Jakob Drachmann Havtorn

A Brief Overview of Unsupervised Neural Speech Representation Learning

Mar 01, 2022
Lasse Borgholt, Jakob Drachmann Havtorn, Joakim Edin, Lars Maaløe, Christian Igel

Figure 2 for A Brief Overview of Unsupervised Neural Speech Representation Learning

Figure 3 for A Brief Overview of Unsupervised Neural Speech Representation Learning

Figure 4 for A Brief Overview of Unsupervised Neural Speech Representation Learning

* The 2nd Workshop on Self-supervised Learning for Audio and Speech Processing (SAS) at AAAI

Access Paper or Ask Questions

Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?

Nov 29, 2021
Lasse Borgholt, Jakob Drachmann Havtorn, Mostafa Abdou, Joakim Edin, Lars Maaløe, Anders Søgaard, Christian Igel

Figure 2 for Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?

Figure 3 for Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?

Figure 4 for Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?

* Under review as a conference paper at ICASSP 2022

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

Figure 2 for Do End-to-End Speech Recognition Models Care About Context?

Figure 3 for Do End-to-End Speech Recognition Models Care About Context?

Figure 4 for Do End-to-End Speech Recognition Models Care About Context?

* 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

Figure 2 for On Scaling Contrastive Representations for Low-Resource Speech Recognition

Figure 3 for On Scaling Contrastive Representations for Low-Resource Speech Recognition

Figure 4 for On Scaling Contrastive Representations for Low-Resource Speech Recognition

* {\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 02, 2020
Jakob Drachmann Havtorn, Jan Latko, Joakim Edin, Lasse Borgholt, Lars Maaløe, Lorenzo Belgrano, Nicolai Frost Jakobsen, Regitze Sdun, Željko Agić

Figure 2 for MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech

Figure 3 for MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech

Figure 4 for MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech

* Accepted at ACL 2020

Access Paper or Ask Questions