Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, MBE (Joint) |
2024-03-12 14:45 |
Tokyo |
The Univ. of Tokyo (Primary: On-site, Secondary: Online) |
Visualization of the learning process of ResNet revealing its learning dynamics Ryodo Yuge, Takashi Shinozaki (Kindai Univ.) NC2023-59 |
We visualize the impact of skip connections, a key element in residual networks (ResNet), and visualize its impact on th... [more] |
NC2023-59 p.94 |
AI |
2024-03-01 14:40 |
Aichi |
Room0221, Bldg.2-C, Nagoya Institute of Technology |
Request span extraction from dialog with Heterogeneous Graph Attention Networks Naoki Mizumoto, Katsuhide Fujita (TUAT) AI2023-41 |
In this study, we formulate the problem of extracting user requests from the dialogue history as a ``span extraction pro... [more] |
AI2023-41 pp.25-30 |
ET |
2023-11-11 14:50 |
Kagawa |
Kagawa University Saiwai-cho (Main) Campus / Online (Primary: On-site, Secondary: Online) |
Uncertainty Estimation in Neural Automatic Scoring Applying Multitask Learning of Regression and Classification Yuto Takahashi, Masaki Uto (UEC) ET2023-31 |
In writing tests, grading by humans can be expensive and is not always sufficiently accurate. To resolve this problem, a... [more] |
ET2023-31 pp.40-46 |
PRMU, IPSJ-CVIM |
2023-05-19 09:50 |
Aichi |
(Primary: On-site, Secondary: Online) |
Incorporating Signed Distance Fields to Improve Text-to-3D Generation Zhuofan Sun, Daichi Horita (Univ. of Tokyo), Satoshi Ikehata (NII), Kiyoharu Aizawa (Univ. of Tokyo) PRMU2023-9 |
Frameworks for generating 3D objects from text description have been proposed in recent years. These frameworks utilize ... [more] |
PRMU2023-9 pp.45-50 |
SP, IPSJ-SLP, EA, SIP [detail] |
2023-03-01 09:30 |
Okinawa |
(Primary: On-site, Secondary: Online) |
A Study on Scheduled Sampling for Neural Transducer-based ASR Takafumi Moriya, Takanori Ashihara, Hiroshi Sato, Kohei Matsuura, Tomohiro Tanaka, Ryo Masumura (NTT) EA2022-100 SIP2022-144 SP2022-64 |
In this paper, we propose scheduled sampling approaches suited for the recurrent neural network-transducer (RNNT) that i... [more] |
EA2022-100 SIP2022-144 SP2022-64 pp.147-152 |
HCGSYMPO (2nd) |
2022-12-14 - 2022-12-16 |
Kagawa |
Onsite (Sunport Takamatsu) and Online (Primary: On-site, Secondary: Online) |
Development of an interactive life support system for people with severely physically disability such as ALS using behavior prediction Yuto Mitsuta, Daisuke Katagami (TPU), Tomoki Miyamoto (UEC) |
In this study, we develop an interactive life support system that can operate home appliances around the user for people... [more] |
|
EA, SIP, SP, IPSJ-SLP [detail] |
2022-03-02 10:20 |
Okinawa |
(Primary: On-site, Secondary: Online) |
A Study on Hybrid RNN-T/Attention-based Streaming ASR with Triggered Chunkwise Attention and Dual Internal Language Model Integration Takafumi Moriya, Takanori Ashihara, Atsushi Ando, Hiroshi Sato, Tomohiro Tanaka, Kohei Matsuura, Ryo Masumura, Marc Delcroix (NTT), Takahiro Shinozaki (Tokyo Tech) EA2021-78 SIP2021-105 SP2021-63 |
In this paper we propose improvements to our recently proposed hybrid RNN-T/Attention architecture that includes a share... [more] |
EA2021-78 SIP2021-105 SP2021-63 pp.90-95 |
PRMU |
2021-12-16 14:55 |
Online |
Online |
Fully automatic scoring of handwritten descriptive answers in Japanese language tests Hung Tuan Nguyen, Cuong Tuan Nguyen (TUAT), Haruki Oka (UTokyo), Tsunenori Ishioka (The National Center for University Entrance Examinations), Masaki Nakagawa (TUAT) PRMU2021-32 |
This paper presents an experiment of automatically scoring handwritten descriptive answers in the trial tests for the ne... [more] |
PRMU2021-32 pp.45-50 |
NC, MBE (Joint) |
2021-11-26 16:15 |
Online |
Online |
Deep Learning Hybrid Models for Sentiment Analysis Yunpeng Rong, Jun Ohkubo (Saitama Univ.) NC2021-30 |
Sentiment analysis (SA), which can analyze the public attitudes towards various texts, has earned increasing attention f... [more] |
NC2021-30 pp.13-17 |
SC |
2021-05-28 16:25 |
Online |
Online |
[Poster Presentation]
Generation of New Question and Answer using Extracted Ontology and Neural Language Model from SQuAD Data Set Ayato Kuwana, Paik Incheon (UoA) |
[more] |
|
WBS, IT, ISEC |
2021-03-05 14:20 |
Online |
Online |
Learning Contract-Wide Code Representations for Vulnerability Detection on Ethereum Smart Contracts Nami Ashizawa, Naoto Yanai, Jason Paul Cruz (Osaka Univ.), Singo Okamura (NITNC) IT2020-156 ISEC2020-86 WBS2020-75 |
Ethereum smart contracts are programs that run on the Ethereum blockchain, and many smart contract vulnerabilities have ... [more] |
IT2020-156 ISEC2020-86 WBS2020-75 pp.273-280 |
KBSE, SC |
2020-11-13 15:22 |
Online |
Online + Kikai-Shinko-Kaikan Bldg. (Primary: Online, Secondary: On-site) |
[Poster Presentation]
Automation of Ontology Generation by Pre-trained Language Model Atusi Oba, Ayato Kuwana, Paik Incheon (UoA) KBSE2020-22 SC2020-26 |
As an initial attempt of ontology generation with neural network, Recurrent Neural Network (RNN) based method is propose... [more] |
KBSE2020-22 SC2020-26 p.40 |
SC |
2020-05-29 15:00 |
Online |
Online |
Service Discovery Using Invocation Sequence Learning in Composition with Neural Language Networks Zeng Kungan, Incheon Paik (UoA) |
Service composition can provide value-added services. Such a composition is a kind of abstract sequence, but it works wi... [more] |
|
IE, IMQ, MVE, CQ (Joint) [detail] |
2020-03-06 10:10 |
Fukuoka |
Kyushu Institute of Technology (Cancelled but technical report was issued) |
A Comparison Study of Neural Sign Language Translation Methods with Spatio-Temporal Features Kodai Watanabe, Wataru Kameyama (Waseda Univ.) IMQ2019-68 IE2019-150 MVE2019-89 |
In Neural Sign Language Translation, a model based on 2DCNN (2 Dimensional Convolutional Neural Network) called AlexNet ... [more] |
IMQ2019-68 IE2019-150 MVE2019-89 pp.273-278 |
SP, EA, SIP |
2020-03-02 13:00 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Japanese dialect speech classification using sequence-to-one neural networks Ryo Imaizumi (TMU), Ryo Masumura (NTT), Sayaka Shiota, Hitoshi Kiya (TMU) EA2019-108 SIP2019-110 SP2019-57 |
The language specific to a certain region is called a dialect, and the task of identifying which dialect the input speec... [more] |
EA2019-108 SIP2019-110 SP2019-57 pp.41-46 |
PRMU, IPSJ-CVIM |
2019-05-31 10:00 |
Tokyo |
|
Cross-modal Search using Visually Grounded Multilingual Speech Signal Yasunori Ohishi, Akisato Kimura, Takahito Kawanishi, Kashino Kunio (NTT), David Harwath, James Glass (MIT) PRMU2019-11 |
We evaluate a deep neural network model capable of learning to associate images and audio captions describing the conten... [more] |
PRMU2019-11 pp.283-288 |
NC, MBE (Joint) |
2018-12-15 15:15 |
Aichi |
Nagoya Institute of Technology |
Improved accuracy of sentence classification using recurrent neural networks Mitsuhiro Komuro, Yuji Sato (HU) NC2018-36 |
Recently various dialogue assistant products have appeared. On one hand, many of them cannot deal with flexible dialogue... [more] |
NC2018-36 pp.47-50 |
MBE, NC (Joint) |
2017-11-24 13:25 |
Miyagi |
Tohoku University |
Phased Learning for Distributed Word Representations Considering Synonym Chiaki Yonekura, Masafumi Hagiwara (Keio Univ.) NC2017-28 |
In natural language processing, distributed word representation is one of the representation methods for treating words ... [more] |
NC2017-28 pp.7-12 |
MBE, NC (Joint) |
2017-11-24 13:50 |
Miyagi |
Tohoku University |
Analyses of Neural Language Model and Its Application to Transformation of Individuality in Speech Tatsuya Takeuchi, Masafumi Hagiwara (Keio Univ.) NC2017-29 |
In this research, we aim to convert the output indirectly by changing the internal state of the neural language model us... [more] |
NC2017-29 pp.13-18 |
WIT, ASJ-H |
2017-05-28 10:45 |
Tokyo |
RION Co., LTD. |
A study on JSL Finger Spelling Recognition Using Convolutional Neural Networks Shinji Sako, Hana Hosoe (NIT), Bogdan Kwolek (AGH Univ. of Technology) WIT2017-10 |
Recently, a few methods for recognition of hand postures on depth maps using convolutional neural networks were proposed... [more] |
WIT2017-10 pp.45-49 |