Explainable artificial intelligence (XAI) in biomedicine: Making AI decisions trustworthy for physicians and patients

J Lötsch, D Kringel, A Ultsch - BioMedInformatics, 2021 - mdpi.com
The use of artificial intelligence (AI) systems in biomedical and clinical settings can disrupt
the traditional doctor–patient relationship, which is based on trust and transparency in …

Multilingual conversational systems to drive the collection of patient-reported outcomes and integration into clinical workflows

I Mlakar, V Šafran, D Hari, M Rojc, G Alankuş… - Symmetry, 2021 - mdpi.com
Patient-reported outcomes (PROs) and their use in the clinical workflow can improve cancer
survivors' outcomes and quality of life. However, there are several challenges regarding …

Domain adaptation speech-to-text for low-resource European portuguese using deep learning

E Medeiros, L Corado, L Rato, P Quaresma… - Future Internet, 2023 - mdpi.com
Automatic speech recognition (ASR), commonly known as speech-to-text, is the process of
transcribing audio recordings into text, ie, transforming speech into the respective sequence …

Multilingual Framework for Risk Assessment and Symptom Tracking (MRAST)

V Šafran, S Lin, J Nateqi, AG Martin, U Smrke, U Ariöz… - Sensors, 2024 - mdpi.com
The importance and value of real-world data in healthcare cannot be overstated because it
offers a valuable source of insights into patient experiences. Traditional patient-reported …

Improving Text-Independent Forced Alignment to Support Speech-Language Pathologists with Phonetic Transcription

Y Li, BJ Wohlan, DS Pham, KY Chan, R Ward… - Sensors, 2023 - mdpi.com
Problem: Phonetic transcription is crucial in diagnosing speech sound disorders (SSDs) but
is susceptible to transcriber experience and perceptual bias. Current forced alignment (FA) …

Evaluating novel speech transcription architectures on the spanish RTVE2020 database

A Álvarez, H Arzelus, IG Torre, A González-Docasal - Applied Sciences, 2022 - mdpi.com
This work presents three novel speech recognition architectures evaluated on the Spanish
RTVE2020 dataset, employed as the main evaluation set in the Albayzín S2T Transcription …

Generalisation gap of keyword spotters in a cross-speaker low-resource scenario

Ł Lepak, K Radzikowski, R Nowak, KJ Piczak - Sensors, 2021 - mdpi.com
Models for keyword spotting in continuous recordings can significantly improve the
experience of navigating vast libraries of audio recordings. In this paper, we describe the …

BayesSpeech: A Bayesian Transformer Network for Automatic Speech Recognition

W Rieger - arXiv preprint arXiv:2301.11276, 2023 - arxiv.org
Recent developments using End-to-End Deep Learning models have been shown to have
near or better performance than state of the art Recurrent Neural Networks (RNNs) on …

Joint Audio Captioning Transformer and Stable Diffusion for Audio-to-Image

J Yu - … Technologies and Sustainable Society: Proceedings of …, 2024 - books.google.com
In the present society where artificial intelligence (AI) is all over the place, there is a growing
trend in using AI for innovative applications in various academic and industrial fields. This …

Joint Audio Captioning Transformer and Stable Diffusion for Audio-to-Image Generation

J Yu - IEEE International Conference on Advanced Infocomm …, 2023 - Springer
In the present society where artificial intelligence (AI) is all over the place, there is a growing
trend in using AI for innovative applications in various academic and industrial fields. This …