Publications
] .
2026. Aligning Generative Music AI with Human Preferences: Methods and Challenges. Proceedings of AAAI, senior member track. 
2511.15038v1.pdf (417.24 KB)
2511.15038v1.pdf (417.24 KB).
2026. APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music. arXiv:2605.03395. 2605.03395v1 (1).pdf (292.45 KB)
2605.03395v1 (1).pdf (292.45 KB).
2026. Development of Interpretable Deep Learning-based Segmentation Algorithm for Automated Assessment of Oral Diadochokinesis in Progressive Neurological Diseases. Journal of Speech, Language, and Hearing Research.
.
2026. Emerging AI Technologies for Music: Towards Controllable, Collaborative, and Creative Systems. Proceedings of Machine Learning Research, PMLR 303:1-5, 2026. bhandari26a.pdf (161.47 KB)
bhandari26a.pdf (161.47 KB).
2026. Generative AI in Education for SDG 4: Insights from Indonesia and Kazakhstan. Proceedings of the Pacific Asia Conference on Information Systems (PACIS)..
.
2026. KARMA-MV: A Benchmark for Causal Question Answering on Music Videos. arXiv:2605.08175. 2605.08175v1.pdf (3.32 MB)
2605.08175v1.pdf (3.32 MB).
2026. Measuring and Mitigating Rapport Bias of Large Language Models under Multi-Agent Social Interactions. Proceedings of ICLR.
.
2026. Scaffolded Vulnerability: Chatbot-Mediated Reciprocal Self-Disclosure and Need-Supportive Interaction in Couples. Proceedings of CHI.
.
2026. SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering. Proceedings of ICML. 2508.03448v2.pdf (3.31 MB)
2508.03448v2.pdf (3.31 MB).
2026. Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment. ICASSP. 2505.12669v1.pdf (360.69 KB)
2505.12669v1.pdf (360.69 KB).
2026. Text2Score: Generating Sheet Music From Textual Prompts. arXiv:2605.13431. 2605.13431v1.pdf (395.67 KB)
2605.13431v1.pdf (395.67 KB).
2025. Analysis and Synthesis of Audio with AI: from Neurological Disease to Accented Speech and Music. thesis_Jan.pdf (26.4 MB)
thesis_Jan.pdf (26.4 MB).
2025. Are we there yet? A brief survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges IEEE Transactions on Affective Computing. 2406.08809v1.pdf (156.19 KB)
2406.08809v1.pdf (156.19 KB).
2025. BandCondiNet: Parallel Transformers-based Conditional Popular Music Generation with Multi-View Features. Expert Systems with Applications. 130059 2407.10462v2.pdf (2.6 MB)
2407.10462v2.pdf (2.6 MB).
2025. Coarse-to-Fine Text-to-Music Latent Diffusion. Proceedings of ICASSP.
.
2025. Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics. arXiv:2510.05137.
.
2025. End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation. Proceedings of IJCNN, Rome, Italy.
.
2025. An exploration of controllability in symbolic music infilling. IEEE Access.
.
2025. Forecasting Bitcoin Volatility Spikes from Whale Transactions and Cryptoquant Data Using Synthesizer Transformer Models. IEEE Access. 13:117788-117807. SSRN-id4247684.pdf (5.05 MB)
SSRN-id4247684.pdf (5.05 MB).
2025. HHNAS-AM: Hierarchical Hybrid Neural Architecture Search using Adaptive Mutation Policies. arXiv:2508.14946.
.
2025. ImprovNet: Generating Controllable Musical Improvisations with Iterative Corruption Refinement. Proceedings of IJCNN.
.
2025. JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata. Proceedings of IJCNN, Rome, Italy.
.
2025. Leveraging LLM Embeddings for Cross Dataset Label Alignment and Zero Shot Music Emotion Prediction.
.
2025. MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection. arXiv:2505.20979.
.
2025. Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey. ACM Computing Surveys. 2402.17467.pdf (1.01 MB)
2402.17467.pdf (1.01 MB).
2025. PRESENT: Zero-Shot Text-to-Prosody Control. IEEE Signal Processing Letters. 2408.06827v1.pdf (367.55 KB)
2408.06827v1.pdf (367.55 KB).
2025. Royalties in the age of AI: paying artists for AI-generated songs. WIPO Magazine.
.
2025. Smart Timing for Mining: A Deep Learning Framework for Bitcoin Hardware ROI Prediction. 2512.05402v1.pdf (908 KB)
2512.05402v1.pdf (908 KB).
2025. SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning. Proceedings of the 6th Conference on AI Music Creativity (AIMC 2025), Brussels, Belgium, September 10th - 12th, 2025.
.
2025. Text2midi: Generating Symbolic Music from Captions. Proceedings of AAAI, Philadelphia. 2412.16526v2.pdf (569.51 KB)
2412.16526v2.pdf (569.51 KB).
2025. Towards the future of education: cyber-physical learning. Discover Education. 4:1–16.
.
2024. Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training. Proc. of IEEE Tencon, Singapore.
.
2024. Accented Text-to-Speech Synthesis with a Conditional Variational Autoencoder. Proc. of IEEE Tencon, Singapore.
.
2024. Coarse-to-Fine Text-to-Music Latent Diffusion. Audio Imagination: NeurIPS 2024 Workshop.
.
2024. DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech. Audio Imagination: NeurIPS 2024 Workshop.
.
2024. DeepUnifiedMom: Unified Time-series Momentum Portfolio Construction via Multi-Task Learning with Multi-Gate Mixture of Experts. arXiv:2406.08742. 2406.08742v1.pdf (1.06 MB)
2406.08742v1.pdf (1.06 MB).
2024. DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage. Proc. of IEEE Tencon, Singapore.
.
2024. Gamification and skills tree. Trends and Foresight Report on Cyber-Physical Learning.
.
2024. MidiCaps — A large-scale MIDI dataset with text captions. ISMIR. 2406.02255v1.pdf (699.83 KB)
2406.02255v1.pdf (699.83 KB).
2024. MIRFLEX: Music Information Retrieval Feature Library for Extraction. ISMIR, Late Breaking Demos. 2411.00469v1.pdf (89.86 KB)
2411.00469v1.pdf (89.86 KB).
2024. Modern Portfolio Construction with Advanced Deep Learning Models. SUTD. PhD Joel_Ong_Thesis.pdf (3.44 MB)
Joel_Ong_Thesis.pdf (3.44 MB).
2024. Mustango: Toward Controllable Text-to-Music Generation. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). pages 8293–8316. 2311.08355 (1).pdf (11.38 MB)
2311.08355 (1).pdf (11.38 MB).
2024. SNIPER Training: Variable Sparsity Rate Training For Text-To-Speech. Proc. of IEEE Tencon, Singapore. 2211.07283.pdf (435.22 KB)
2211.07283.pdf (435.22 KB).
2024. Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model. Expert Systems with Applications. 2311.00968.pdf (5.51 MB)
2311.00968.pdf (5.51 MB).
2023. Constructing Time-Series Momentum Portfolios with Deep Multi-Task Learning. Expert Systems with Applications. 230(120587) 2306.13661.pdf (707.95 KB)
2306.13661.pdf (707.95 KB).
2023. DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability. ICASSP. diffroll.pdf (2.2 MB)
diffroll.pdf (2.2 MB).
2023. A Domain-Knowledge-Inspired Music Embedding Space and a Novel Attention Mechanism for Symbolic Music Modeling. Proceedings of the 37th AAAI Conference on Artificial Intelligence. 2212.00973.pdf (1.74 MB)
2212.00973.pdf (1.74 MB).
2023. Learning accent representation with multi-level VAE towards controllable speech synthesis. IEEE Spoken Language Technology (SLT) Workshop.
.
2023. MERP: A Music Dataset with Emotion Ratings and Raters’ Profile Information. Sensors - Intelligent Sensors. 23(1) sensors-23-00382 (2).pdf (1.21 MB)
sensors-23-00382 (2).pdf (1.21 MB).
2023. A Multimodal Model with Twitter Finbert Embeddings for Extreme Price Movement Prediction of Bitcoin. Expert Systems with Applications. 2206.00648.pdf (3.26 MB)
2206.00648.pdf (3.26 MB).
2022. Computationally Efficient Physics Approximating Neural Networks for Highly Nonlinear Maps. 2022 International Conference on Research in Adaptive and Convergent Systems.
.
2022. Conditional Drums Generation using Compound Word Representations. EvoMUSART (EVO*) - Lecture Notes in Computer Science. 2202.04464.pdf (525.36 KB)
2202.04464.pdf (525.36 KB).
2022. Downscaling using Deep Convolutional Autoencoders, a case study for South East Asia. Egusphere preprint. egusphere-2022-234.pdf (8.99 MB)
egusphere-2022-234.pdf (8.99 MB).
2022. EmoMV: Affective Music-Video Correspondence Learning Datasets for Classification and Retrieval. Information Fusion. SSRN-id4189323.pdf (2.01 MB)
SSRN-id4189323.pdf (2.01 MB).
2022. A Gaussian mixture classifier model to differentiate respiratory symptoms using phonated /ɑː/ sounds. The 18th Australasian International Conference on Speech Science and Technology (SST). ahsounds.pdf (1018.01 KB)
ahsounds.pdf (1018.01 KB).
2022. HEAR 2021: Holistic Evaluation of Audio Representations. Proceedings of Machine Learning Research (PMLR): NeurIPS 2021 Competition Track. 2203.03022.pdf (406.58 KB)
2203.03022.pdf (406.58 KB).
2022. Jointist: Joint Learning for Multi-instrument Transcription and Its Applications. 2206.10805.pdf (427.51 KB)
2206.10805.pdf (427.51 KB).
2022. A Machine Learning Approach for MIDI to Guitar Tablature Conversion. Sound and Music Computing Conference (SMC). 25.pdf (528.42 KB)
25.pdf (528.42 KB).
2022. MusIAC: An extensible generative framework for Music Infilling Application with multi-level Control. EvoMUSART. 2202.05528.pdf (893.23 KB)
2202.05528.pdf (893.23 KB).
2022. Predicting emotion from music videos: exploring the relative contribution of visual and auditory information to affective responses. Arxiv preprint.
.
2022. Single Image Video Prediction with Auto-Regressive GANs. Sensors. 22:3533.
.
2022. Understanding Audio Features via Trainable Basis Functions. Arxiv preprint. 2204.11437.pdf (7.36 MB)
2204.11437.pdf (7.36 MB).
2022. A white paper on cyberphysical learning. White paper, Singapore University of Technology and Design. LSL_WhitePaper_Cyber-physical-Campus-Higher-Education.pdf (6.98 MB)
LSL_WhitePaper_Cyber-physical-Campus-Higher-Education.pdf (6.98 MB).
2021. aiSTROM - A roadmap for developing a successful AI strategy. IEEE Access.
.
2021. AttendAffectNet – Emotion Prediction of Movie Viewers Using Multimodal Fusion with Self-attention. Sensors. Special issue on Intelligent Sensors: Sensor Based Multi-Modal Emotion Recognition. sensors-21-08356.pdf (1.03 MB)
sensors-21-08356.pdf (1.03 MB).
2021. AttendAffectNet: Self-Attention based Networks for Predicting Affective Responses from Movies. Proceedings of the International Conference on Pattern Recognition (ICPR2020). 2010.11188.pdf (7.07 MB)
2010.11188.pdf (7.07 MB).
2021. Deep Neural Network Based Respiratory Pathology Classification Using Cough Sounds. Sensors. 21(16):5555. 2106.12174.pdf (6.52 MB)
2106.12174.pdf (6.52 MB).
2021. The Effect of Spectrogram Reconstructions on Automatic Music Transcription:An Alternative Approach to Improve Transcription Accuracy. Proceedings of the International Conference on Pattern Recognition (ICPR2020). 2010.09969.pdf (3.46 MB)
2010.09969.pdf (3.46 MB).
2021. Evaluating the Effectiveness of an Augmented Reality Game Promoting Environmental Action. Sustainability. 13(24):13912. sustainability-13-13912.pdf (16.23 MB)
sustainability-13-13912.pdf (16.23 MB).
2021. Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework. Proceedings of the International Joint Conference on Neural Networks (IJCNN). 2104.13056.pdf (857.78 KB)
2104.13056.pdf (857.78 KB).
2021. Hierarchical Recurrent Neural Networks for Conditional Melody Generation with Long-term Structure. Proceedings of the International Joint Conference on Neural Networks (IJCNN). 2102.09794.pdf (1015.73 KB)
2102.09794.pdf (1015.73 KB).
2021. Music, Computing, and Health: A roadmap for the current and future roles of music technology for healthcare and well-being. Music & Science. Preprint for OSF_Agres, Schaefer, Volk, et al. (2021)_Music & Science_watermark.pdf (4.07 MB)
Preprint for OSF_Agres, Schaefer, Volk, et al. (2021)_Music & Science_watermark.pdf (4.07 MB).
2021. Musical stylometry: Characterisation of music. Multivariate Humanities.
.
2021. ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data. ACM Multimedia.
.
2021. Revisiting the Onsets and Frames Model with Additive Attention. Proceedings of the International Joint Conference on Neural Networks (IJCNN). 2104.06607.pdf (1.52 MB)
2104.06607.pdf (1.52 MB).
2021. Underwater Acoustic Communication Receiver Using Deep Belief Network. IEEE Transactions on Communications. :1-1. 2102.13397.pdf (12.87 MB)
2102.13397.pdf (12.87 MB).
2020. Acoustic prediction of flowrate: varying liquid jet stream onto a free surface. IEEE International Conference on Signal Processing and Communications (SPCOM). preprint flow.pdf (1.01 MB)
preprint flow.pdf (1.01 MB).
2020. Asthmatic versus healthy child classification based on cough and vocalised /a:/ sounds. The Journal of the Acoustical Society of America (JASA). 148, EL253
.
2020. Data-driven 3D Scene Understanding. PhD
.
2020. A dataset and classification model for Malay, Hindi, Tamil and Chinese music. 13th Workshop on music and machine learning (MML) as part of ECML/PKDD. 2009.04459.pdf (234.8 KB)
2009.04459.pdf (234.8 KB).
2020. Generative Modelling for Controllable Audio Synthesis of Expressive Piano Performance. Workshop on Machine Learning for Music Discover (ML4MD) as part of ICML. 2006.09833.pdf (2.81 MB)
2006.09833.pdf (2.81 MB).
2020. The impact of Audio input representations on neural network based music transcription. Proceedings of the International Joint Conference on Neural Networks (IJCNN). 2001.09989.pdf (1.87 MB)
2001.09989.pdf (1.87 MB).
2020. Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling. ISMIR. 2007.15474.pdf (2.67 MB)
2007.15474.pdf (2.67 MB).
2020. nnAudio: An on-the-fly GPU Audio to Spectrogram Conversion Toolbox Using 1D Convolution Neural Networks. IEEE Access. nnAudio.pdf (10.2 MB)
nnAudio.pdf (10.2 MB).
2020. PerceptionGAN: Real-world image construction from provided text through perceptual understanding. 4th Int. Conf. on Imaging, Vision and Pattern Recognition (IVPR), and 9th Int. Conf. on Informatics, Electronics & Vision (ICIEV). perceptionGAN-preprint.pdf (2.83 MB)
perceptionGAN-preprint.pdf (2.83 MB).
2020. Regression-based music emotion prediction using triplet neural networks. Proceedings of the International Joint Conference on Neural Networks (IJCNN). 2001.09988.pdf (777.31 KB)
2001.09988.pdf (777.31 KB).
2020. Singing voice conversion with disentangled representations of singer and vocal technique using variational autoencoders. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 1912.02613.pdf (2.9 MB)
1912.02613.pdf (2.9 MB).
2020. Unsupervised disentanglement of pitch and timbre for isolated musical instrument sounds. Proceedings of the International Society of Music Information Retrieval (ISMIR).
.
2020. A variational autoencoder for music generation controlled by tonal tension. Joint Conference on AI Music Creativity (CSMC + MuMe). 2010.06230.pdf (622.82 KB)
2010.06230.pdf (622.82 KB).
2019. Development of Machine Learning for asthmatic and healthy voluntary cough - a proof of concept study. Applied Sciences. 9(14) applsci-09-02833.pdf (2.06 MB)
applsci-09-02833.pdf (2.06 MB).
2019. Doppler Invariant Demodulation for Shallow Water Acoustic Communications Using Deep Belief Networks. 16th IEEE Asia Pacific Wireless Communications Symposium (APWCS). 1909.02850.pdf (790.54 KB)
1909.02850.pdf (790.54 KB).
2019. The emergence of deep learning: new opportunities for music and audio technologies. Neural Computing and Applications. main_preprint.pdf (102.16 KB)
main_preprint.pdf (102.16 KB).
2019. A Hybrid Fuzzy Logic-Neural Network Approach For Multi-path Separation Of Underwater Acoustic Signals. 89th IEEE Vehicular Technology Conference. fuzzy logic.pdf (1.66 MB)
fuzzy logic.pdf (1.66 MB).
2019. The impact of musical structure on enjoyment and absorptive listening states in trance music. Music and Consciousness 2 - Worlds, Practices, Modalities.
.
2019. Latent space representation for multi-target speaker detection and identification with a sparse dataset using Triplet neural networks. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2019). 1910.01463.pdf (934.76 KB)
1910.01463.pdf (934.76 KB).
2019. Learning Disentangled Representations of Timbre and Pitch for Musical Instrument Sounds Using Gaussian Mixture Variational Autoencoders. ISMIR. jyun-ismir.pdf (5.62 MB)
jyun-ismir.pdf (5.62 MB).
2019. Machine Learning Research that Matters for Music Creation: A Case Study. Journal of New Music Research. 48(1):36-55. concert_paper_preprint.pdf (1.6 MB)
concert_paper_preprint.pdf (1.6 MB)