5 papers
Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech
William N. Havard, Jean-Pierre Chevrot, Laurent Besacier
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 ado…
Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech
William N. Havard, Jean-Pierre Chevrot, Laurent Besacier
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 p…
MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible
Marcely Zanon Boito, William N. Havard, Mahault Garnerin +2
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 b…
Models of Visually Grounded Speech Signal Pay Attention To Nouns: a Bilingual Experiment on English and Japanese
William N. Havard, Jean-Pierre Chevrot, Laurent Besacier
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 focu…
Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation
Xuanli He, Quan Hung Tran, William Havard +3
In spite of the recent success of Dialogue Act (DA) classification, the majority of prior works focus on text-based classification with oracle transcriptions, i.e. human transcript…