Jeremy H. M. Wong

University of Sydney — Australia

Computer Science · Physical Sciences

8h-index235citations38works0.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(27), Speech and Audio Processing(19), Music and Audio Processing(17), Natural Language Processing Techniques(7), Advanced Data Compression Techniques(3)

Publications38 total

Distilling a speech and music encoder with task arithmetic
2025
Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models
arXiv (Cornell University)·2025Open Access
A correlation-permutation approach for speech-music encoders model merging
arXiv (Cornell University)·2025Open Access
Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs
arXiv (Cornell University)·2025Open Access
Distilling a speech and music encoder with task arithmetic
arXiv (Cornell University)·2025Open Access
A comparison of three modes of online key word sign training to determine efficacy and acceptability in comparison to in-person key word sign training
Augmentative and Alternative Communication·2025· 1 cited
Semi-Supervised Learning for Robust Speech Evaluation
2024
Semi-supervised Learning For Robust Speech Evaluation
arXiv (Cornell University)·2024Open Access
Dataset-Distillation Generative Model for Speech Emotion Recognition
2024· 3 cited
Bounded Gaussian process with multiple outputs and ensemble combination
2024
Dataset-Distillation Generative Model for Speech Emotion Recognition
arXiv (Cornell University)·2024Open Access
Noise Robust Distillation of Self-Supervised Speech Models via Correlation Metrics
2024· 1 cited
Distilling Distributional Uncertainty from a Gaussian Process
2024
Noise robust distillation of self-supervised speech models via correlation metrics
arXiv (Cornell University)·2023Open Access
Distilling knowledge from Gaussian process teacher to neural network student
2023· 4 cited
Multiple output samples per input in a single-output Gaussian process
arXiv (Cornell University)·2023Open Access
Diarisation Using Location Tracking with Agglomerative Clustering
2022 IEEE Spoken Language Technology Workshop (SLT)·2023· 1 cited
Joint Speaker Diarisation and Tracking in Switching State-Space Model
2022 IEEE Spoken Language Technology Workshop (SLT)·2023
Modelling Inter-Rater Uncertainty in Spoken Language Assessment
IEEE/ACM Transactions on Audio Speech and Language Processing·2023· 1 cited
Variations of multi-task learning for spoken language assessment
Interspeech 2022·2022· 6 cited
page 1 of 2Next →

Frequent Co-authors

Nancy F. Chen(17), Mark Gales(9), Huayun Zhang(7), Fabian Ritter-Gutierrez(7), Hung-yi Lee(7), Eng Siong Chng(7), Yifan Gong(5), Jinyu Li(4), Eric Sun(4), Yifan Gong(4), Anton Ragni(4), Kuan-Po Huang(4), Dianwen Ng(4), Rui Zhao(3), Yu Wang(3), Xiong Xiao(3), Geyu Lin(3), Yi‐Cheng Lin(3), Amit Das(2), Zhong Meng(2)