output
20162020
most citedHow2: A Large-scale Dataset for Multimodal Language Understanding

187 citations

9 papers

eess.AS2020

Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models

Natalia Tomashenko, Yuri Khokhlov, Yannick Esteve

In this paper we investigate the GMM-derived (GMMD) features for adaptation of deep neural network (DNN) acoustic models. The adaptation of the DNN trained on GMMD features is done…

cs.CL2020★ 12 cited

Dialogue history integration into end-to-end signal-to-concept spoken language understanding systems

Natalia Tomashenko, Christian Raymond, Antoine Caubriere +2

This work investigates the embeddings for representing dialog history in spoken language understanding (SLU) systems. We focus on the scenario when the semantic information is extr…

cs.CY2018

Éléments pour la conception de Jeux Éducatifs sur Mobile

Aous Karoui, Iza Marfisi-Schottman, Sébastien George

School classrooms are equipped with more and more mobile devices. However, the latest studies show that their use by teachers is still very limited because of a lack of resources a…

cs.CL2018★ 187 cited

How2: A Large-scale Dataset for Multimodal Language Understanding

Ramon Sanabria, Ozan Caglayan, Shruti Palaskar +4

In this paper, we introduce How2, a multimodal collection of instructional videos with English subtitles and crowdsourced Portuguese translations. We also present integrated sequen…

cs.CY2018★ 1 cited

Extraire et r{é}utiliser des patrons de conception {à} partir de Learning Games existants

Iza Marfisi-Schottman, Claudine Piau-Toffolon

Learning Games (LGs) are promising pedagogical tools but their design still remains experimental. Inspired by design-pattern based methods, recommended in educational domains, we p…

cs.HC2018

Mobile Learning Game Authoring Tools: Assessment, Synthesis and Proposals

Aous Karoui, Iza Marfisi-Schottman, Sébastien George

Mobile Learning Games (MLGs) show great potential for increasing engagement, creativity and authentic learning. Yet, despite their great potential for education, the use of MLGs by…