Music Research Symposium

Institute of High Performance Computing, A*STAR

Venue:  Infuse Theatrette, Level 14, Connexis South Tower, Fusionopolis 1
Date:  Friday, Feb 2nd, 2018
Time:  9:00am - 6:30pm (including a music performance from 5:15-6:30pm)

This symposium will be the first of its kind, providing an opportunity for researchers in Singapore who are interested in music cognition, music technology, music therapy, and related fields, to present their work and share ideas. The event will feature several keynotes and invited talks, a special session for undergraduate and graduate students to share their work*, a session on available grants and collaborative opportunities, and more. It will be a free and catered event at IHPC (A*STAR), and open to students, professors, scientists, industry researchers, and clinicians.

Topics will include: 
- music cognition
- neuroscience and BCI
- music information retrieval (MIR)
- music technology for healthcare/medicine
- music and AI
- machine learning and deep neural networks
- artistic research in music
- other related areas

*We also invite students to present posters during a dedicated 1-hr session during the afternoon. Students are very welcome to "recycle" their old posters from past conferences. Please indicate in the google sheet below if you would like to present a poster.

This is a FREE event, but please register by Jan 15th so that we may plan accordingly for the logistics and catering. You may register here:

Symposium schedule

9:00-9:30 Registration

Please aim to arrive at 9am, as you must exchange your ID for an A*STAR badge upon arrival at Fusionopolis One, and there will likely be a queue at the entrance. Registration for the symposium will take place just outside of the Infuse Theatrette on Level 14, Connexis South tower. (Please take the South Tower elevators up to level 14, not the North tower elevators.)

9.30-9.40 Symposium Opening by Dr. Kat Agres and Welcome Address by Dr. Alfred Huan, Executive Director of IHPC

9:40-10:10 Keynote: Dr. Feng Lei, NUS Yong Loo Lin School of Medicine

Title: Choral singing for the prevention of dementia: a randomized controlled trial

AbstractMusic is potentially a useful tool for the promotion of cognitive health in aging. Up to date, there is no firm evidence from interventional studies. In Singapore, we are currently working on a large randomized controlled trial that aims to assess the efficacy of choral singing in the prevention of cognitive decline among at-risk individuals living in the community. In this talk, I will elaborate on the scientific rationales, study designs and outcome measures of this clinical trial,  and also share some preliminary results. We believe this novel study will produce firm data on the effects of choral singing in delaying brain aging and cognitive decline, as well as biological mechanisms underlying the hypothesized efficacy.

Bio: Feng Lei is a currently a Research Assistant Professor at the Department of Psychological Medicine, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System. His primary research interest is the promotion of healthy, functional and active aging in the community and the epidemiology and primary prevention of cognitive decline and dementia through lifestyle and psychosocial interventions. He is currently leading several community-based research studies in Singapore: The Diet and Healthy Aging (DaHA) study, the Aging in a Community Environment Study (ACES), and the Choral Singing for Dementia Prevention Trial (in this trial, health education intervention is used as active control arm). Feng Lei is a core team member of the emerging SG90 and SG60 cohort studies under the NUHS-A*STAR-NUS Health Span-Biology of Aging research program. He has over 100 research publications and is a regular peer reviewer for top journals such as the British Medical Journal (BMJ). Feng Lei has successfully obtained competitive research grants amounting to over S$2 million as the Principal Investigator. He holds the Transition Award (TA) from the Ministry of Health, Singapore. 

10:10-10:30 Talk: Dr. Kat Agres, IHPC Music Cognition

Title:  From Neural Networks to Music Technology for Healthcare: An Overview of Recent Research from IHPC Music Cognition

Abstract: The musical mind is never stagnant. As with language, listening to music entails implicit prediction mechanisms based on previous experience and schematic knowledge. I will briefly explore how auditory statistical learning plays a crucial role in both computational simulation of music cognition as well as perceptual studies of learning and memory for music. After presenting a selection of recent research findings, I will discuss our group’s current focus on developing music technology for healthcare and well-being. Given the recent plethora of findings highlighting music’s ability to improve mental health, aid cognitive function, and support fine and gross motor control, we aim to leverage the therapeutic effects of music in a set of interactive games for e-health. One such game supports motor rehabilitation in stroke patients, and another serves as a preventive medicine tool for motor and cognitive function in the elderly.

BioDr. Kat Agres joined the Institute of High Performance Computing at A*STAR in early 2017 to help start a programme of research focused on Music Cognition. Kat received her PhD in Experimental Psychology (with a minor in Cognitive Science) from Cornell University, and completed her postdoctoral work at the University of London, where she was supported by a European Union Seventh Framework Programme grant to investigate music perception and computational creativity. She has also played cello professionally, and served as the senior research scientist for a London-based company at the intersection of music technology and health. Kat has presented her work at international workshops and conferences in more than fifteen countries, and has received numerous grants to support her research, including Fellowships from the National Institute of Health (NIH) and the National Institute of Mental Health (NIMH). Her current research explores an interdisciplinary range of topics focused on music cognition, computational simulation of music perception, statistical learning, and translational research on the clinical and therapeutic applications of music.

10:30-10:50 Talk: Jerry Chen, Express In Music

Title: Music Psychology Selling – a rare insight into B2B commercial music streaming

Abstract: Music is important but also not important. We will be sharing real-life case studies and tips on how we bring sound strategies to 3,000 over F&B, Retail and Hotels points in Asia Pacific. Do commercial parties really care about music? They know the influence of music is great but have often contradict by putting it as their lowest priority. We share with you the secrets of what REALLY matters and why people would be paying you $ for it. *P.S. it is not about your music… 

Bio: Jerry is highly passionate about audio branding through music psychology and the science behind it. How consumers are influenced by the sensory marketing around us - especially through the use of modern technology and AI. Together with his business partner Adriel, they founded Express In Music which is headquartered in Singapore and now grown to 7 other countries within Asia Pacific. Their subsidiaries, Express Melody, have reached out to more than 3,000 points and over hundreds of brands in the F&B, Retail and Hotel industry players internationally. From McDonald's, KFC, Crocs, IKEA, BMW, Mandarin Orchard Hotel, etc., the team have achieved to service the spectrum of clients they have.

Background Environmental Music isn't just playing any sort of music that is trending or simply popular. There must be a purpose, objective to curating a music playlist.

  1. Higher sales through a professionally curated ambient sound experience.
  2. Increased productivity and convenience with our automated music system.
  3. Costs savings and legal assurance through our international music licensing program.

The company he founded is backed by investors like TNF Ventures and USEN Corporation, and the vision is to be the Number 1 solution provider in Asia when it comes to BGM background music and audio branding expert. He has won the company numerous awards such as the prestigious SiTF and ASEAN ICT – being the only awardee that streams more than 200,000 original licensed content on this exclusive platform to thousands of physical outlets regionally.

10:50-11:20 Tea break

11:20-11:50 Keynote: Prof Wang Ye, NUS School of Computing

Title: Developing Music Technology for Health and Learning

AbstractThe use of music as an aid for improving body and mind has received enormous attention over the last 20 years from a wide range of disciplines, including neuroscience, cognitive science, physical therapy, exercise science, psychological medicine, and pedagogy. It is important to translate insights gained from the scientific study of music, learning, and medicine into real-life applications. Such applications should be delivered widely, effectively, and accurately, harnessing the synergy of sound and music computing (SMC), wearable computing, and cloud computing technologies to promote learning and to facilitate disease prevention, diagnosis, and treatment in both developed countries and resource-poor developing countries. In this talk, I will highlight our recent projects at NUS Sound and Music Computing Lab that are developed to facilitate joyful learning, and motivate physical Rehabilitation.

Bio: WANG Ye is an Associate Professor in the Computer Science Department at the National University of Singapore (NUS) and NUS Graduate School for Integrative Sciences and Engineering (NGS). He established and directed the sound and music computing (SMC) Lab ( Before joining NUS he was a member of the technical staff at Nokia Research Center in Tampere, Finland for 9 years. His research interests include sound analysis and music information retrieval (MIR), mobile computing, and cloud computing, and their applications in music edutainment, e-Learning, and e-Health, as well as determining their effectiveness via subjective and objective evaluations. He has served as the general chair of ISMIR2017 ( and TPC co-chair of ICOT2017 ( His most recent projects involve the design and evaluation of systems to support 1) therapeutic gait training using Rhythmic Auditory Stimulation (RAS), 2) auditory training and second language learning.

11:50-12:30 Panel discussion on the 'Future of Music Research in Singapore'

  • Prof Doug Turnbull (Associate Professor, Ithaca College, Visiting professor at NUS)
  • Prof Cuntai Guan (Professor, NTU)
  • Melanie Kwan (Senior Music Therapist, KK Women's & Children's Hospital)

12:30-1:30 Lunch

1:30-2:00 Keynote: Prof Bernard Lanskey, Dean of NUS Yong Siew Toh Conservatory of Music

Title: Fantasies Courting Realities: The Conservatory World and Recent Evolutions in the Field of Artistic Research in Music

Abstract: The 21st Century has seen a change in the attitudes of conservatories, particularly in Europe and Australasia, to the concept of an institutionally embedded research culture. Such research has involved multiple forms of which perhaps the most closely linked to the traditional conservatoire paradigm has been the comparatively new field of Artistic Research in Music, which itself has been undergoing significant evolution across the first two decades of the 21st century. Arguably, part of this transformation has been the consequence of different cultural approaches to the Research concept, involving at first an interesting range of insularities which has evolved outwards to even more curious mixture of cross-pollination and/or argument.

In offering first-hand experiences both of personal perceptions of best practice and of fundamental questions which continue to seek answers, the presentation will use the original discussions about Doctoral Studies and Artistic Research in Scandinavia in around 2003 as the prelude to an odyssey through mainland Europe (including evolutions led by the European Association of Conservatoires, the Orpheus Institute and the Norwegian Academy’s Arne Nordheim Centre for Artistic Research) and the UK (with the Music Performance Network and the Reflective Conservatoire), before returning back through Singapore (Performer’s Voice, Mathemusical Conversations and Performers(‘) Present) and Thailand (Princess Galyani Verdhana’s Institute of Music’s annual symposia, including the recently concluded 2017 event, Music, Myths & Realities) before touching finally on apparent tendencies and developments in Australia. Some cross-sector exploration as well as some examples of latest practice will also be offered to frame the challenges still facing the field.

In offering what is without apology a somewhat subjective account of the perceived journey, the presentation will use excerpts from Mozart’s Fantasy in C Minor K475 as a metaphor for forming and framing its argument.

Bio: Bernard Lanskey is Dean, since 2007, of the Yong Siew Toh Conservatory of Music, National University of Singapore. From 1994-2006, his senior management role at the Guildhall School of Music & Drama Drama London involved overseeing the ensemble and postgraduate programmes. Since 2005, he has been an Artist-in- Residence at La Loingtaine, near Fontainebleau, France. President of the South East Asia Directors of Music Association (SEADOM) and a co-opted Council member of the European Association of Conservatoires (AEC), he is active internationally as an administrator, collaborative pianist, scholar, recording producer and festival director. Research interests integrate his activity as a collaborative pianist and chamber music coach with a particular interest in the role of metaphor in shaping performance.

2:00-2:20 Talk: Prof Dorien Herremans, SUTD Information Systems Technology and Design

Title: Applications of Music and AI

Abstract: Recent advances in cloud computing have enabled large-scale complex computations such as deep models and optimization algorithms on personal devices. Intelligent music generation systems have begun to emerge, yet they still face important challenges such as the lack of long-term structures and themes, and the steered integration of emotion and tension in the resulting music. In this talk I will talk about some of my previous work that directly tackles these challenges, including the MorpheuS music generation system and a recent LSTM network that implements a novel tonnetz-based image representation. A second application that I will briefly discuss is an intelligent hit prediction model that uses SVM to predict top 10 dance hits based on both audio data and social network listening behaviour.

Bio: Dorien Herremans is an Assistant Professor at Singapore University of Technology and Design, and has a joint-appointment at the Institute of High Performance Computing, A*STAR. She also an instructor for the NVIDIA Deep Learning Institute and is the director of SUTD Game Lab. Before moving to SUTD, she was a Marie Sklodowska-Curie Postdoctoral Fellow at the Centre for Digital Music at Queen Mary University of London. She received her Ph.D. in Applied Economics on the topic of Computer Generation and Classification of Music through Operations Research Methods and graduated as a commercial engineer in management information systems at the University of Antwerp in 2005. After that, she worked as a Drupal consultant and was an IT lecturer at the Les Roches University in Bluche, Switzerland. Dr. Herremans' research interests include machine learning and music for automatic music generation, data mining for music classification and novel applications in the intersections of machine learning/optimization and music.

2:20-3:20 Breakout groups for discussion

Small groups will be formed to:
  • Quickly brainstorm main research themes
  • Discuss competitive advantages of SG for music research
  • Discuss grant opportunities!
  • Consider possible industry / academic collaboration and partnerships

3:20-4:20 Coffee break and poster session

  • ‘Projects in Deep Learning with Audio’ by Muhammad Huzaifah bin Md Shahrin (NUS) 
  • ‘Design of a Convolutional Neural Network for separating Singing Voice from Monaural Pop Music’ by Lin Kin Wah Edward (SUTD) 
  • ‘Music education game for ukulele using rudimentary polyphonic note detection’ by Tong Hui Kang, Zheng Xingjian, Foo Lin Geng (SUTD) 
  • ‘Using Music Technology for Language Learning’ by Dania Murad (NUS) 
  • ‘Culturally Relevant Music Therapy and Rehabilitation for Three Asian Teenagers at a Paediatric Hospital in Singapore’ by Melanie Kwan (KK Women's & Children's Hospital)   
  • ‘Perceptual Evaluation of Singing Quality’ by Chitralekha Gupta (NUS)
  • Intelligibility of Sung Lyrics’ by Karim M. Ibrahim (NUS)

4:20-4:40 Talk: Dr. Samuel Gan, A*STAR Bioinformatics Institute

Title:  The Psychological Effect of Music on Anxiety and Studying

Abstract: Music is often used as a soothing tool for animals (e.g. cobras) and humans. How real is that effect? There have been conflicting findings on the ability of music to reduce anxiety. To resolve the discrepancy, we propose a model of the role of music in anxiety, particularly, mathematical anxiety. While music may help reduce anxiety, what is the effect of listening to music while studying? Many older folks believe music to be a distraction when used while studying, but is this really a matter of concern for educators and parents? Our study seems to suggest that it really depends…

Bio: Dr Samuel Gan is the Principal Investigator of the Antibody and Product Development (APD) Lab (joint lab of the Bioinformatics Institute and the p53 Laboratory, A*STAR Singapore) and also the founding Chief Editor of the first specialized open access journal “Scientific Phone Apps and Mobile Devices” and a pioneer in the area. His other affiliations include associate lecturer at the School of Psychology of James Cook University, Singapore, and School of Science & Technology, Singapore Institute of Management University (UniSIM). His APD lab currently performs research in multiple areas from antibody engineering, allergy, product development, virology, mobile device development, smartphone apps, and psychology. Samuel is himself trained in a wide variety of disciplines across biomedical sciences (TP-SGP, UCL-UK, KCL-UK, BBK-UK), translation & interpretation (TP-SGP), psychology (OU-UK), higher education (KCL-UK), theology (KCL-UK, CLBS-SGP, GBI-SGP, FEBC-SGP), business admin (OU-UK), complexity science (SFI-USA), and commercial law & tech transfer (TP-SGP). He is an associate of King’s College, Psychological Society, Biochemical Society UK, and Allergy & Clinical Immunology Singapore, and was listed as one of fifty skilled talent alumni from technical tertiary the SG50 book “A Nation of Skilled Talents”.

4:40-5:00 Talk: Prof Lonce Wyse, NUS Communications and New Media Department

Title: Parameterized Sound Modeling with RNNs

Abstract: We would like to be able to construct models of sounds that expose parameters for real-time interactive control. Programming synthesizers is laborious and the sonic results rarely match the richness of natural sound. WaveNet and SampleRNN are fairly recent examples of neural networks that learn to synthesize sound by training on large audio data sets, and some research has been devoted to synthesis conditioned on input parameters such as phonemes. In this talk, I will present on-going work using RNNs for data-driven sound modeling with a focus on learning continuous real-time control for parameters such as musical pitch.

Bio: Lonce Wyse is an Associate Professor with the Department of Communications and New Media at the National University of Singapore, and directs the Arts and Creativity Lab of the Interactive and Digital Media Institute at NUS. He holds a PhD in Cognitive and Neural Systems (Boston University, 1994). He serves on the editorial boards of the Computer Music Journal (MIT Press), Organized Sound (Cambridge University Press), and the International Journal of Performance Arts and Digital Media. Lonce teaches courses on software studies, creative coding, media art, and interactive sound. His recent research endeavors include sound perception, real-time musical communication and notation, and networked music making. His current research focus is on neural networks for interactive sound synthesis.

5:15-6:30 Music performance

  • Prof Bernard Lanskey (NUS YST Conservatory of Music), Keyboard

Bernard Lanskey is Dean, since 2007, of the Yong Siew Toh Conservatory of Music, National University of Singapore. From 1994-2006, his senior management role at the Guildhall School of Music & Drama Drama London involved overseeing the ensemble and postgraduate programmes. Since 2005, he has been an Artist-in-Residence at La Loingtaine, near Fontainebleau, France. President of the South East Asia Directors of Music Association (SEADOM) and a co-opted Council member of the European Association of Conservatoires (AEC), he is active internationally as an administrator, collaborative pianist, scholar, recording producer and festival director. Research interests integrate his activity as a collaborative pianist and chamber music coach with a particular interest in the role of metaphor in shaping performance.

  • Prof Stephen Lim (NUS Psychology), Electone

Assoc. Prof. Dr. Stephen Lim (Dept. of Psychology, NUS) is currently Director of the NUS Cognition and Education Laboratory, and Associate Editor of Frontiers in Psychology: Educational Psychology. He won the Grand Prix Award (First Prize) at the 2017 Yamaha Electone Festival Singapore (Senior Section), and the Silver Prize at the 2017 Asia-Pacific Electone Festival (Senior Section). He will play a selection of short works on the Electone.