[HTML][HTML] Artificial intelligence in emergency medicine: viewpoint of current applications and foreseeable opportunities and challenges

G Chenais, E Lagarde, C Gil-Jardiné - Journal of Medical Internet Research, 2023 - jmir.org
Emergency medicine and its services have reached a breaking point during the COVID-19
pandemic. This pandemic has highlighted the failures of a system that needs to be …

Improved Mask-CTC for non-autoregressive end-to-end ASR

Y Higuchi, H Inaguma, S Watanabe… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
For real-world deployment of automatic speech recognition (ASR), the system is desired to
be capable of fast inference while relieving the requirement of computational resources. The …

Context-aware adversarial training for name regularity bias in named entity recognition

A Ghaddar, P Langlais, A Rashid… - Transactions of the …, 2021 - direct.mit.edu
In this work, we examine the ability of NER models to use contextual information when
predicting the type of an ambiguous entity. We introduce NRB, a new testbed carefully …

A retrospective study on machine learning-assisted stroke recognition for medical helpline calls

J Wenstrup, JD Havtorn, L Borgholt, SN Blomberg… - NPJ digital …, 2023 - nature.com
Advanced stroke treatment is time-dependent and, therefore, relies on recognition by call-
takers at prehospital telehealth services to ensure fast hospitalisation. This study aims to …

[HTML][HTML] Machine learning can support dispatchers to better and faster recognize out-of-hospital cardiac arrest during emergency calls: a retrospective study

F Byrsell, A Claesson, M Ringh, L Svensson… - Resuscitation, 2021 - Elsevier
Aim Fast recognition of out-of-hospital cardiac arrest (OHCA) by dispatchers might increase
survival. The aim of this observational study of emergency calls was to (1) examine whether …

Speaker conditioning of acoustic models using affine transformation for multi-speaker speech recognition

M Yousefi, JHL Hansen - 2021 IEEE Automatic Speech …, 2021 - ieeexplore.ieee.org
This study addresses the problem of single-channel Automatic Speech Recognition of a
target speaker within an overlap speech scenario. In the proposed method, the hidden …

On scaling contrastive representations for low-resource speech recognition

L Borgholt, TMS Tax, JD Havtorn… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
Recent advances in self-supervised learning through contrastive training have shown that it
is possible to learn a competitive speech recognition system with as little as 10 minutes of …

Using natural language processing techniques to study and regulate emergency department flows: development and application to the study of trauma risks based on …

G Chenais - 2023 - theses.hal.science
The TARPON (Traitement Automatique des Résumés de Passage aux urgences dans le but
de créer un Observatoire National du traumatisme) project aims to demonstrate the …

Speech-to-text models to transcribe emergency calls

JA Thuestad, Ø Grutle - 2023 - bora.uib.no
This thesis is part of the larger project “AI-Support in Medical Emergency Calls (AISMEC)”,
which aims to develop a decision support system for Emergency Medical Communication …