Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
CCS, NLP |
2023-06-09 13:55 |
Tokyo |
Tokyo City Univ. |
Analysis of Vocal and Ventricular Folds Data Using Machine Learning Takumi Inoue, Kota Shiozawa, Isao Tokuda (Rits Univ) NLP2023-24 CCS2023-12 |
Vocal fold vibration is a nonlinear phenomenon in the real world. In humans, vocal folds can produce complex sounds by i... [more] |
NLP2023-24 CCS2023-12 pp.49-52 |
MBE, NC (Joint) |
2022-03-04 09:30 |
Online |
Online |
An estimation method of missing Information of compressed sound source using the Deep U-Net as an Auto-Encoder Kazuma Hirai, Susumu Kuroyanagi (NITech) NC2021-69 |
Some systems of speech-based information transmission, such as radio, telephone, and records, deal with sounds that lack... [more] |
NC2021-69 pp.121-126 |
PRMU |
2021-12-16 16:45 |
Online |
Online |
Verification of Cyclical Annealing for Object-Oriented Representation Learning Atsushi Kobayashi (Waseda Univ.), Hideki Tsunashima (Waseda Univ./AIST), Takehiko Ohkawa (The Univ. of Tokyo), Hiroaki Aizawa (Hiroshima Univ.), Qiu Yue, Hirokatsu Kataoka (AIST), Shigeo Morishima (Waseda Univ.) PRMU2021-39 |
Object-oriented Representation Learning is a method for obtaining images for each object and background part from an ima... [more] |
PRMU2021-39 pp.83-87 |
NC, NLP (Joint) |
2021-01-22 10:05 |
Online |
Online |
Verification of a Visuomotor Integration Model for Grasping the Cups of Different Sizes with a Multi-Fingered Robot Hand Motoi Matsuda, Naohiro Fukumura (Toyohashi Univ. of Tech) NC2020-36 |
Object recognition and object grasping using image recognition methods have been actively researched, but most of them c... [more] |
NC2020-36 pp.24-28 |
PRMU |
2020-12-17 16:30 |
Online |
Online |
Towards Discovery of Relevant Latent Factors with Limited Data Mohit Chhabra, Quan Kong, Tomoaki Yoshinaga (Hitachi) PRMU2020-49 |
The remarkable effectiveness of neural networks on vision tasks has led to an interest in adapting neural network models... [more] |
PRMU2020-49 pp.63-68 |
MI |
2020-09-03 13:10 |
Online |
Online |
[Invited Talk]
Manifold modeling in embedded space for image restoration Tatsuya Yokota (Nitech) MI2020-27 |
In this invited talk, I will discuss convolutional neural networks, which have achieved remarkable results in various im... [more] |
MI2020-27 pp.43-44 |
SP, EA, SIP |
2020-03-03 09:00 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Cross-Lingual Voice Conversion using Cyclic Variational Auto-encoder Hikaru Nakatani, Patrick Lumban Tobing, Kazuya Takeda, Tomoki Toda (Nagoya Univ.) EA2019-139 SIP2019-141 SP2019-88 |
In this report, we present a novel cross-lingual voice conversion (VC) method based on cyclic variational auto-encoder (... [more] |
EA2019-139 SIP2019-141 SP2019-88 pp.219-224 |
EMT, IEE-EMT |
2019-11-07 15:15 |
Saga |
Hotel Syunkeiya |
Land classification using unsupervised quaternion neural network with neighbor pixel information Jungmin Song, Ryo Natusaki, Akira Hirose (The Univ. of Tokyo) EMT2019-57 |
(To be available after the conference date) [more] |
EMT2019-57 pp.117-122 |
MIKA (2nd) |
2019-10-04 10:15 |
Hokkaido |
Hokkaido Univ. |
[Poster Presentation]
A study of similar network generative model using machine learning Shohei Nakazawa, Kohei Watabe, Kenji Nakagawa (Nagaoka Univ. of Tech.) |
A real topology data are required when we simulate assuming an environment close to a real situation. The real data of t... [more] |
|
MBE, NC (Joint) |
2018-03-14 10:00 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
Hierarchical quaternion neural networks with self-organizing codebook for unsupervised PolSAR land classification Hyunsoo Kim, Akira Hirose (Tokyo Univ.) NC2017-88 |
We propose a self-organizing codebook-based hierarchical polarization feature vector generation to realize an unsupervis... [more] |
NC2017-88 pp.121-126 |
EMT, IEE-EMT |
2017-11-09 10:50 |
Yamagata |
Tendo Hotel (Tendo, Yamagata) |
Flexible Unsupervised PolSAR Land Classification System Based on Quaternion Neural Networks Hyunsoo Kim, Akira Hirose (Tokyo Univ.) EMT2017-48 |
We propose a flexible unsupervised PolSAR land classification system based on quaternion neural networks. The existing ... [more] |
EMT2017-48 pp.37-42 |
SANE |
2017-10-05 14:20 |
Tokyo |
Maison franco - japonaise (Tokyo) |
Unsupervised Adaptive PolSAR Land Classification System Using Quaternion Neural Networks Hyunsoo Kim, Akira Hirose (Univ. of Tokyo) SANE2017-57 |
We propose an unsupervised adaptive PolSAR land classification system using quaternion neural networks. Most of the exis... [more] |
SANE2017-57 pp.73-78 |
MBE, NC (Joint) |
2017-05-26 13:50 |
Toyama |
Toyama Prefectural Univ. |
A Parallel Forward-Backward Propagation Learning Rule for Auto-Encoder Yoshihiro Ohama, Takayoshi Yoshimura (Toyota CRDL) NC2017-3 |
Auto-encoder is known as a hourglass neural network for acquiring essential representations from multi-dimensional data ... [more] |
NC2017-3 pp.13-18 |
MBE, NC (Joint) |
2017-03-13 13:10 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
Application of Forward-Propagation Learning Rule to Three-Layer Auto-Encoder Tadamasa Kurosawa, Naohiro Fukumura (Toyohashi Univ. of Tech) NC2016-82 |
By the development of Deep Learning, the concern over three-layer Auto-Encoder for Pre-training has risen.
On the othe... [more] |
NC2016-82 pp.109-114 |
SP, IPSJ-SLP, NLC, IPSJ-NL (Joint) [detail] |
2016-12-20 15:10 |
Tokyo |
NTT Musashino R&D |
[Poster Presentation]
Quantization Noise Reduction of Speech by Using Denoising Auto-encoder Shohei Oouchi, Kazunori Mano (SIT) SP2016-59 |
A quantization noise reduction technique based on Denoising Auto-encoder (DAE) was studied. DAE is a neural network to c... [more] |
SP2016-59 pp.57-58 |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2015-12-03 09:25 |
Aichi |
Nagoya Inst of Tech. |
Deep Auto-encoder based Low-dimensional Feature Extraction using FFT Spectral Envelopes in Statistical Parametric Speech Synthesis Shinji Takaki, Junichi Yamagishi (NII) SP2015-81 |
In the state-of-the-art statistical parametric speech synthesis system, a speech analysis module, e.g. STRAIGHT spectral... [more] |
SP2015-81 pp.99-104 |
HIP |
2014-03-18 11:35 |
Tokyo |
Tokyo Univ. |
An Extraction of Muscle Synergies in the Grasping Task by the Integration of Hand Shape Information and EMG Signal Katsunari Masuzaki, Naohiro Fukumura (Toyohashi Univ. of Tech.) HIP2013-82 |
Since a human has a large number of muscles, it is thought that controlling the enormous degrees of freedom is difficult... [more] |
HIP2013-82 pp.17-22 |