Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Ewan Dunbar"'
Autor:
Ewan Dunbar, Emmanuel Dupoux
Publikováno v:
Frontiers in Psychology, Vol 7 (2016)
We investigate the idea that the languages of the world have developed coherent sound systems in which having one sound increases or decreases the chances of having certain other sounds, depending on shared properties of those sounds. We investigate
Externí odkaz:
https://doaj.org/article/81644ee9b327433fb215bd71dc9cf68c
Autor:
Alexis Wellwood, Ewan Dunbar
Publikováno v:
Glossa, Vol 1, Iss 1 (2016)
How much meaning can a morpheme have? Syntactic and morphological analyses generally underdetermine when distinctions in meaning between two forms are due to (i) the presence of an additional syntactic head or to (ii) different information coded on t
Externí odkaz:
https://doaj.org/article/285ffbeccf1346a1ad4f30a0d7dc5e8e
Autor:
Juliette Millet, Charlotte Caucheteux, Pierre Orhan, Yves Boubenec, Alexandre Gramfort, Pallier, Christophe C., Ewan Dunbar, Jean-Rémi King
Publikováno v:
Actes de NeurIPS 2022
NeurIPS 2022-36th Conference on Neural Information Processing Systems
NeurIPS 2022-36th Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States
HAL
Arxiv
NeurIPS 2022-36th Conference on Neural Information Processing Systems
NeurIPS 2022-36th Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States
HAL
Arxiv
Several deep neural networks have recently been shown to generate activations similar to those of the brain in response to the same input. These algorithms, however, remain largely implausible: they require (1) extraordinarily large amounts of data,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d52658331e88efb91278b28b354d095
http://arxiv.org/abs/2206.01685
http://arxiv.org/abs/2206.01685
Our native language influences the way we perceive speech sounds, affecting our ability to discriminate non-native sounds. We compare two ideas about the influence of the native language on speech perception: the Perceptual Assimilation Model, which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4fed039977287973a5f8fd6bc7113a6e
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing
IEEE Journal of Selected Topics in Signal Processing, In press, ⟨10.1109/jstsp.2022.3206084⟩
IEEE Journal of Selected Topics in Signal Processing, In press, ⟨10.1109/jstsp.2022.3206084⟩
International audience; Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as phone
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d65eb9563594a41fb13ed98a08c2e55
https://hal.science/hal-03789716
https://hal.science/hal-03789716
Autor:
Ewan Dunbar, Emmanuel Dupoux, Mathieu Bernard, Patricia Rozé, Maureen de Seyssel, Morgane Riviere, Tu Anh Nguyen, Nicolas Hamilakis, Eugene Kharitonov
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2021, pp.1-1. ⟨10.1109/TPAMI.2021.3083839⟩
Interspeech 2021-Conference of the International Speech Communication Association
Interspeech 2021-Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. ⟨10.1109/TPAMI.2021.3083839⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2021, pp.1-1. ⟨10.1109/TPAMI.2021.3083839⟩
Interspeech 2021-Conference of the International Speech Communication Association
Interspeech 2021-Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. ⟨10.1109/TPAMI.2021.3083839⟩
We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of audio from Eng
Autor:
Ewan Dunbar
Publikováno v:
Language
Language, Linguistic Society of America, 2019, 95 (1), pp.e87-e98. ⟨10.1353/lan.2019.0013⟩
Language, 2019, 95 (1), pp.e87-e98. ⟨10.1353/lan.2019.0013⟩
Language, Linguistic Society of America, 2019, 95 (1), pp.e87-e98. ⟨10.1353/lan.2019.0013⟩
Language, 2019, 95 (1), pp.e87-e98. ⟨10.1353/lan.2019.0013⟩
International audience; On the same list that ranked Syntactic Structures as the number one most influential twentieth-century work in cognitive science, the number two work cited is David Marr's Vision (Marr, 1982). Marr proposed that the only way t
Autor:
Louis Fournier, Ewan Dunbar
Publikováno v:
EACL
EACL 2021-16th Conference of the European Chapter of the Association for Computational Linguistics
EACL 2021-16th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2021, Online, France. pp.2129-2134, ⟨10.18653/v1/2021.eacl-main.182⟩
EACL 2021-16th Conference of the European Chapter of the Association for Computational Linguistics
EACL 2021-16th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2021, Online, France. pp.2129-2134, ⟨10.18653/v1/2021.eacl-main.182⟩
Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between "jump" and "jumped" will be in a similar direction to that of "walk" and "walked," and so on). Several attempts have been made
Autor:
Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé, Morgane Rivière, Evgeny Kharitonov, Alexei Baevski, Ewan Dunbar, Emmanuel Dupoux
Publikováno v:
NeuRIPS Workshop on Self-Supervised Learning for Speech and Audio Processing
NeuRIPS Workshop on Self-Supervised Learning for Speech and Audio Processing, Dec 2020, Virtuel, France
HAL
NeuRIPS Workshop on Self-Supervised Learning for Speech and Audio Processing, Dec 2020, Virtuel, France
HAL
We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot metrics probin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d8cf1c7e2631ab6a0ff4004e19a204f9
https://hal.archives-ouvertes.fr/hal-03070362/document
https://hal.archives-ouvertes.fr/hal-03070362/document
Autor:
Xuan-Nga Cao, Mathieu Bernard, Lucas Ondel, Julien Karadayi, Laurent Besacier, Sakriani Sakti, Ewan Dunbar, Robin Algayres, Emmanuel Dupoux
Publikováno v:
Interspeech 2020-Conference of the International Speech Communication Association
Interspeech 2020-Conference of the International Speech Communication Association, Oct 2020, Shangai / Virtual, China
HAL
INTERSPEECH
Interspeech 2020-Conference of the International Speech Communication Association, Oct 2020, Shangai / Virtual, China
HAL
INTERSPEECH
International audience; We present the Zero Resource Speech Challenge 2020, which aims at learning speech representations from raw audio signals without any labels. It combines the data sets and metrics from two previous benchmarks (2017 and 2019) an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::57f2b6686cb2733352cb2b76889f4fe0
https://hal.archives-ouvertes.fr/hal-02962224/file/interspeech_2020___ZR2020_Summary_paper__Ewan_.pdf
https://hal.archives-ouvertes.fr/hal-02962224/file/interspeech_2020___ZR2020_Summary_paper__Ewan_.pdf