Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2019-12-06 13:55 |
Tokyo |
NHK Science & Technology Research Labs. |
[Poster Presentation]
Effectiveness of sequence-to-sequence acoustic modeling by using automatic generated labels Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano (NHK) SP2019-37 |
We have proposed a method that uses yomigana (Japanese character readings) and prosodic symbols as input for sequence-to... [more] |
SP2019-37 pp.49-54 |
MVE, ITE-HI, ITE-SIP [detail] |
2019-06-10 10:30 |
Tokyo |
|
Impression Prediction of Oral Presentation Using LSTM with Dot-product Attention Mechanism Shengzhou Yi, Xueting Wang, Toshihiko Yamasaki (UTokyo) MVE2019-1 |
For automatically evaluating oral presentation, we propose an end-to-end system to predict audience’s impression on spee... [more] |
MVE2019-1 pp.1-6 |
EA, SIP, SP |
2019-03-15 13:30 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
[Poster Presentation]
Data augmentation using multiple databases for end-to-end dysarthric speech recognition Yuki Takashima, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) EA2018-156 SIP2018-162 SP2018-118 |
We present in this paper an end-to-end speech recognition system for a Japanese person with an articulation disorder res... [more] |
EA2018-156 SIP2018-162 SP2018-118 pp.335-340 |
SP |
2019-01-27 09:00 |
Ishikawa |
Kanazawa-Harmonie |
[Tutorial Invited Lecture]
Software components towards end-to-end speech synthesis at NII
-- Tutorial for Tacotron and WaveNet -- Yusuke Yasuda, Xin Wang (NII) SP2018-56 |
This presentation describes recent advances of end-to-end speech synthesis. We introduce major approaches and our method... [more] |
SP2018-56 p.21 |
SP |
2019-01-27 10:40 |
Ishikawa |
Kanazawa-Harmonie |
Evaluation of end-to-end speech synthesis method using speaking styles Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Atsushi Imai (NHK) SP2018-58 |
The purpose of this study was to conduct end-to-end text-to-speech synthesis in Japanese; we developed a system that use... [more] |
SP2018-58 pp.29-34 |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2018-12-10 13:15 |
Tokyo |
Waseda Univ. Nishiwaseda Campus |
[Invited Talk]
Review of Automatic Speech Recognition Methodology
-- Outlook of Acoustic-to-Word Model -- Tatsuya Kawahara (Kyoto Univ.) SP2018-48 |
The methodology of speech recognition has been changing due to the introduction of deep learning, in particular end-to-e... [more] |
SP2018-48 pp.25-30 |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2018-12-10 16:30 |
Tokyo |
Waseda Univ. Nishiwaseda Campus |
Evaluation of Japanese end-to-end speech synthesis method inputting kana and prosodic symbols Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Atsushi Imai (NHK) SP2018-49 |
The purpose of this study was to conduct end-to-end text-to-speech synthesis in Japanese; we developed a system that use... [more] |
SP2018-49 pp.89-94 |
SP |
2018-08-27 11:35 |
Kyoto |
Kyoto Univ. |
SP2018-23 |
(To be available after the conference date) [more] |
SP2018-23 pp.7-8 |
IBISML |
2017-03-07 14:00 |
Tokyo |
Tokyo Institute of Technology |
CTC network with explicit representation vector of Markov property Yuta Kawachi, Taichi Asami, Yoshikazu Yamaguchi, Yushi Aono (NTT) IBISML2016-111 |
Current neural acoustic models are incapable of utilizing language resources except speech transcriptions. So toward the... [more] |
IBISML2016-111 pp.83-88 |
SP |
2016-10-27 16:00 |
Shizuoka |
Shizuoka University. |
Word modeling for end-to-end Japanese speech recognition Hitoshi Ito, Aiko Hagiwara, Manon Ichiki, Takeshi Mishima, Shoei Sato (NHK), Akio Kobayashi (NES) SP2016-47 |
In this paper, we propose a novel modeling for end-to-end Japanese speech recognition using Deep Neural Networks(DNN). W... [more] |
SP2016-47 pp.31-36 |
ICM |
2011-03-11 16:30 |
Okinawa |
Miyakojima Marine Terminal |
Practical Models for Multi-Hop End-to-End Network Paths Marat Zhanikeev, Yoshiaki Tanaka (Waseda Univ.) ICM2010-72 |
Leaky and Token Bucket models are traditionally used to model end-to-end communication paths. However, recent research... [more] |
ICM2010-72 pp.105-108 |
NS, ICM, CQ (Joint) |
2010-11-18 15:45 |
Kyoto |
Katsura Campus, Kyoto Univ. |
[Special Talk]
Squeezing Out the Best of End-to-End Performance Marat Zhanikeev, Yoshiaki Tanaka (Waseda Univ.) CQ2010-53 |
Although end-to-end performance has long been recognized as an important topic in QoS research, little is currently sol... [more] |
CQ2010-53 pp.29-34 |
IN |
2010-07-09 11:15 |
Hokkaido |
Hokkaido Univ. |
Fluid-based Analysis of TCP Flows in a Scale-Free Network Yusuke Sakumoto, Hiroyuki Ohsaki, Makoto Imase (Osaka Univ.) IN2010-36 |
In this paper, we derive distributions of throughput, round-trip time,
and packet loss probability of TCP flows in a sc... [more] |
IN2010-36 pp.79-84 |
ICM |
2009-03-13 16:25 |
Kagoshima |
|
Directional Active Probing in Real Network Services Marat Zhanikeev, Yoshiaki Tanaka (Waseda Univ.) ICM2008-87 |
Connectivity in global network today is the cause and primary component of all traditional communication patterns where ... [more] |
ICM2008-87 pp.167-172 |
IN, NS (Joint) |
2006-03-03 12:30 |
Okinawa |
Rizzan Sea-Park Hotel Tancha-Bay (Okinawa) |
Impact of Logical and Physical Network Topologies on the Delay Performance of Overlay Routing Yasuo Tamura, Shoji Kasahara, Yutaka Takahashi (Kyoto Univ.) |
In overlay networks such as P2P network and contents delivery network (CDN),
data is transmitted by overlay routing. Th... [more] |
NS2005-186 pp.113-116 |
IN |
2006-02-16 13:50 |
Kochi |
Kochi Univ. of Technology |
On the Scale-Free Structure of Netowork Topology on End-to-End Performance Koutaro Yagi, Hiroyuki Ohsaki, Makoto Imase (Osaka Univ.) |
In recent years, it has been reported that several existing networks represented by the Internet have a scale free struc... [more] |
IN2005-145 pp.13-18 |
RCS, SIP (Joint) |
2006-01-26 09:40 |
Fukuoka |
Kyusyu Univ. |
A Feasibility Study on Realizing Ultra Low-Latency Mobile Networks Satoshi Konishi, Takeshi Kitahara, Xiaoqiu Wang, Hajime Nakamura (KDDI R&D Labs.), Masataka Ohta (TIT), Fumiaki Maehara (Waseda Univ.) |
Traffic demand for real-time services have recently been increasing as well as non real-time services because of the rap... [more] |
RCS2005-144 pp.119-124 |