop and Conference Proceedings volume 48, Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA, 2016 

  Access Paper or Ask Questions

Ladder Variational Autoencoders


May 27, 2016
Casper Kaae Sønderby, Tapani Raiko, Lars Maaløe, Søren Kaae Sønderby, Ole Winther


  Access Paper or Ask Questions

Recurrent Spatial Transformer Networks


Sep 17, 2015
Søren Kaae Sønderby, Casper Kaae Sønderby, Lars Maaløe, Ole Winther


  Access Paper or Ask Questions