Crossmodal

We are very proud that our paper “ConceptBeam: Concept Driven Target Speech Extraction” was one of the best paper candidates at ACM Multimedia 2022.

Target speech extraction based on “concept” or semantic information.

We are pleased to announce that our paper “ConceptBeam: Concept Driven Target Speech Extraction” by Yasunori Ohishi, Marc Delcroix, Tsubasa Ochiai, Shoko Araki, Daiki Takeuchi, Daisuke Niizumi, Akisato Kimura, Noboru Harada, and Kunio Kashino has been accepted to ACM Multimedia 2022 (acceptance rate = 690/2473 = 27.9%).

We are excited to announce that our dataset, The Places audio caption (Japanese) 100K corpus, is now available. This speech corpus was collected to investigate the learning of spoken language (words, sub-word units, higher-level semantics, etc.) from visually-grounded speech.

Japanese spoken captions for the Places205 image dataset