Past Talks

Current trends in speech deepfake detection and privacy protection

I’ll begin by introducing myself briefly. Then, I’ll provide an overview of my Ph.D. research on “Robust Speaker Representation …

This paper introduces a novel objective function for quality mean opinion score (MOS) prediction of unseen speech synthesis systems. …

We have several INTERSPEECH 2023 practice talks coming up! Thursday August 3rd at 4pm in Room 1706: Chang Zeng “Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms” Wednesday August 9 at 5pm: Lin Zhang

Automatic speaker verification has numerous studies widely used in applications such as user authentication, access control, and smart …

We have several ICASSP 2023 practice talks coming up! Tuesday April 18 at 11am: Xuan Shi “Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?” and “Use of Speaker Recognition Approaches for Learning and Evaluating Embedding Representations of Musical Instrument Sounds” Tuesday April 18 at 1pm: Xin Wang

Title: An Attention Based Approach for Automated Account Linkage in Federated Identity Management Abstract: Linking digital accounts belonging to the same user has progressed from a research topic to a foundation for security, user satisfaction, and developing next-generation services.

Title: Cyber Vaccine for Deepfake Immunity Abstract: Deepfakes pose an evolving threat to cybersecurity, which calls for the development of automated countermeasures. While considerable forensic research has been devoted to the detection and localisation of deepfakes, solutions for reversing fake to real are yet to be developed.

Title Analysing the Masked Predictive Coding Training Criterion for Pre-Training a Speech Representation Model Abstract Recent developments in pre-trained speech representation utilizing self-supervised learning (SSL) have yielded exceptional results on a variety of downstream tasks.

Fact verification is part of the fact checking task. In this study, we want to enable the fact verification task across language. We …