Zobrazeno 1 - 10
of 1 826
pro vyhledávání: '"A. Van Hamme"'
Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often sensitive
Externí odkaz:
http://arxiv.org/abs/2409.02565
Aphasia is a language disorder affecting one third of stroke patients. Current aphasia assessment does not consider natural speech due to the time consuming nature of manual transcriptions and a lack of knowledge on how to analyze such data. Here, we
Externí odkaz:
http://arxiv.org/abs/2408.14082
Autor:
Eeckt, Steven Vander, Van hamme, Hugo
Adapting Automatic Speech Recognition (ASR) models to new domains leads to Catastrophic Forgetting (CF) of previously learned information. This paper addresses CF in the challenging context of Online Continual Learning (OCL), with tasks presented as
Externí odkaz:
http://arxiv.org/abs/2406.12503
While extensively explored in text-based tasks, Named Entity Recognition (NER) remains largely neglected in spoken language understanding. Existing resources are limited to a single, English-only dataset. This paper addresses this gap by introducing
Externí odkaz:
http://arxiv.org/abs/2405.11519
Autor:
De Clercq, Pieter, Puffay, Corentin, Kries, Jill, Van Hamme, Hugo, Vandermosten, Maaike, Francart, Tom, Vanthornhout, Jonas
Aphasia, a language disorder primarily caused by a stroke, is traditionally diagnosed using behavioral language tests. However, these tests are time-consuming, require manual interpretation by trained clinicians, suffer from low ecological validity,
Externí odkaz:
http://arxiv.org/abs/2401.10291
Autor:
Poncelet, Jakob, Van hamme, Hugo
Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete acoustic uni
Externí odkaz:
http://arxiv.org/abs/2309.13994
In online conferencing applications, estimating the perceived quality of an audio signal is crucial to ensure high quality of experience for the end user. The most reliable way to assess the quality of a speech signal is through human judgments in th
Externí odkaz:
http://arxiv.org/abs/2308.12077
To investigate how the auditory system processes natural speech, models have been created to relate the electroencephalography (EEG) signal of a person listening to speech to various representations of the speech. Mainly the speech envelope has been
Externí odkaz:
http://arxiv.org/abs/2308.00161
Autor:
Eeckt, Steven Vander, Van hamme, Hugo
Fine-tuning an Automatic Speech Recognition (ASR) model to new domains results in degradation on original domains, referred to as Catastrophic Forgetting (CF). Continual Learning (CL) attempts to train ASR models without suffering from CF. While in A
Externí odkaz:
http://arxiv.org/abs/2306.10860
Autor:
Qi, Jinzi, Van hamme, Hugo
In dysarthric speech recognition, data scarcity and the vast diversity between dysarthric speakers pose significant challenges. While finetuning has been a popular solution, it can lead to overfitting and low parameter efficiency. Adapter modules off
Externí odkaz:
http://arxiv.org/abs/2306.07090