Si-Ioi (Herman) NG

Postdoctoral Scholar at College of Health Solutions, Arizona State University

B.Eng, Ph.D in Electronic Engineering, The Chinese University of Hong Kong

I'm a postdoctoral scholar working with Prof. Visar Berisha and Prof. Julie Liss at the College of Health Solutions at Arizona State University. I previously obtained my B.Eng and Ph. D in the Department of Electronic Engineering, The Chinese University of Hong Kong (CUHK), working with Prof. Tan Lee.
My research focuses on the application and responsible development of clinical speech AI that integrates spoken-language processing, clinical speech science and machine learning (ML) to assess various health conditions through speech. I co-developed a large-scale Cantonese corpus of children's speech collected from ~2000 pre-schooler. Recently I also co-organised a tutorial in "Responsible Development and Translation of Clinical Speech Analytics" at Interspeech 2024, and I'm currently leading an large-scale overview study on the relevant topic.

Education

Education:
B. Eng in Electronic Engineering, The Chinese University of Hong Kong, 2018
Ph. D in Electronic Engineering, The Chinese University of Hong Kong, 2023
Supervisor: Prof. Tan Lee.
Thesis:
Automatic Detection of Speech Sound Disorder in Cantonese-speaking Preschool Children

Contact

Skills

Research Interest: Clinical speech AI; Spoken-language resource development; Spoken-language technology for Children; Speech and physical wellness; Cognitive impairment and Alzheimer’s disease; Forced alignment tools
Research skills: Spoken-language processing (speech recognition, speaker verification, text-to-speech synthesis); Signal processing; Natural language processing; Machine Learning; Statistics; Pathological speech processing
Programming: Python, MATLAB, R, Shell
Toolkit: PyTorch, Tensorflow, Kaldi, Praat, Librosa, PyAudio, HuggingFace (Large-language model and speech language model)
Language: Cantonese (native), English (fluent), Mandarin (fluent), Japanese (elementary)

Teaching

Co-instructor in EEE 598 - Special Topics: Speech and Audio Processing and Perception (ASU)
Mentor in ELEG 4998 & ELEG 4999 (Thesis studies) - Supervised 5 Bachelor's thesis and 1 Master's thesis
Lead TA in ENGG 2030 - Signal and Systems (CUHK)
TA in ELEG 2201 - Digital Circuits and Computing Systems (CUHK)

Selected Works

S. -I. Ng, C. W. -Y. Ng, J. Wang and T. Lee, “Automatic Detection of Speech Sound Disorder in Cantonese- Speaking Pre-School Children,” in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 4355-4368, 2024.
S. -I. Ng, L. Xu, I. Siegert, N. Cummins, N. R. Benway, J. Liss and V. Berisha, “An End-to-End Overview of Clinical Speech AI”, IEEE/ACM Transactions on Audio, Speech and Language Processing (Invited Overview Paper Under Review,)
S. -I. Ng, P. S. Ambadi, P. Kadambi, K. D. Mueller, J. Liss and V. Berisha, “Assessing Limits of Clinical Speech Features for Detecting Alzheimer’s Disease via Classification Bounds.” (Under Preparation)
S. -I. Ng, P. S. Ambadi, K. D. Mueller, J. Liss and V. Berisha, “Automated Extraction of Spatio-Semantic Graphs for Identifying Cognitive Impairment,” Proc. ICASSP, 2025, pp. 1-5.
S. -I. Ng, L. Xu, K. D. Muller, J. Liss and V. Berisha, “Segmental and Suprasegmental Speech Foundation Models for Classifying Cognitive Risk Factors: Evaluating Out-of-the-Box Performance”, Proc. Interspeech, 2024, pp. 917-921.
S. -I. Ng, C. W. -Y. Ng and T. Lee, “A Study on Using Duration and Formant Features in Automatic Detection of Speech Sound Disorder in Children,” in Proc. Interspeech, 2023, pp. 4643–4647.
S. -I. Ng, C. W. -Y. Ng, J. Wang and T. Lee, “Automatic Detection of Speech Sound Disorder in Child Speech Using Posterior-based Speaker Representations,” in Proc. Interspeech, 2022, pp. 2853–2857.
S. -I. Ng, R. Ma, T. Lee and R. K. -W. Sum, “Acoustical Analysis of Speech Under Physical Stress in Relation to Physical Activities and Physical Literacy,” in Proc. Speech Prosody, 2022, pp. 200–204.
J. Li, S. -I. Ng and T. Lee, “Improving Text-Independent Speaker Verification with Auxiliary Speakers Using Graph,” Proc. Automatic Speech Recognition and Understanding Workshop (ASRU), 2021, pp. 198-205.
S. -I. Ng, C. W. -Y. Ng, J. Li and T. Lee, “Detection of Consonant Errors in Disordered Speech Based on Consonant-Vowel Segment Embedding,” in Proc. Interspeech, 2021, pp. 2931–2935.
S. -I. Ng and T. Lee, “Automatic Detection of Phonological Errors in Child Speech Using Siamese Recurrent Autoencoder,” in Proc. Interspeech, 2020, pp. 4476–4480. (Best Student Paper Award Finalist)
S. -I. Ng, C. W. -Y. Ng, J. Wang, T. Lee, K. Y. -S. Lee and M. C. -F. Tong “CUCHILD: A Large-Scale Cantonese Corpus of Child Speech for Phonology and Articulation Assessment,” in Proc. Interspeech, 2020, pp. 424–428. (Co-First Author)
J. Wang, S. -I. Ng, D. Tao, C. W. -Y. Ng and T. Lee, “A study on acoustic modeling for child speech based on multi-task learning,” in Proc. International Symposium on Chinese Spoken Language Processing (ISCSLP), 2018, pp. 389–393.

Selected Awards

Talent Development Scholarship --- Education Bureau, Hong Kong SAR Government (2021)
INTERSPEECH Travel Grant --- International Speech Communication Association (2020)
Scholarship for Postgraduate Studies --- Fundo do Ensino Superior, Macau (2018 - 2021)
Third Prize (Information Technology) --- National Challenge Cup of Science and Technology (2019)
Gold Prize --- HKEIA Innovation & Technology Project Competition Award (2018)
First Prize and Designated Award (Information Technology) --- Hong Kong University Student Innovation and Entrepreneurship Competition (2018)
Charles Kao Scholarship --- The Chinese University of Hong Kong (2016)
Scholarship for Undergraduate Studies --- Direcção dos Serviços de Educação e Juventude, Macau (2016-2018)

About Me

I'm a classical music lover. I hold a DipABRSM in cello performance. I was a cellist in the Macau Youth Symphony Orchestra and performed internationally. I'm particularly fond of music by Bach, Schubert and Brahms.
I maintain an active lifestyle. I do sports including basketball, hiking, cycling, swimming, gym workout, running and snooker.