***
Hello! I am an enthusiastic artificial intelligence researcher. My strong curiosity has driven me to explore multiple areas, including multi-modal machine understanding, recognition, and generation. I am passionate about advancing AI to enhance functionality and develop purposeful solutions that better serve users. With dedication and hard work, I strive to make meaningful progress in the field.
I completed my master's and undergraduate studies in Statistics and Economics at the National University of Singapore (NUS).
Currently, I am pursuing a PhD in speech modelling at Nanyang Technological University (NTU), under the esteemed guidance of Prof. Eng-Siong Chng (NTU) and Dr. Bin Ma (Alibaba DAMO Academy).
My research interests focus on the domains of
#foundational model,
#automatic speech recognition (ASR),
#self-supervised learning,
#efficient tuning of large-scale models,
#speech synthesis,
#spoken dialogue,
#retrieval-augmented generation
Recent Publications (Non-Exhaustive)
2024
Are Soft Prompts Good Zero-shot Learners for Speech Recognition?
Dianwen Ng, Chong Zhang, Ruixi Zhang, Yukun Ma, Fabian Ritter-Gutierrez, Trung Hieu Nguyen, Chongjia Ni, Shengkui Zhao, Eng Siong Chng and Bin Ma.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced-Time Domain Monaural Speech Separation
Shengkui Zhao, Yukun Ma, Chongjia Ni, Chong Zhang, Hao Wang, Trung Hieu Nguyen, Kun Zhou, Jia Qi Yip, Dianwen Ng, Bin Ma.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
2023
deHuBERT: Disentangling Noise In A Self-Supervised Model For Robust Speech Recognition
Dianwen Ng, Ruixi Zhang, Jia Qi Yip, Zhao Yang, Jinjie Ni, Chong Zhang, Yukun Ma, Chongjia Ni, Eng Siong Chng and Bin Ma.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
Contrastive Speech Mixup For Low-resource Keyword Spotting
Dianwen Ng, Ruixi Zhang, Jia Qi Yip, Chong Zhang, Yukun Ma, Trung Hieu Nguyen, Chongjia Ni, Eng Siong Chng and Bin Ma.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
Adaptive Knowledge Distillation Between Text and Speech Pre-trained Models
Jinjie Ni, Yukun Ma, Wen Wang, Qian Chen, Dianwen Ng, Han Lei, Trung Hieu Nguyen, Chong Zhang and Bin Ma.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
Adapter-tuning with Effective Token-dependent Representation Shift for Automatic Speech Recognition
Dianwen Ng, Chong Zhang, Ruixi Zhang, Yukun Ma, Trung Hieu Nguyen, Chongjia Ni, Qian Chen, Wen Wang, Eng Siong Chng and Bin Ma.
INTERSPEECH 2023
Small Footprint Multi-channel Network for Keyword Spotting with Centroid Based Awareness
Dianwen Ng, Yang Xiao, Jia Qi Yip, Zhao Yang, Biao Tian, Qiang Fu, Eng Siong Chng and Bin Ma
INTERSPEECH 2023
Dual-Acoustic Linguistic Self-supervised Representation Learning for Cross-Domain Speech Recognition
Zhao Yang, Dianwen Ng, Chong Zhang, Xiao Fu, Rui Jiang, Wei Xi, Yukun Ma, Chongjia Ni, Eng Siong Chng, Bin Ma, Jizhong Zhao
INTERSPEECH 2023
ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
Jia Qi Yip, Tuan Truong, Dianwen Ng, Chong Zhang, Yukun Ma, Trung Hieu Nguyen, Chongjia Ni, Shengkui Zhao, Eng Siong Chng and Bin Ma
INTERSPEECH 2023
2022
I2CR: Improving Noise Robustness on Keyword Spotting using Inter-Intra Contrastive Regularization
Dianwen Ng, Jia Qi Yip, Tanmay Surana, Zhao Yang, Chong Zhang, Yukun Ma, Chongjia Ni, Eng Siong Chng and Bin Ma.
2022 Asia Pacific Signal and Information Processing Association (APSIPA) Annual Summit and Conference, 2022
ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spotting
Dianwen Ng, Yunqi Chen, Biao Tian, Qiang Fu, Eng Siong Chng
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals
Xiang Lan, Dianwen Ng, Shenda Hong, Mengling Feng
Association for the Advancement of Artificial Intelligence (AAAI), 2022
Educations
Doctor of Philosophy, School of Computer Science and Engineering, Nanyang Technological University (2021 - 2024)
Speech Processing, Automatic Speech Recognition, Self-supervised Learning
Master of Science, National University of Singapore (2018 - 2020)
Statistics
Computer Vision, Healthcare Informatics and Analytics
Bachelor of Science (Honours), National University of Singapore (2014 - 2018)
Double Major in Economics and Statistics
Specialising in Business Analytics and Statistical Finance
Thesis: Designing Artificial Intelligence for Games with Deep Reinforement Learning
Diploma, Nanyang Academy of Fine Arts - Central Conservatory of Music
Chinese Instruments Graded Examinations (Erhu)
Academic Services
Journal/Letter Reviewer:
IEEE Signal Processing Letters
Speech Communication
Conference/Workshop Reviewer:
Conference on Empirical Methods in Natural Language Processing (EMNLP)
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ISCA INTERSPEECH
International Symposium on Chinese Spoken Language Processing (ISCSLP)
International Conference on Asian Language Processing (IALP)
IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
MICCAI Workshop on Distributed, Collaborative and Federated Learning (DeCaF)
Random Achievements and Awards
INTERSPEECH 2024 Best student paper nominee
INTERSPEECH 2023, Dublin, Ireland, Travel Grant Recipient
APSIPA ASC 2022, Chiang Mai, Thailand, Travel Grant Recipient
Alibaba-NTU Talent Scholarship Programme Recipient
Kaggle Competition Expert