Search Results for author: Lars Maaløe

Found 12 papers, 6 papers with code

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

no code implementations17 Feb 2021 Lasse Borgholt, Jakob Drachmann Havtorn, Željko Agić, Anders Søgaard, Lars Maaløe, Christian Igel

We test this hypothesis by measuring temporal context sensitivity and evaluate how the models perform when we constrain the amount of contextual information in the audio input.

End-To-End Speech Recognition Language Modelling +1

Hierarchical VAEs Know What They Don't Know

1 code implementation16 Feb 2021 Jakob D. Havtorn, Jes Frellsen, Søren Hauberg, Lars Maaløe

Deep generative models have been demonstrated as state-of-the-art density estimators.

Out-of-Distribution Detection

On Scaling Contrastive Representations for Low-Resource Speech Recognition

no code implementations1 Feb 2021 Lasse Borgholt, Tycho Max Sylvester Tax, Jakob Drachmann Havtorn, Lars Maaløe, Christian Igel

We explore the performance of such systems without fine-tuning by training a state-of-the-art speech recognizer on the fixed representations from the computationally demanding wav2vec 2. 0 framework.

Self-Supervised Learning Speech Recognition

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

no code implementations ACL 2020 Jakob D. Havtorn, Jan Latko, Joakim Edin, Lasse Borgholt, Lars Maaløe, Lorenzo Belgrano, Nicolai F. Jacobsen, Regitze Sdun, Željko Agić

We address a challenging and practical task of labeling questions in speech in real time during telephone calls to emergency medical services in English, which embeds within a broader decision support system for emergency call-takers.

Speech Recognition

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

2 code implementations NeurIPS 2019 Lars Maaløe, Marco Fraccaro, Valentin Liévin, Ole Winther

In this paper we close the performance gap by constructing VAE models that can effectively utilize a deep hierarchy of stochastic variables and model complex covariance structures.

Anomaly Detection Image Generation +1

Feature Map Variational Auto-Encoders

no code implementations ICLR 2018 Lars Maaløe, Ole Winther

There have been multiple attempts with variational auto-encoders (VAE) to learn powerful global representations of complex data using a combination of latent stochastic variables and an autoregressive model over the dimensions of the data.

Image Generation

Utilizing Domain Knowledge in End-to-End Audio Processing

1 code implementation1 Dec 2017 Tycho Max Sylvester Tax, Jose Luis Diez Antich, Hendrik Purwins, Lars Maaløe

End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations.

Environmental Sound Classification General Classification

Exploiting Nontrivial Connectivity for Automatic Speech Recognition

no code implementations28 Nov 2017 Marius Paraschiv, Lasse Borgholt, Tycho Max Sylvester Tax, Marco Singh, Lars Maaløe

Nontrivial connectivity has allowed the training of very deep networks by addressing the problem of vanishing gradients and offering a more efficient method of reusing parameters.

General Classification Image Classification +1

Semi-Supervised Generation with Cluster-aware Generative Models

no code implementations3 Apr 2017 Lars Maaløe, Marco Fraccaro, Ole Winther

Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning.

General Classification

Auxiliary Deep Generative Models

1 code implementation17 Feb 2016 Lars Maaløe, Casper Kaae Sønderby, Søren Kaae Sønderby, Ole Winther

The auxiliary variables leave the generative model unchanged but make the variational distribution more expressive.

Recurrent Spatial Transformer Networks

2 code implementations17 Sep 2015 Søren Kaae Sønderby, Casper Kaae Sønderby, Lars Maaløe, Ole Winther

We investigate different down-sampling factors (ratio of pixel in input and output) for the SPN and show that the RNN-SPN model is able to down-sample the input images without deteriorating performance.

Cannot find the paper you are looking for? You can Submit a new open access paper.