Details of a Researcher - Saito, Hiroaki

Saito, Hiroaki

写真a

Affiliation: Faculty of Science and Technology, Department of Information and Computer Science (Yagami)

Position: Professor

External Links

Page Top ▲

Career 【 Display / hide 】

1991.04

-

1997.03

慶應義塾大学（理工学部） ,助手
1997.04

-

Present

慶應義塾大学（理工学部） ,専任講師

Page Top ▲

Academic Background 【 Display / hide 】

1983.03

Keio University, Faculty of Engineering, 数理工学科

University, Graduated
1985.03

Keio University, Graduate School, Division of Engineering, 数理工学専攻

Graduate School, Completed, Master's course
1991.03

Keio University, Graduate School, Division of Science and Engineeri, 数理科学専攻

Graduate School, Completed, Doctoral course

Page Top ▲

Academic Degrees 【 Display / hide 】

工学　, Keio University, 1991.03

Page Top ▲

Papers 【 Display / hide 】

ボーカルメロディに応じた歌詞生成

宮野友弥，斎藤博昭

芸術科学会論文誌 20 ( 2 ) 129 - 138 2021

Research paper (scientific journal), Last author, Accepted
Anna: A Dapper Open-Domain Dialogue Agent Based on a Joint Attention Network

Itsugun Cho and Hiroaki Saito

自然言語処理 28 ( 4 ) 1184 - 1209 2021

Research paper (scientific journal), Joint Work, Last author, Accepted
Rap Lyrics Generation Using Vowel GAN

Miyano T., Saito H.

Communications in Computer and Information Science (Communications in Computer and Information Science) 1215 CCIS 307 - 318 2020

ISSN 18650929

　View Summary

Despite the success of recent rap and poetry generations using neural models, many of them do not consider vowels of the entire lyrics. Also, in many cases it is virtually impossible to generate completely new lyrics, because only existing rap lyrics are used as data sets. This paper proposes a new method of rap lyrics generation using a large amount of text such as novels in addition to rap lyrics. We divided the generation of rap lyrics into two steps; first, Generative Adversalial Net (GAN) generates rhymes and flows. Second, sequence-to-sequence converts them into rap lyrics. In addition, this method refers to the generation style of rap songs. In other words, they determine the music and rhythm first and apply the words second. We evaluated our method based on BLEU that can be measured mechanically.
- Access to Document (DOI)
A Tool for Creating Glossed Japanese Reading Materials

Gregory Hazelbeck, SAITO HIROAKI

Journal of Information Processing (情報処理学会) 20 ( 1 ) 10 pages 2012.01

Research paper (conference, symposium, etc.), Joint Work, Accepted
擬音語と書体表現を用いた環境音の可視化

YAMAMOTO TAKASHI, MATSUBARA MASAKI, SAITO HIROAKI

芸術科学会論文誌 (芸術科学会) 11 ( 1 ) 1-11 2012.01

Research paper (conference, symposium, etc.), Joint Work, Accepted

display all >>

Page Top ▲

Papers, etc., Registered in KOARA 【 Display / hide 】

Deep learning with less data

Saito, Hiroaki

学事振興資金研究成果実績報告書 (慶應義塾大学) 2022
A method of textual entailment from big data

Saito, Hiroaki

学事振興資金研究成果実績報告書 (慶應義塾大学) 2018
Language processing of big data in versatile formats

Saito, Hiroaki

学事振興資金研究成果実績報告書 (慶應義塾大学) 2017

Page Top ▲

Presentations 【 Display / hide 】

Patent search based on automatic investigation of topic-related documents

Hiroaki Kikuchi, Masaki Matsubara, Hiroyuki Okamoto, Tomohisa Sano, Shiho Nobesawa, Hiroaki Saito

12th Pacific Association for Computational Linguistics (PACLING 2011) (Kuala Lumpur) ,

2011.07
,
Poster presentation
Prioritized Contig Combining to Segregate Voices in Polyphonic Music

Asako Ishigaki, Masaki Matsubara, Hiroaki Saito

8th Sound and Music Computing Conference (SMC2011) (Padova, Italy) ,

2011.07
,
Poster presentation
言語処理を取り入れた英語学習者向けディベート支援環境の構築

SAITOU HIROAKI

言語処理学会第11回年次大会 (高松　（香川大学工学部）) ,

2005.03
,
Oral presentation (general)
日本語フレームネット：意味タグ付きコーパスの試み

SAITOU HIROAKI

言語処理学会第11回年次大会 (高松　（香川大学工学部）) ,

2005.03
,
Oral presentation (general)
日本語話し言葉における自己修復の統計モデル

SAITOU HIROAKI

言語処理学会第10回年次大会 (東京　（東京工業大学大岡山キャンパス）) ,

2004.03
,
Oral presentation (general)