Yasunori Ohishi
Yasunori Ohishi
Home
Posts
Skills
Publications
Projects
Experience
Contact
Light
Dark
Automatic
Crossmodal
Best paper candidates at ACM Multimedia 2022!!
We are very proud that our paper “ConceptBeam: Concept Driven Target Speech Extraction” was one of the best paper candidates at ACM Multimedia 2022.
Yasunori Ohishi
Oct 11, 2022
1 min read
Crossmodal
,
Visually-grounded speech
Project
ConceptBeam
Target speech extraction based on “concept” or semantic information.
Yasunori Ohishi
,
Marc Delcroix
,
Tsubasa Ochiai
,
Shoko Araki
,
Daiki Takeuchi
,
Daisuke Niizumi
,
Akisato Kimura
,
Noboru Harada
,
Kunio Kashino
PDF
arXiv
A paper presented at ACM Multimedia 2022
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%).
Yasunori Ohishi
Jul 1, 2022
1 min read
Crossmodal
,
Visually-grounded speech
Project
Our dataset publicly available
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.
Yasunori Ohishi
Nov 18, 2021
1 min read
Dataset
,
Visually-grounded speech
,
Crossmodal
The Places Japanese audio caption corpus
Japanese spoken captions for the Places205 image dataset
Yasunori Ohishi
,
Akisato Kimura
,
Takahito Kawanishi
,
Kunio Kashino
,
David Harwath
,
James Glass
PDF
dataset
Cite
×