SHENG LI (李 勝) Japanese version

Ph.D.
Tenure-track Researcher
National Institute of Information and Communications Technology (NICT)
Advanced Speech Technology Laboratory (ASTL)
Researchmap

E-mail: sheng.li [at] nict.go.jp / lisheng.cs [at] gmail.com / sheng.li [at] ieee.org
Address: Seika-cho, Souraku-gun, Kyoto 619-0289, JAPAN

CURRENT RESEARCH:


EDUCATION:


PUBLICATIONS:

GoogleScholar | ResearchGate | DBLP | Researchmap | SemanticScholar | ORCID | Scopus

Ph.D Thesis:

Book Chapter:

Journals (Peer reviewed):

International Conferences (Peer reviewed):

Technical Reports:

Other Talks:


RESEARCH EXPERIENCES:

1.Mis-pronunciation detection for second language learners (NSFC60772165)(2009-2012)
2.Phone-level articulatory 3D animation in pronunciation training (NSFC61135003)(2009-2012)
3.Discriminative training of acoustic models for Sohu IME (2012.4-2012.9)
4.Spoken lecture transcription enhanced by lightly-supervised and semi-supervised training(2012-2016)
5.Research about speaker adaptive training of DNN acoustic model (cooperation with NICT)(2012-2016)
6.ERATO project (2015-2016) English acoustic modeling and online decoding for Erica (the humanoid robot)
(picture cited from http://dl.acm.org/citation.cfm?id=3005472)
7. Focusing on leveraging the performance of ASR systems for Tokyo Olymic 2020 (NICT, 2017-2019)
(see http://voicetra.nict.go.jp/en/)

Fundings


[1] 2019-2020: JSPS startup fund

AWARDS:

[1] 2002 Award of chemistry and biology Olympic for high school students (Jiangsu Province)
[2] 2002 Chen Yinchuan Scholarship for Excellent University New Students
[3] 2004 People's Scholarship of Nanjing University
[4] 2011 Excellent Staff Award of Chinese Academy of Sciences
[5] 2011 Best Creative Project Award in Young Entrepreneur Program 2011, HK
[6] 2012 MEXT scholarship by Japanese Government
[7] 2012 Travel grant by IBM research for INTERSPEECH2012 at Portland
[8] 2016 Paper nominated as ACM/IEEE Trans. Audio, Speech \& Language Process. cover
[9] 2018 IEEE Signal Processing Society Japan Student Journal Paper Award

ACADEMIC SERVICES:

Reviewer/Program committee:
[1] IEICE transactions, letters
[2] APSIPA transactions
[3] ACL-2017/2018/2020,
[4] COLING-2018,
[5] NAACL-HLT-2016/2018/2019,
[6] IJCNLP-2017, EMNLP-IJCNLP2019, EMNLP2020, AACL-IJCNLP2020
[7] INTERSPEECH-2020/2019/2018/2015
[8] IROS-2019
[9] APSIPA-2019
[10] AAAI-2019
[11] ICME-2020
[12] Ubiquitous Robots (UR)-2020

(I will be happy to review for Open Access publications).
ISCA Student Volunteer2015-2016
TA ALAGIN 2015 Acoustic Modeling @Kyoto University

MEMBERSHIP:

IEEE/IEEE-SPS (Signal Processing Society),
ISCA (International Speech Communication Association),
ASJ (Acoustical Society of Japan),
SIG-CSLP (Chinese Spoken Language Processing),
APSIPA (Asia Pacific Signal and Information Processing Association)

SOFTWARE & RECIPES (our teamwork, strongly suggest trying):

VoiceTra: Multilingual Speech Translation Application

DATA RELEASES:

  • S.Li, Y.Akita, and T.Kawahara.(Copy-right belongs to Kawahara Lab. Kyoto Univ.)
    Corpus and transcription system of Chinese Lecture Room.
    In Proc. Int'l Sympo. Chinese Spoken Language Processing (ISCSLP), pp.442--445, 2014. (link)

    ALUMNI:

    Nanjing University
    NJUer at Kansai
    Info. OB of Kyoto University
    Lilybbs

    Last update: 2020-3-21