Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Lasse Borgholt"'
Autor:
Jonathan Wenstrup, Jakob Drachmann Havtorn, Lasse Borgholt, Stig Nikolaj Blomberg, Lars Maaloe, Michael R. Sayre, Hanne Christensen, Christina Kruuse, Helle Collatz Christensen
Publikováno v:
npj Digital Medicine, Vol 6, Iss 1, Pp 1-8 (2023)
Abstract 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 develop and assess the potential of machine learning in im
Externí odkaz:
https://doaj.org/article/32a67596e26b4c91b7ed8fcb17e4d93d
Autor:
Abdelrahman Mohamed, Hung-yi Lee, Lasse Borgholt, Jakob D. Havtorn, Joakim Edin, Christian Igel, Katrin Kirchhoff, Shang-Wen Li, Karen Livescu, Lars Maaloe, Tara N. Sainath, Shinji Watanabe
Publikováno v:
Mohamed, A, Lee, H, Borgholt, L, Havtorn, J D, Edin, J, Igel, C, Kirchhoff, K, Li, S-W, Livescu, K, Maaløe, L, Sainath, T N & Watanabe, S 2022, ' Self-Supervised Speech Representation Learning: A Review ', IEEE Journal of Selected Topics in Signal Processing, vol. 16, no. 6, pp. 1179-1210 . https://doi.org/10.1109/JSTSP.2022.3207050
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::545143f4d8a2d73ad2a084dd4dafe28e
http://arxiv.org/abs/2205.10643
http://arxiv.org/abs/2205.10643
Publikováno v:
Havtorn, J D, Borgholt, L, Hauberg, S, Frellsen, J & Maaløe, L 2022, Benchmarking Generative Latent Variable Models for Speech . in Proceedings of ICLR Workshop on Deep Generative Models for Highly Structured Data . ICLR Workshop on Deep Generative Models for Highly Structured Data, 29/04/2022 .
Technical University of Denmark Orbit
Technical University of Denmark Orbit
Stochastic latent variable models (LVMs) achieve state-of-the-art performance on natural image generation but are still inferior to deterministic models on speech. In this paper, we develop a speech benchmark of popular temporal LVMs and compare them
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::99ca19ca48f1b74959b7255395178b34
http://arxiv.org/abs/2202.12707
http://arxiv.org/abs/2202.12707
Publikováno v:
Borgholt, L, Havtorn, J D, Agic, Ž, Søgaard, A, Maaløe, L & Igel, C 2020, Do end-to-end speech recognition models care about context? in Proceedings of the Annual Conference of the International Speech Communication Association . Proceedings of the Annual Conference of the International Speech Communication Association, Interspeech, pp. 4352-4356, Interspeech 2020, Shanghai, China, 25/10/2020 . https://doi.org/10.21437/Interspeech.2020-1750
Borgholt, L, Havtorn, J D, Agic, Ž, Søgaard, A, Maaløe, L & Igel, C 2020, Do end-to-end speech recognition models care about context? in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH . vol. 2020-October, International Speech Communication Association (ISCA), pp. 4352-4356, 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020, Shanghai, China, 25/10/2020 . https://doi.org/10.21437/Interspeech.2020-1750
INTERSPEECH
Borgholt, L, Havtorn, J D, Agic, Ž, Søgaard, A, Maaløe, L & Igel, C 2020, Do end-to-end speech recognition models care about context? in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH . vol. 2020-October, International Speech Communication Association (ISCA), pp. 4352-4356, 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020, Shanghai, China, 25/10/2020 . https://doi.org/10.21437/Interspeech.2020-1750
INTERSPEECH
The two most common paradigms for end-to-end speech recognition are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models. It has been argued that the latter is better suited for learning an implicit language mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f03bc76f832fdcf78bda18a84982ee8
http://arxiv.org/abs/2102.09928
http://arxiv.org/abs/2102.09928
Publikováno v:
Borgholt, L, Tax, T M S, Havtorn, J D, Maaløe, L & Igel, C 2021, On scaling contrastive representations for low-resource speech recognition . in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing . vol. 2021-, IEEE, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing-Proceedings, pp. 3885-3889, 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, Ontario, Canada, 06/06/2021 . https://doi.org/10.1109/ICASSP39728.2021.9414310
ICASSP
ICASSP
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 labeled data. However, these systems are computationally expensiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a291b0d2bde1237368fa4c58d015cbe
http://arxiv.org/abs/2102.00850
http://arxiv.org/abs/2102.00850
Autor:
Jan Latko, Joakim Edin, Lorenzo Belgrano, Jakob D. Havtorn, Nicolai F. Jacobsen, Lasse Borgholt, Regitze Sdun, Lars Maaløe, Željko Agić
Publikováno v:
ACL
Havtorn, J D, Latko, J, Edin, J, Borgholt, L, Maaloe, L, Belgrano, L, Jacobsen, N F, Sdun, R & Agic, Z 2020, MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech . in Proceedings of 58 th Annual Meeting of the Association for Computational Linguistics . pp. 2370-2380, 58 th Annual Meeting of the Association for Computational Linguistics, 06/07/2020 .
Havtorn, J D, Latko, J, Edin, J, Borgholt, L, Maaloe, L, Belgrano, L, Jacobsen, N F, Sdun, R & Agic, Z 2020, MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech . in Proceedings of 58 th Annual Meeting of the Association for Computational Linguistics . pp. 2370-2380, 58 th Annual Meeting of the Association for Computational Linguistics, 06/07/2020 .
We address a challenging and practical task of labeling questions in speech in real time during telephone calls to emergency medical services in English, which embeds within a broader decision support system for emergency call-takers. We propose a no
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff35772ef17b0a914a191937f2072577
Publikováno v:
EMNLP
Sentiment analysis models often use ratings as labels, assuming that these ratings reflect the sentiment of the accompanying text. We investigate (i) whether human readers can infer ratings from review text, (ii) how human performance compares to a r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::860fa4ed7e8ca206e32e16c724226858
http://hdl.handle.net/11565/4006591
http://hdl.handle.net/11565/4006591