Zobrazeno 1 - 10
of 256
pro vyhledávání: '"Mark J. F. Gales"'
Publikováno v:
PLOS Digital Health, Vol 3, Iss 11, p e0000436 (2024)
The detection of heart disease using a stethoscope requires significant skill and time, making it expensive and impractical for widespread screening in low-resource environments. Machine learning analysis of heart sound recordings can improve upon th
Externí odkaz:
https://doaj.org/article/511d49db92c44e9c84afe45165238583
Autor:
Anton Ragni, Mark J. F. Gales, Oliver Rose, Katherine M. Knill, Alexandros Kastanos, Qiujia Li, Preben M. Ness
Accurate confidence measures for predictions from machine learning techniques play a critical role in the deployment and training of many speech and language processing applications. For example, confidence scores are important when making use of aut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::284256c11327a54ba44b4477a35c7d3a
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e8d7ef901abebdd50c4a2ff358fdbeed
https://doi.org/10.21437/interspeech.2021-1405
https://doi.org/10.21437/interspeech.2021-1405
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 27:1725-1736
In automatic speech recognition, performance gains can often be obtained by combining an ensemble of multiple models. However, this can be computationally expensive when performing recognition. Teacher–student learning alleviates this cost by train
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ee7fd6f4b97fff4a61ad1f57194274a
https://doi.org/10.1109/taslp.2019.2929859
https://doi.org/10.1109/taslp.2019.2929859
Publikováno v:
ICASSP
A significant concern with deep learning based approaches is that they are difficult to interpret, which means detecting bias in network predictions can be challenging. Concept Activation Vectors (CAVs) have been proposed to address this problem. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::53d49a113de31a2b1e6850bac085cc1b
https://doi.org/10.1109/icassp39728.2021.9413988
https://doi.org/10.1109/icassp39728.2021.9413988
Publikováno v:
ICASSP
For many challenging tasks there is often limited data to train the systems in an end-to-end fashion, which has become increasingly popular for deep-learning. However, these tasks can normally be split into multiple separate modules, with significant
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0900b9e600b3625de9f70b8439e3d041
https://doi.org/10.1109/icassp39728.2021.9414510
https://doi.org/10.1109/icassp39728.2021.9414510
Autor:
Mark J. F. Gales, Potsawee Manakul
Publikováno v:
ACL/IJCNLP (1)
Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the target ta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb73d1cfef15bd17fc2eeaf5641d0477
http://arxiv.org/abs/2105.03801
http://arxiv.org/abs/2105.03801
Publikováno v:
ICASSP
Ensemble approaches are commonly used techniques to improving a system by combining multiple model predictions. Additionally these schemes allow the uncertainty, as well as the source of the uncertainty, to be derived for the prediction. Unfortunatel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::feef05cfd444f31e0a1c4d9db3b36830
http://arxiv.org/abs/2012.07535
http://arxiv.org/abs/2012.07535
Publikováno v:
INTERSPEECH
Deep learning has dramatically improved the performance of automated systems on a range of tasks including spoken language assessment. One of the issues with these deep learning approaches is that they tend to be overconfident in the decisions that t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa4a9201bfc779ca3fad3a8572a9e426
https://doi.org/10.21437/interspeech.2020-2238
https://doi.org/10.21437/interspeech.2020-2238
Publikováno v:
INTERSPEECH
ive summarization is a standard task for written documents, such as news articles. Applying summarization schemes to spoken documents is more challenging, especially in situations involving human interactions, such as meetings. Here, utterances tend
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c89a96ecbbc488bc141285613cc6966e
https://doi.org/10.21437/interspeech.2020-1683
https://doi.org/10.21437/interspeech.2020-1683