LINKS:
Speech & Language Grp
Teaching
Pictures of Past Gatherings
and Interests
Address:
Blk N4, 02c-96, Nanyang Avenue.
School of Computer Science and
Engineering. Nanyang Technolog-
ical University, Singapore 639798
MapLink
Q: how to get to NTU?
Q: Nearest carpark to N4?
Contact:
Email: aseschng at ntu dot edu
dot sg
Tel : +65-6790-6200
Fax: +65-6792-6559
CHNG Eng Siong
I am currently an Associate Professor in the School of
Computer Science and Engineering SCSE, Nanyang
Technological University (NTU), Singapore.
Prior to joining NTU in 2003, I worked in: Knowles
Electronics (2001-2002), Lernout and Hauspie
(1999-2000,Belgium), Institute of Infocomm Re-
search (1996-1999,I2R, Singapore), and RIKEN
(1996,Japan).
I received both BEng (Hons) and PhD from Edin-
burgh University, U.K. in 1991 and 1996 respectively.
My PhD was supervised by Bernard Mulgrew, Peter
Grant and Chen Sheng.
My area of focus is in speech research and signal
processing. To date, I have been Principal Investiga-
tor of several research grants awarded by NTU-Rolls Royce, Mindef, MOE and
AStar with a total funding amount of over
S$9
million under the Speech and
Language Research Group at SCSE. I have supervised 11 PhD students and 6
Masters Engineering students. My publications include 2 edited books and
over 100 journal/conference papers. What Google and Microsoft say about
me.
I have served as the publication chair for 5 international conferences (Human
Agent Interaction 2016, INTERSPEECH 2014, APSIPA-2010, APSIPA-2011,
ISCSLP-2006), and have been an associate editor for IEICE (special issue 2012),
a reviewer for Speech Communications, Eupsico, IEEE Trans Man,System and
Cybernectics Part B, Journal of Signal Processing System, ACM Multimedia
Systems, IEEE Trans Neural Network, IEEE Trans CAS-II, and Signal Process-
ing.
I was the recipient of the Tan Chin Tuan fellowship (2007) to visit Tsinghua
University, the JSPS travel grant award (2008) to visit Tokyo Institute of
Technology, and the Merlion Singapore-France research collaboration award
in 2009.
Publications
1. Google scholar
2. Researcherid
3. Microsoft Academic
Visited by: ClustrMap details
last updated: Oct 2018
Speech & Language
Research Group
LINKS:
Main Page
Speech & Language Grp
Collaborators
Current
Staff/Students
Past Graduate Stu-
dents/Staff
Fundings
Teaching
Speech & Language Research Group
The speech and language research group in SCSE was founded in 2007 by
Chng Eng Siong and Prof Li Haizhou (now in NUS, Singapore). Our group is
now situated within Media & Interactive Computing Lab (formely MML) in
SCSE.
The focus of our research group is in the area of speech and language research.
We are currently working in the following areas:
1. Code-switch speech recognition
2.
Robust Large vocabulary continuous speech recognition and Keyword
spotting
3. Speech and feature enhancement
4. Speaker identification
5. Voice conversion (morphing)
6.
Towards Speech Understanding (ChatBot) - some aspects of NLP such
as topic detection, name entity recognition
Demos
1.
Our code-switch demos in Youtube: CES speaking English/Mandarin to
our code-switch LVCSR system (2018 June) and Comparing our system
against Google, Siri (2018 Sep)
Collaborators
1. Prof Xie Lei, Northwestern Polytechnic, Xian, China
2. Dr Ma Bin, Alibaba - robust ASR
3. Dr Raphael Banchs, AStar, I2R - dialogue ChatBot
Current Staff/Students
Current staff member:
1. Dr Xu Hauhua: robust LVCSR, keyword spotting
2. Dr Rao Wei: speaker verification
3. Ho Thi Nga: speech indexing and SUD, , part-time MEng.
4.
Xu Chenglin: part-time PhD, Qualifying Exam (Oct2018) Single Channel
Multi-talker Speech Separation with Deep Learning and Slides
5. Lim Zhi Hao: speaker verification, part-time PhD.
6. Tian XiaoHai: TTS and voice morphing, part-time PhD.
7. Kyaw Zin Tun: speech indexing and chatBot
8. Ly Vu Thi: speech indexing and chatBot
9. Ho Danyuan: corpus development and linguistic.
10. Zeng Zhiping: LVCSR
The current full time PhD students of our team are:
1. Phan Van Tung: keyword spotting
2. Khassan Yerbolat: language model adaptation
3. Hou Nana: robust LVCSR for air traffic control speech
The current part time graduate students of our team are:
1.
Paul Chan Yaozhu: Synthesis of the human singing voice (partTime PhD)
2.
Li ZhongWei: Name and Digit Entity Recognition for simultaneous
translation (partTime PhD)
Speech & Language
Research Group
LINKS:
Main Page
Speech & Language Grp
Collaborators
Current
Staff/Students
Past PhD Students
Past MEng Students
Past Staff
Past Interns
Fundings
Teaching
Past PhD Students
1.
Chong Tze Yuang: PhD thesis (2018), Slides Exploiting Long Context Us-
ing Joint Distance and Occurrence Information for Language Modeling.
now at AStar
2.
Nguyen Duc Hoang Ha, PhD (2017), PhD-Slides, Feature based robust
techniques for speech recognition. now in Vietnam.
3.
Nguyen Trung Hieu, PhD (2015), Speaker Diarization in Meeting room
domain. Now at Alibaba
4.
Do Van Hai PhD (2015), Acoustic modelling of speech under limited
training data condition. Now in Vietnam Telecoms.
5.
Wu Zhizheng PhD (2015), Spectral Mapping for Voice Conversion. Now
in Apple.
6.
Jonathan Dennis PhD (2014) PhD Slides, now in Green Runnning-Data
Scientist
7.
Wang Lei, PhD (2013), Audio Pattern Discovery and retrieval. Now at
AStar.
8.
Tong Rong, PhD (2012), Towards a high performance phonotactic fea-
tures for spoken language recognition. Now at Alibaba.
9.
Omid Dehzanghi, PhD (2012), Discriminative Learning for speech recog-
nition. Now in U Michigan.
10.
Xiao Xiong, PhD (2010), Robust speech features and acoustic models
for speech recognition. PhD QE (2006). Now in Microsoft, Redmond -
since Apr 2017
11.
Wang Jinjun, PhD (2008), Content based sports video analysis and
composition. Now in Xian Jiaotong
Past MEng Student
1.
Leow Sujun: (MEng 2018), Image Processing Technique for Speech
Signal Processing
2. Nguyen Quy Hy, (MEng 2017), Voice conversion using DNN
3. Steven Du, (MEng 2015), Robust Front End for Speaker Verification
4.
Terrence Ng Wen Zheng, MEng (2014), Sound Event recognition in
home environment, now in AStar.
5.
Chen Wenda (MEng 2014), Computer Assisted Language Learning, now
PhD student in UIUC.
6. Ben Pham Chau Khoa, MEng (2012), now in Microsoft
7.
Eugene Koh, (MEng 2009), Speaker Diarization of News Broadcasts and
Meeting Recordings.
Speech & Language
Research Group
LINKS:
Main Page
Speech & Language Grp
Collaborators
Current
Staff/Students
Past PhD Students
Past MEng Students
Past Staff
Past Interns
Fundings
Teaching
Past Staff
1.
XiaoXiong, PhD Student 2004-2008, Staff 2008-2017, Now in Microsoft,
Redmond - since Apr 2017
2. Benjamin Bigot,2014-2016 - LVCSR for RR
3. Huang Guangpu, Staff 2012-2015 - Articulatory Phonetics Features
4. Lyu Daucheng, 2009-2013 - Code switch LVCSR
5. Zhao Shengkui, 2009-2010 - Microphone array and beamforming.
Past Interns (incomplete)
1.
Interns from 2018: Picture of the student group taken Jan 2018 and
second group picture with more students - taken May 2018 and third
group picture with more students - taken July 2018
2.
Interns from 2017: India and SPMS (2017 May-July) : Picture of the
student group and Gangeshwar Krishnamurthy, Undergraduate from
Bangalore Institute of Technology, Bengaluru, India,Jan - April 2017,
sentence unit detection and Gao Shengheng, Undergraduate from Uni-
versity Paul Sabatier (Toulouse III), Mar-Jun 2016, NLP-topic detection.
Note: if you have been a past intern and wish to be included in above list, do
send me a linkedin acccount id, when you were here, and from which college
were you at when you were here. Will be great to have you in the list.
Fundings
Total Funding: > S$8.5 million
1.
July 2018- July 2021, Alibab-NTU Singapore joint lab - Code-switch speeech recognition (Amount S$272K + 2
PhD students (approx S$450K)) , PI
2. Jan 2018 - Dec 2020, Project Malvin, Mindef, Amount: S$600K, PI
3. Jul 2017 - Jul 2021, Project Creton, Mindef, Amount: S$780K, PI-Track2
4. Nov 2016 - Nov 2018, Project Acumon, Mindef, Amount: S$560K, PI
5.
Jan 2016 1 RSS from ATMRI-NTU for PhD student Hou Nana, Robust ASR for very noisy speech in air-traffic
control domain, (Amount:S$200K) ATMRI-NTU, PI
6.
Jun 2014 - Jun 2017, Project Maison: Robust Speaker Verification And Keyword Spotting, DSO M4061477,
Amount: S$2.2 million, PI.
7.
Mar 2014 - Jul 2018, RT1.2: Smart Visual Analytics of unconventional data NRF & Rolls Royce Project, Amount:
S$777K, PI
8.
Mar 2014 - Jul 2018, RT1.1: Smart Knowledge Discovery from unconventional data, NRF & Rolls Royce, Amount:
S$872K (75%-PI), PI
9.
Apr 2013 - Apr 2015, Development of Linguistic Resources and LVCSR for Southeast Asia Languages on KALDI
platform (DeKALDI) AStar, S$124,800, PI
10. Sep 2011 - Aug 2014, Audio Mining Broadcast News, DSTA: M4060890.683, S$500K, PI
11. Jan 2010 - Dec 2011, Merlion 2009, MultiLing, French Embassy (Singapore), S$30K, PI
12.
July 2010 - Jun 2012, Speech Recognition for Code-switch Conversational Speech, Temasek Lab@NTU, ProjectID:
M48680100, Amount: S$200K, PI
13.
Mar 2010 - Feb 2012, A pilot study of a Computer Assisted Pronunciation Evaluation (CAPE) system for English
learners in Singapore, MOE Tier 1 ProjectID: M52020089, Amount: S$190K, PI-Chng Eng Siong, Co-PI: Tan
Ying Ying
14. Nov 2009-Oct 2010, Malay Text-to-Speech Synthesis Astar ProjectID: M48020073, Amount: S$90K
15.
Nov 2009 - Oct 2011, A Microphone Array with a 3-dimensional configuration for the I2R social robot, AStar
ProjectID: M48020074, Amount: S$200,400
16.
Dec 2008, Attachment to Tokyo Institute of Technology, Japan to visit Prof S. Furui Lab for exchange in speech
research, NTU/NUS-JSPS New Scientific Exchange Programme (NSEP). Amount: S$3K, PI
17.
Sep 2008 - Mar 2010, Statistical Language Modeling for spoken document retrieval Astar ProjectID: M48020061,
Amount: S$240K, PI
18.
Apr 2008 - Oct 2008, Speech Channel Modelling & Classification, Astar ProjectID: M48020050, Amount: S$108K,
PI
19.
Mar 2008 - Feb 2013 Advanced Research in Automatic Speech Recognition, Temasek Lab@NTU, ProjectID:
M48680101, Amount: S$1 million, PI: Li Haizhou, Co-PI: Chng Eng Siong
20.
Jan 2008 - Jun 2008 Robust Speech Signal Acquisition and Enhancement, AStar ProjectID: M48020049, Amount:
S$72,000, PI.
21.
Dec 2007 - Dec 2009 Micro-eBlock: A scalable microcomputer peripheral system for tertiary level micro-controller
education, MOE & NTU & Renesas, Amount: S$313,572, ProjectID: M20440011, Co-Principal Investigators:
Chng Eng Siong & Tan Su Lim
22.
Jun - July 2007, Tan Chin Tuan Fellowship. Attachment to Tsinghua University, Beijing, China, Amount: S$6000
PI.
23.
Jun 2007 - Jun 2008, Speech Data Collection Technology for Robotic Dialog Application Astar ProjectID,
M48020040, Amount: S$69,920, PI.
24. July 2006, ROAR 2006 Award, 1 PhD studentship, NTU Award: Approx S$100K, PI.
25.
Feb 2007 - Feb 2008, Supplementary Equipment Purchase, Digital Signal Processing for Voice Enhancement
Recognition and Search, NTU Award: ProjectID:: M52020057, Project Ref number: RG129/06, Amount:
S$39,440, PI.
26.
Mar 2006-Mar 2007, Development of Speaker turn library for I2R AStar, Project ID: M48020025, Amount:
S$70,000, PI.
27.
Sep 2004- July 2010, Digital Signal Processing for Voice Enhancement, Recognition & Search: AStar G/L Acct:
500360, Amount: S$138,000, PI.
28.
Oct 2004 - Mar 2005, Summarization of proceedings in a Smart Meeting Rooms for AStar Thematic Pilot project,
AStar M47020015, SERC grant number: 0421110063, Amount: S$21,000 Chng Eng Siong & Deepu Rajan
29.
Jun 2003 - Jun 2004, Collaborative acoustic sensor for a smart meeting room application. NTU, SCE CE-SUG-
01/03 Amount: S$14,600, PI
30.
Dec 2003 - Jan 2004, 2 months, Overseas Attachment programme to University of Southampton, Dept of ECE.
Attachment to Prof Sheng Chen AStar Award, Amount: S$3600, PI
——————————
Teaching
Some interesting read
1. Karpathy’s writing on "A survival guide to a PhD" - link
2. Karpathy’s "Doing well in a course" - link
Advice To Writing
This section describes my take in how you can organize your thesis, final year report, etc.
For PhD Students, my suggestion is that the structure is the most important aspect, and you should aim to get that
right first. E.g, you can write a series of questions to drive the report, and with the questions, write a power point
(which provide more contents) towards answering the questions, and then finally the report. You can have a look at
1. Chong’s question and power point slide as an example.
2. Khassan’s writing and his question.
I have other tips about writing thesis: word document (last updated: March 2016) and the mindmap
Undergraduate FYP Writing Advice/Example: An example here
Tools for Writing
Please use latex for your writing - it will help a lot! In windows you have miktex. You can get a host of templates here.
My editor of choice is TexStudio - but ask Quora for the latest answer.
Please see what Jonh Dennis had used to write his thesis. tip on tools he used for writing thesis.
You can start with using Xiao Xiong’s latex PhD thesis template.
Writing Advice from Others
1. Professor Simon Peyton Jones (Cambridge) - How to write a Great Research Paper Youtube
2. Judy Swan (Princeton) - Scientific Writing youtube
3. Kristin Sainani - writing for the sciences youtube
4. Steve Easterbrook - how thesis get written.
Final Year Project Advise
1. See FYP Presentation (2017-Dec) by Ronald - From an Image to a Close Caption Youtube
Taught Courses
1. CPE3007 - Digital Signal Processing (Since 2013), CPE414/ES6105 DSP (2005-9?)
2. CPE3006 - Digital Communications (since Jan 2016 - 2017)
3. CPE206 - Micro-controller Systems Design (2004-2009)
4. Maths1 - (tut-2018 Jan)
Some relevant E-Learning Videos
1. Speech Recognition - WFST
(a)
Weighted Finite State Transducer - YouTube - link produced by Lim Zhi Hao (PhD Student of our lab) in
2015
2. Undergraduate Algebra and Analysis
(a)
Essence of Linear Algebra by 3Blue1Brown - for undergraduate, an intutive understanding, Youtube - link
(b) Essence of Calculus by 3Blue1Brown - for undergraduate, an intutive understanding, Youtube - link
(c) Petra Bonfert-Taylor’s lectures - Analysis of a Complex Kind Youtube - link
3. Graduate classes:
(a) Ole Chirstensen lectures - Hilbert Space link
(b) Fredric Schuller’s lectures - Hilbert Space and such Youtube - link