Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Havard, William N."'
The language acquisition literature shows that children do not build their lexicon by segmenting the spoken input into phonemes and then building up words from them, but rather adopt a top-down approach and start by segmenting word-like units and the
Externí odkaz:
http://arxiv.org/abs/2006.08387
In this paper, we study how word-like units are represented and activated in a recurrent neural model of visually grounded speech. The model used in our experiments is trained to project an image and its spoken description in a common representation
Externí odkaz:
http://arxiv.org/abs/1909.08491
Autor:
Boito, Marcely Zanon, Havard, William N., Garnerin, Mahault, Ferrand, Éric Le, Besacier, Laurent
The CMU Wilderness Multilingual Speech Dataset (Black, 2019) is a newly published multilingual speech dataset based on recorded readings of the New Testament. It provides data to build Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) model
Externí odkaz:
http://arxiv.org/abs/1907.12895
We investigate the behaviour of attention in neural models of visually grounded speech trained on two languages: English and Japanese. Experimental results show that attention focuses on nouns and this behaviour holds true for two very typologically
Externí odkaz:
http://arxiv.org/abs/1902.03052
Autor:
Havard, William N
Publikováno v:
Sciences de l'Homme et Société. 2017
Many languages are on the brink of extinction and many disappear each and every year at a rate never seen before. Field linguists lack the time and the means to document and describe all of them before they die out. The goal of our work is to help th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c0ea3685ee91a14ffefb612d3536e2a
https://dumas.ccsd.cnrs.fr/dumas-01562024/file/HAVARD_William_M2_IDL.pdf
https://dumas.ccsd.cnrs.fr/dumas-01562024/file/HAVARD_William_M2_IDL.pdf