Welcome to Sound and Music Computing Lab at National University of Singapore! The NUS Sound and Music Computing Lab strives to develop Sound and Music Computing (SMC) technologies, in particular Music Information Retrieval (MIR) technologies, with an emphasis on applications in e-Learning (especially computer-assisted music and language edutainment) and e-Health (especially computer-assisted music-enhanced exercise and therapy).
We seek to harness the synergy of SMC, MIR, mobile computing, and cloud computing technologies to promote healthy lifestyles and to facilitate disease prevention, diagnosis, and treatment in both developed countries and resource-poor developing countries.
The National University of Singapore (NUS) Sound and Music Computing Lab is pursuing research in Sound and Music Computing for Human Health and Potential (SMC4HHP) and has multiple research positions (RF, RA, PhD scholarships) available.
We are currently seeking two full-time Postdoctoral Research Fellows in automatic lyrics generation and automatic singing voice/speech evaluation. [Here is a detailed job description]
We have advised students from a wide range of disciplines and across many education levels. See our alumni here!
Wang, Y., Wei W., Gu, X., Guan, X., and Wang, Y., (2023). Disentangled Adversarial Domain Adaptation for Phonation Mode Detection in Singing and Speech. IEEE/ACM Transactions on Audio, Speech, and Language Processing (DOI: 10.1109/TASLP.2023.3317568).
Gu, X., Zeng, W., and Wang, Y., (2023, October). Elucidate Gender Fairness in Singing Voice Transcription, in 2023 ACM Multimedia Conference (MM'23).
Liu, H., Shi, M., and Wang, Y., (2023, August). Zero-Shot Automatic Pronunciation Assessment, in the 19th Annual Conference of the International Speech Communication Association (Interspeech 2023).
Zhao, J., Xia, G., and Wang, Y., (2023, August). Q&A: Query-Based Representation Learning for Multi-Track Symbolic Music re-Arrangement, in Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023). [code] [demo] [colab notebook]
Ou, L., Ma, X., Kan, M. Y., and Wang, Y., (2023, July). Songs Across Borders: Singable and Controllable Neural Lyric Translation, in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). [code] [demo]
Wang, Y., Wei, W., and Wang, Y., (2023, June). Phonation Mode Detection in Singing: A Singer Adapted Model, in ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023). IEEE.
Dai, S., Ma, X., Wang, Y. and Dannenberg, R. B. (2023). Personalized Popular Music Generation Using Imitation and Structure. Journal of New Music Research, pp.1-17.
Wei, W.*, Huang, H.*, Gu, X., Wang, H., and Wang, Y., (2022). Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization. Transactions on Machine Learning Research (12/2022).
Wu, X.*, Huang, H.*, Ding, Y., Wang, H., Wang, Y., and Xu, Q., (2023, February). FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation, in Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023). [video]
Huang, H., Gu, X., Wang H., Xiao C., Liu H., and Wang, Y., (2022, December). Extrapolative Continuous-time Bayesian Neural Network for Fast Training-free Test-time Adaptation, in Proceedings of Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 (NeurIPS 2022). [video]
Ou, L.*, Gu, X.*, and Wang, Y., (2022, December). Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription, in Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR 2022).
Ma, X., Liu, X., Zhang, B., and Wang, Y., (2022, December). Robust Melody Track Identification in Symbolic Music, in Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR 2022).
Zhao, J., Xia, G., and Wang, Y., (2022, December). Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-Attention, in Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR 2022). [code] [colab notebook] [video]
Zhao, J., Xia, G., and Wang, Y., (2022, December). Domain Adversarial Traning on Conditional Variational Auto-Encoder for Controllable Music Generation, in Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR 2022). [code] [demo] [video]
Gu, X.*, Ou, L.*, Ong, D., and Wang, Y., (2022, October). MM-ALT: A Multimodal Automatic Lyric Transcription System, in 2022 ACM Multimedia Conference (MM’22). (Top Paper Award) [demo]
Ma, X., Wang, Y., and Wang, Y., (2022, October). Content based User Preference Modeling in Music Generation, in 2022 ACM Multimedia Conference (MM’22). [demo 1] [demo 2]
Ou, L., Guo, Z., Benetos, E., Han, J., & Wang, Y. (2022, May). Exploring Transformer’s Potential on Automatic Piano Transcription, in ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022).
Ma, X., Wang, Y., Kan, M. Y., and Lee, W. S., (2021, October). AI-Lyricist: Generating Music and Vocabulary Constrained Lyrics, in 2021 ACM Multimedia Conference (MM’21). [lyrics demo] [synthsis demo]
Huang, H., Liu, H., Wang, H., Xiao, C., & Wang, Y. (2021, July). STRODE: Stochastic Boundary Ordinary Differential Equation, in International Conference on Machine Learning (ICML 2021). [code] [slides]
[Song Intelligibility Data] Ibrahim, K. M., Grunberg, D., Agres, K., Gupta, C., & Wang, Y. (2017). Intelligibility of sung lyrics: A pilot study, in Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017, Suzhou, China, October 23-27, 2017, 2017, pp. 686-693. [data]
[LyricFind Corpus] Ellis, R. J., Xing, Z., Fang, J., & Wang, Y. (2015). Quantifying Lexical Novelty in Song Lyrics. in Proceedings of the 16th International Society for Music Information Retrieval Conference, ISMIR 2015, Málaga, Spain, October 26-30, 2015, 2015, pp. 694-700. [data]
[NUS-48E Sung and Spoken Lyrics Corpus] Duan, Z., Fang, H., Li, B., Sim, K. C., & Wang, Y. (2013, October). The NUS sung and spoken lyrics corpus: A quantitative comparison of singing and speech. in Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2013 Asia-Pacific (pp. 1-9). IEEE. [data]
[2022.12] SLIONS-Kids: AI-empowered language learning mobile application. [video]
[2022.11] "Sound and Music Computing for Human Health and Potential" (SMC4HHP) Theme Seminar & Concert Event. [videos]
[2022.06] Our lab member Yuchen Wang won Outstanding Computing Project Prize from NUS School of Computing. [NUS News]
[2021.11] APSIPA Distinguished Lecture 1: Neuroscience-Inspired Sound and Music Computing (SMC) for Bilingualism and Human Potential – Wang Ye [video]
[2021.11] NUS Sound and Music Computing Lab Showcase at ISMIR 2021 [video]
[2021.11] Special Session on MIR for Human Health and Potential at ISMIR2021 [video]
[2021.08] Wang, Y., Keynote Speech at Computing Research Week Aug 2021, “Music & Wearable Computing for Health and Learning: a Decade-long Exploration on a Neuroscience-inspired Interdisciplinary Approach”, National University of Singapore [slides] [video]
[2019.04] NUS Computing Music Concert [video]
[2018.08] Sound & Music Computing Concert [video]
Addr: 11 Computing Dr, SG, 117416
Tel: (65) 6516 2980
Fax: (65) 6779 4580
Office: AS6 #04-08
Lab Director: A/Prof. Ye Wang